CN120338436A

CN120338436A - Port cargo intelligent dispatching system and method based on big data analysis

Info

Publication number: CN120338436A
Application number: CN202510787332.7A
Authority: CN
Inventors: 谢圣伟; 方基成; 张梦曜
Original assignee: Guangdong Tuowei Tianhai Technology Co ltd
Current assignee: Guangdong Wuliu Digital Technology Co ltd
Priority date: 2025-06-13
Filing date: 2025-06-13
Publication date: 2025-07-18
Anticipated expiration: 2045-06-13
Also published as: CN120338436B

Abstract

The present invention discloses a port cargo intelligent dispatching system and method based on big data analysis, and relates to the field of port cargo dispatching data processing technology. The system includes an environmental collection and evaluation module, a first comparative analysis and calling module of a cargo intelligent dispatching distributed computing node, and a second comparative analysis and calling module of a cargo intelligent dispatching distributed computing node. The present invention optimizes cargo environment monitoring, optimizes equipment operation efficiency, and dynamically allocates computing resources. The three constitute an intelligent closed-loop optimization system of "environment-equipment-computing power". Through data collection at the perception layer of the Internet of Things, digital twin modeling, and edge cloud computing, the all-round efficiency improvement of port operations from physical infrastructure to digital decision-making systems is achieved, which solves the problem in the prior art that the port cargo intelligent dispatching system is insufficient in accuracy in adapting to the distributed dispatching environment under extreme weather.

Description

Port cargo intelligent scheduling system and method based on big data analysis

Technical Field

The invention relates to the technical field of port cargo scheduling data processing, in particular to a port cargo intelligent scheduling system and method based on big data analysis.

Background

With the rapid development of international trade, throughput of ports as logistics hubs is continuously increased, and the traditional manual scheduling mode is low in efficiency and difficult to meet requirements due to the problems of asymmetric information, decision delay and the like. The maturity of technologies such as big data, thing networking, artificial intelligence provides new thinking for the harbour dispatch, optimizes the resource allocation through real-time data analysis and intelligent algorithm, becomes the necessary choice of trade upgrading, and technology degree of depth fuses and automatic upgrading, and future harbour dispatch will be degree of depth fuses big data, cloud calculates, thing networking, 5G and AI technique, realizes millisecond data response and full flow automation. The intelligent dispatching system opens up inland transportation networks such as ports, railways, highways and the like, and realizes cross-regional coordination.

The conventional port cargo intelligent scheduling system based on big data analysis is realized by utilizing machine learning to predict cargo throughput, ship arrival time and the like, optimizing resource allocation, and generating optimal loading and unloading sequence and path planning by combining operation study and reinforcement learning with an LSTM time sequence model which is excellent in demand prediction. And the goods and equipment state data are acquired in real time through technologies such as a sensor, RFID and the like, so that the full-flow tracking is supported.

The port management method, system and equipment based on the digital intelligent algorithm are disclosed in CN119151403A, and comprise the steps of collecting cargo information, ship information and vehicle information, preprocessing, conducting intelligent berth planning according to the preprocessed ship information to obtain berth information, conducting intelligent allocation planning according to the preprocessed cargo information, the preprocessed vehicle information and the berth information to obtain allocation information, collecting port storage information, conducting intelligent stockpiling planning according to the allocation information in combination with the port storage information to obtain stockpiling information, conducting intelligent position selection according to the berth information, allocation information and stockpiling information to obtain position selection parameters and position selection tasks, and conducting automatic box distribution according to the position selection parameters and the position selection tasks to realize port real-time scheduling.

For example, the invention patent publication number CN116542488B discloses a port scheduling method and system based on artificial intelligence, which comprises the steps of calculating navigation parameters of each ship according to cargo properties, ship tonnage and ship type, sequencing each ship according to the sequence from big to small of the navigation parameters to obtain navigation sequences, constructing a ship scheduling model and a berth allocation model, constructing an objective function of the ship scheduling model by taking the minimum of the objective function of the ship scheduling model as an objective training ship scheduling model by taking the total scheduling time, the total waiting time and the loss of time value, calculating the scheduling time of each ship according to the navigation sequences by the ship scheduling model, constructing an objective function of the berth allocation model by taking the minimum of the objective function of the berth allocation model as an objective training berth allocation model, and allocating berths for each ship by the ship scheduling model.

However, in the process of implementing the technical scheme of the embodiment of the application, the application discovers that the above technology has at least the following technical problems:

In the prior art, under extreme weather, the port intelligent scheduling system faces multi-level risks, which comprise the influence of various factors such as a data sensing layer, an algorithm decision layer, an execution control layer and the like, so that the risks of dynamic scheduling and multi-mode intermodal stop and swing are greatly increased, the scheduling response time is greatly delayed, the response timeliness for coping with weather risk challenges is weaker, and the problem of insufficient response accuracy of the port cargo intelligent scheduling system for coping with distributed scheduling environments under extreme weather exists.

Disclosure of Invention

According to the port cargo intelligent scheduling system and the port cargo intelligent scheduling method based on big data analysis, the problem that in the prior art, the distributed scheduling environment adaptation response accuracy of the port cargo intelligent scheduling system is insufficient in response to extreme weather is solved, and the distributed scheduling environment adaptation response accuracy of the port cargo intelligent scheduling system in response to extreme weather is improved.

The embodiment of the application provides a port cargo intelligent dispatching system based on big data analysis, which comprises an environment acquisition evaluation module, a cargo intelligent dispatching distributed computing node first comparison analysis calling module and a cargo intelligent dispatching distributed computing node second comparison analysis calling module, wherein the environment acquisition evaluation module is used for evaluating and analyzing port cargo environment parameters and carrying out comparison analysis adjustment according to the port cargo environment parameters, the cargo intelligent dispatching distributed computing node first comparison analysis calling module is used for evaluating and analyzing the port dispatching equipment fluctuation parameters and carrying out comparison analysis adjustment according to the port dispatching equipment fluctuation parameters, and the cargo intelligent dispatching distributed computing node second comparison analysis calling module is used for carrying out comprehensive evaluation analysis on port dispatching distributed computing node equipment and carrying out comparison analysis adjustment according to comprehensive evaluation analysis results.

Further, according to the port cargo environment parameters, the intelligent scheduling environment assessment mutation assessment is carried out, if the port environment water level maximum value is equal to or greater than the port environment water level maximum value threshold or the unit time rainfall maximum value is equal to or greater than the port environment wind speed threshold, early warning is sent out and related personnel are notified to improve the port cargo intelligent scheduling early warning level to the highest level.

Further, carrying out port cargo intelligent scheduling environment assessment mutation assessment, which specifically comprises acquiring the highest value of the port environment salt fog concentration by a laser scattering method salt fog on-line monitor; extracting from a port cargo intelligent scheduling environment evaluation database to obtain a port environment seawater level historical average value, a port environment salt spray concentration historical average value, a port environment sea speed to port environment seawater level correction factor, a port environment rainfall historical average value, a port cargo environment characteristic change first scheduling specific gravity factor, a port cargo environment characteristic change second scheduling specific gravity factor and a port cargo environment characteristic change third scheduling specific gravity factor, performing duty ratio analysis on the port environment seawater level maximum value and the port environment seawater level historical average value, correcting the port environment seawater level correction factor through the port environment sea speed, correcting the port environment seawater level correction factor through the port cargo environment characteristic change first scheduling specific gravity factor to obtain a port cargo intelligent scheduling environment evaluation mutation first component, performing duty ratio analysis on the port environment salt spray concentration maximum value and the port environment salt spray concentration historical average value, correcting the port cargo environment characteristic change second scheduling specific gravity factor to obtain a port cargo intelligent scheduling mutation second component, performing duty ratio analysis on the port environment rainfall maximum value and the port environment rainfall historical average value, correcting the port cargo characteristic change third scheduling factor to obtain a port cargo intelligent scheduling mutation environment component, and obtaining a port cargo intelligent scheduling mutation first component through the port cargo intelligent scheduling mutation component, and carrying out coupling analysis on the port cargo intelligent scheduling environment assessment mutation second component and the port cargo intelligent scheduling environment assessment mutation third component to obtain a port cargo intelligent scheduling environment assessment mutation value.

Further, the specific process of performing comparative analysis adjustment according to the port cargo environment parameters comprises the steps of not adjusting if the port cargo intelligent scheduling environment assessment mutation value is smaller than the port cargo intelligent scheduling environment assessment mutation threshold, performing coupling analysis on the port cargo intelligent scheduling environment assessment mutation value and the real-time centralized calculation power load utilization rate of the port cargo intelligent scheduling resource center if the port cargo intelligent scheduling environment assessment mutation value is equal to or larger than the port cargo intelligent scheduling environment assessment mutation threshold, obtaining a port cargo intelligent scheduling resource center coupling value, wherein the port cargo intelligent scheduling resource center coupling value is used for quantitatively representing the relative scarce risk degree of schedulable resources of the port cargo intelligent scheduling resource center, notifying related personnel and temporarily not starting automatic distributed resource scheduling if the port cargo intelligent scheduling resource center coupling value is smaller than the port cargo intelligent scheduling resource center coupling threshold, and starting distributed resource scheduling if the port cargo intelligent scheduling resource center coupling value is equal to or larger than the port cargo intelligent scheduling resource center coupling threshold.

Further, the method comprises the steps of acquiring network delay of the port distributed scheduling equipment and network error rate of the port distributed scheduling equipment through a built-in tool of the port distributed scheduling equipment, directly extracting from an intelligent port cargo scheduling environment evaluation database to obtain a port distributed scheduling equipment network delay threshold, a port distributed scheduling equipment network error rate threshold, an average fault rate threshold of the port distributed scheduling equipment, a first scheduling proportion factor of port equipment scheduling characteristic change, a second scheduling proportion factor of port equipment scheduling characteristic change, a third scheduling proportion factor of port equipment scheduling characteristic change and a correction factor of port distributed scheduling equipment terminal interface salt spray corrosion to use time, performing duty ratio analysis on the port distributed scheduling equipment network delay and the port distributed scheduling equipment network delay threshold, correcting the port distributed scheduling equipment network delay threshold through the first scheduling proportion factor of port equipment scheduling characteristic change to obtain a first component of port distributed scheduling equipment performance evaluation fluctuation, performing duty ratio analysis on the port distributed scheduling equipment network error rate and the port distributed scheduling equipment network error rate threshold, correcting the second scheduling proportion factor of port equipment scheduling characteristic change to obtain a second scheduling characteristic change, correcting the port equipment scheduling characteristic of port equipment scheduling characteristic fluctuation characteristic change, and performing duty ratio analysis on the average fault rate of port distributed scheduling equipment performance component of port distributed scheduling equipment performance fluctuation component through the third scheduling characteristic change proportion factor of port distributed scheduling characteristic change of port equipment network error rate evaluation, and performing coupling analysis on the second component of the performance evaluation fluctuation of the port distributed scheduling equipment and the third component of the performance evaluation fluctuation of the port distributed scheduling equipment, and correcting a correction factor of the using time through salt spray corrosion of a port distributed scheduling equipment terminal interface to obtain a port distributed scheduling equipment performance evaluation fluctuation mutation value.

Further, according to the fluctuation parameters of the port dispatching equipment, comparison analysis adjustment is carried out, and the method specifically comprises the steps of recording corresponding port distributed dispatching equipment to be adjusted first nodes if the performance evaluation fluctuation mutation value of the port distributed dispatching equipment is smaller than the performance evaluation fluctuation mutation threshold of the port distributed dispatching equipment, recording corresponding port distributed dispatching equipment to be adjusted second nodes if the performance evaluation fluctuation mutation value of the port distributed dispatching equipment is equal to or larger than the performance evaluation fluctuation mutation threshold of the port distributed dispatching equipment, carrying out corrosion prevention and dehumidification emergency treatment, carrying out descending order arrangement on the performance evaluation fluctuation mutation value of the port distributed dispatching equipment corresponding to the second nodes to be adjusted of the port distributed dispatching equipment, and gradually transferring corresponding calculation tasks to the port distributed dispatching equipment to be adjusted first nodes according to descending order of the arranged port distributed dispatching equipment to be adjusted second nodes.

The comprehensive evaluation analysis method comprises the steps of directly extracting a port cargo intelligent dispatching equipment distributed computing power resource comprehensive first dispatching specific gravity factor, a port cargo intelligent dispatching equipment distributed computing power resource comprehensive second dispatching specific gravity factor and a port cargo distributed dispatching equipment local temperature rising rate from a port cargo intelligent dispatching environment evaluation database to obtain a port cargo intelligent dispatching equipment distributed computing power resource comprehensive second component, coupling analysis is conducted on the port cargo intelligent dispatching equipment distributed computing power resource comprehensive risk value correction factor through the port cargo intelligent dispatching equipment distributed computing power resource comprehensive first dispatching specific gravity factor, the port cargo intelligent dispatching environment evaluation mutation value is obtained, the port cargo intelligent dispatching equipment distributed computing power resource comprehensive risk first component is obtained, the port cargo distributed dispatching equipment distributed computing power resource comprehensive risk value is obtained through coupling analysis of the port cargo intelligent dispatching equipment distributed computing power resource comprehensive second component, and the port cargo intelligent dispatching equipment distributed computing power resource comprehensive risk value correction factor is obtained through the port cargo intelligent dispatching equipment distributed computing power resource comprehensive risk value correction factor.

Further, according to the comprehensive evaluation analysis result, the comparison analysis adjustment is carried out, and the method specifically comprises the steps that if the comprehensive risk value of the distributed computing power resources of the intelligent port cargo scheduling equipment is smaller than the comprehensive risk threshold of the distributed computing power resources of the intelligent port cargo scheduling equipment, the second nodes to be adjusted of the distributed port scheduling equipment after arrangement gradually transfer corresponding computing tasks to the first nodes to be adjusted of the distributed port scheduling equipment according to descending arrangement sequence, the corresponding intelligent port cargo scheduling equipment according to the predefined percentage after arrangement according to descending arrangement is recorded as secondary high-order computing power nodes, and computing power resources of the predefined computing power percentage are reserved for the secondary high-order computing power nodes.

Further, the method comprises the steps of carrying out comparison analysis adjustment according to comprehensive evaluation analysis results, and further comprising the steps of if the comprehensive risk value of the distributed computing power resources of the intelligent port cargo scheduling equipment is equal to or greater than the comprehensive risk threshold of the distributed computing power resources of the intelligent port cargo scheduling equipment, lifting the rotating speed of a cooling fan of the corresponding intelligent port cargo scheduling equipment, starting a liquid cooling system of the corresponding intelligent port cargo scheduling equipment, carrying out descending arrangement according to the comprehensive risk value of the distributed computing power resources of the intelligent port cargo scheduling equipment, marking the intelligent port cargo scheduling equipment within the corresponding predefined percentage as a high-order computing power node according to the predefined percentage, switching a wireless link of the intelligent port cargo scheduling equipment to an optical fiber private network, and stopping distributing computing power tasks to the intelligent port cargo scheduling equipment.

The embodiment of the application provides an intelligent port cargo scheduling method based on big data analysis, which is characterized by comprising the specific steps of carrying out evaluation analysis on port cargo environment parameters, carrying out comparison analysis adjustment according to port cargo environment parameters, carrying out evaluation analysis on port scheduling equipment fluctuation parameters, carrying out comparison analysis adjustment according to port scheduling equipment fluctuation parameters, carrying out comprehensive evaluation analysis on port scheduling distributed computing node equipment, and carrying out comparison analysis adjustment according to comprehensive evaluation analysis results.

One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:

1. According to the intelligent closed-loop optimization system for the environment-equipment-computing power through cargo environment monitoring optimization, equipment operation efficiency optimization and computing resource dynamic allocation, the intelligent closed-loop optimization system is formed, and through the sensing layer data acquisition of the Internet of things, digital twin modeling and edge cloud computing, the comprehensive efficiency improvement from a physical infrastructure to a digital decision system of port operation is further realized, and the problem that in the prior art, the distributed scheduling environment adaptation response accuracy of the port cargo intelligent scheduling system under extreme weather is insufficient is solved.

2. According to the port scheduling equipment fluctuation parameters, the comparison analysis adjustment is carried out, the maintenance period is dynamically adjusted through the salt spray corrosion correction factors, when the typhoon quaternary salt spray concentration is increased, the task migration energy consumption is reduced, and the corrosion loss is reduced by the nitrogen spraying system, so that the port has the intelligent capability of environment self-adaption, risk self-treatment and resource self-allocation, and the environment adaptability of the port cargo intelligent scheduling system is improved.

3. According to the comprehensive evaluation analysis result, the comparison analysis adjustment is carried out, the task migration is triggered based on the calculation power risk value, the calculation power resource is reserved to cope with the sudden demand, the high-priority task zero interruption is ensured, the emergency response speed is improved, the automatic starting heat dissipation enhancement is carried out, the chip junction temperature is reduced, the equipment frequency reduction probability is reduced, the secondary high-level node pre-allocation mechanism improves the processing capacity of the sudden task, the closed loop of 'risk real-time perception-resource dynamic adaptation-efficiency continuous optimization' is further realized, the comprehensive fault rate of port dispatching distributed computing node equipment under extreme weather is reduced, and the energy efficiency is improved.

Drawings

Fig. 1 is a schematic structural diagram of a port cargo intelligent dispatching system based on big data analysis according to an embodiment of the present application.

Fig. 2 is a schematic flow chart of comparison analysis adjustment according to parameters of a port cargo environment according to an embodiment of the present application.

Fig. 3 is a schematic flow chart of comparative analysis adjustment according to fluctuation parameters of a port scheduling device according to an embodiment of the present application.

Fig. 4 is a schematic flow chart of comprehensive evaluation analysis for port scheduling distributed computing node devices according to an embodiment of the present application.

Fig. 5 is a schematic diagram of a port cargo intelligent scheduling method based on big data analysis according to an embodiment of the present application.

Detailed Description

According to the port cargo intelligent scheduling system and method based on big data analysis, the problem that in the prior art, the port cargo intelligent scheduling system is insufficient in response accuracy of the distributed scheduling environment adaptation under extreme weather is solved, the intelligent closed loop optimization system of environment-equipment-computing power is formed through cargo environment monitoring optimization, equipment operation efficiency optimization and computing resource dynamic allocation, and the comprehensive efficiency improvement from port operation physical infrastructure to a digital decision system is realized through data acquisition of an Internet of things sensing layer, digital twin modeling and edge cloud computing.

In order to better understand the above technical solutions, the following detailed description will refer to the accompanying drawings and specific embodiments.

The port cargo intelligent dispatching system based on big data analysis provided by the embodiment of the application comprises an environment acquisition evaluation module, a cargo intelligent dispatching distributed computing node first comparison analysis calling module and a cargo intelligent dispatching distributed computing node second comparison analysis calling module, wherein the environment acquisition evaluation module is used for evaluating and analyzing port cargo environment parameters and carrying out comparison analysis adjustment according to the port cargo environment parameters, the cargo intelligent dispatching distributed computing node first comparison analysis calling module is used for evaluating and analyzing port dispatching equipment fluctuation parameters and carrying out comparison analysis adjustment according to the port dispatching equipment fluctuation parameters, and the cargo intelligent dispatching distributed computing node second comparison analysis calling module is used for carrying out comprehensive evaluation analysis on port dispatching distributed computing node equipment and carrying out comparison analysis adjustment according to comprehensive evaluation analysis results.

In this embodiment, the wind speed sensor is used to collect and obtain the ambient wind speed of the port, for example, an ultrasonic wind speed sensing device without a mechanical transmission structure is configured at the top end of a fixed structure with the vertical height exceeding a preset threshold in the port area, including but not limited to a shore monitoring tower body, a top platform of a large loading and unloading device and the top of a meteorological observation facility. The ultrasonic wind speed sensing device is coupled with the edge computing node through the industrial grade communication gateway, wherein a real-time data processing algorithm is arranged in the edge computing node, and response delay of the ultrasonic wind speed sensing device meets the preset time sequence requirement of the port operation safety control system.

The highest value of the sea water level in the port environment is acquired and obtained through a water level sensor, for example, an electromagnetic wave reflection type water level sensing device is adopted by a water level monitoring module, and the installation position of the water level monitoring module comprises a port breakwater structure.

The method comprises the steps of collecting and obtaining the highest rainfall value in unit time through a rainfall sensor, installing a mechanical tipping bucket metering device at an elevation datum point of a storage yard area for detecting ponding risk parameters of a solid bulk cargo storage area, arranging a composite monitoring terminal at a key node of a drainage pipe network, integrating a flow detection unit and a liquid level sensing unit, enabling an output signal of the composite monitoring terminal and a drainage pump station control system to form a closed-loop control loop, and arranging an extensible communication module in a container storage area, wherein the module is connected with a plurality of rainfall detection terminals through a standard industrial bus protocol to form a meshed monitoring array.

In the embodiment, the distributed port cargo intelligent dispatching environment monitoring points are numbered,The number of the monitoring points of the intelligent dispatching environment of the distributed port cargoes is represented,,And the total number of the number numbers of the monitoring points of the intelligent dispatching environment of the distributed port cargoes is represented.

Represent the firstThe port cargo intelligent scheduling environment assessment mutation values of the distributed port cargo intelligent scheduling environment monitoring points are used for quantifying mutation degree values of environments where software and hardware equipment required by port cargo intelligent scheduling is located.

;

Represent the firstAnd the highest value of the sea water level in the port environment of the intelligent dispatching environment monitoring point of the distributed port cargoes. The highest value of the sea water level in the port environment is acquired through a water level sensor.

The historical average value of the sea water level in the port environment is represented and extracted from the intelligent dispatching environment evaluation database of the cargo in the port.

The sustained sea wind can create tangential stresses on the sea surface, resulting in momentum transfer of the body of water in the direction of the wind field. When the wind direction forms a specific angle with the coastline, the surface layer seawater is transported and accumulated to the coast under the continuous action of the shoreline, so that the actual water level is obviously higher than the theoretical value predicted by the tide model. The wave break generated by the high-frequency gust can form climbing effect in the near-shore area, and further raise the instantaneous water level. Meanwhile, when typhoons or strong cyclones pass through the environment, storm surge can be caused due to the synergistic effect of the wind speed of the sea wind and the sudden drop of the air pressure. At this time, the water level correction factor needs to be dynamically amplified to reflect the nonlinear influence of the wind field and the air pressure coupling on the water level.

Represent the firstAnd the port environment sea water level correction factors of the port environment sea water wind speed at the intelligent dispatching environment monitoring points of the distributed port cargoes. The value ranges from 0 to 1. The harbour environment sea water level correction factors of the harbour environment sea water speed are extracted from a harbour cargo intelligent scheduling environment evaluation database, and specific acquisition examples are that an ultrasonic anemometer is adopted and deployed in a harbour high exposure area (such as a lighthouse and an overhead monitoring tower), so that a main channel and a loading and unloading operation area are ensured to be covered, and building shielding is avoided. Real-time water level data is obtained from port tidal monitoring stations, combined with historical averages (e.g., chart depth references). The wind speed and tide data are subjected to time stamp alignment, and abnormal values (such as abrupt change values caused by sensor faults) are removed. Interpolation algorithms (e.g., cubic splines) are used to fill in missing data. And determining fitting coefficients through least square fitting historical data, and cross-verifying to avoid over-fitting. The training set (70%) and the test set (30%) were divided. And obtaining a mapping relation between the real-time wind speed value and the corresponding port environment sea water level correction factor, and inputting the real-time wind speed value to obtain the corresponding port environment sea water level correction factor.

Represent the firstThe highest value of the salt fog concentration in the port environment of the intelligent dispatching environment monitoring point of the distributed port cargo is acquired by a laser scattering method salt fog on-line monitor, the salt particle concentration in the air is measured by a laser scattering principle, and the salt fog content is output in real time by combining environmental parameters such as temperature, humidity and the like. The laser scattering method salt spray on-line monitor supports wall-hanging or guide rail installation, is suitable for a narrow space, is convenient to integrate with a monitoring system, is suitable for coastal and offshore high salt spray environments, and can stably operate for a long time.

The historical average value of the salt fog concentration in the port environment is represented and extracted from an intelligent dispatching environment evaluation database of the port goods.

Represent the firstThe highest harbour environment rainfall value of the intelligent dispatching environment monitoring points of the distributed harbour cargoes is acquired through the mechanical tipping bucket metering device.

The historical average value of the rainfall in the port environment is represented and extracted from the intelligent dispatching environment evaluation database of the port goods.

The first dispatching proportion factor representing the characteristic change of the port cargo environment is directly extracted from the port cargo intelligent dispatching environment evaluation database.

And the second dispatching proportion factor representing the characteristic change of the port cargo environment is directly extracted from the port cargo intelligent dispatching environment evaluation database.

And the third scheduling proportion factor representing the characteristic change of the port cargo environment is directly extracted from the port cargo intelligent scheduling environment evaluation database.

The temperature suddenly changes, such as abnormal fluctuation (such as cold wave or hot wave) with the temperature change amplitude exceeding the historical average value in 24 hours, the density of the seawater is increased, the volume is contracted, the tide level abnormality is possibly caused, and the extremely high temperature accelerates evaporation to indirectly influence the water level balance. Sudden changes in temperature (e.g., cold front passing) often accompany heavy rainfall or heavy rain, directly affecting port drainage system loads. High temperature accelerates evaporation of seawater, salt fog concentration increases, low temperature inhibits evaporation, but salt fog distribution can be indirectly influenced by changing humidity.

An example of construction of the mapping relation between the ambient temperature and the corresponding specific gravity is as follows, a high-precision temperature sensor is deployed in a port key area (such as a wharf and a warehouse), and temperature data is collected in real time. Historical temperature shock events (such as cold and hot waves) and corresponding port operation data are extracted. Outliers (such as abrupt values caused by sensor faults) are removed, and the missing data is filled in by using a moving average method. And carrying out normalization processing on the temperature, and calculating the temperature change rate. And (3) dynamically mapping the temperature abrupt change and three scheduling proportion factors, and counting mutation frequencies of three evaluation dimensions in different temperature change intervals. And constructing different contribution degree mapping relations of water levels, salt fog and rainfall in each interval, obtaining mapping relations of the environment temperature, corresponding port cargo environment characteristic change first scheduling specific gravity factors, port cargo environment characteristic change second scheduling specific gravity factors and port cargo environment characteristic change third scheduling specific gravity factors, inputting the environment temperature, and obtaining corresponding port cargo environment characteristic change first scheduling specific gravity factors, port cargo environment characteristic change second scheduling specific gravity factors and port cargo environment characteristic change third scheduling specific gravity factors.

Further, the specific process of performing comparative analysis adjustment according to the port cargo environment parameters comprises the steps of not adjusting if the port cargo intelligent scheduling environment assessment mutation value is smaller than the port cargo intelligent scheduling environment assessment mutation threshold, multiplying the port cargo intelligent scheduling environment assessment mutation value by the real-time centralized calculation power load utilization rate of the port cargo intelligent scheduling resource center if the port cargo intelligent scheduling environment assessment mutation value is equal to or larger than the port cargo intelligent scheduling environment assessment mutation threshold, obtaining a port cargo intelligent scheduling resource center coupling value, wherein the port cargo intelligent scheduling resource center coupling value is used for quantitatively representing the relative scarce risk degree of schedulable resources of the port cargo intelligent scheduling resource center, notifying related personnel and temporarily not starting automatic distributed resource scheduling if the port cargo intelligent scheduling resource center coupling value is smaller than the port cargo intelligent scheduling resource center coupling threshold, and starting distributed resource scheduling if the port cargo intelligent scheduling resource center coupling value is equal to or larger than the port cargo intelligent scheduling resource center coupling threshold.

In this embodiment, as shown in fig. 2, a flow chart of comparative analysis adjustment according to the port cargo environment parameters is provided in the embodiment of the present application.

The method is to send out a notification to related personnel and temporarily not start the automatic distributed resource scheduling, so that the related personnel can judge whether the distributed resource scheduling needs to be manually adjusted.

In the distributed port cargo intelligent dispatching system, whether the distributed computing power resource (edge calculation) needs to be dispatched or not is judged, real-time evaluation based on the environment mutation value is needed, and the system load and the service requirement are combined. The following specific judgment logic, technical steps and system adjustment scheme:

And (3) state monitoring, namely monitoring the computing power (CPU/GPU utilization rate), storage and network states of the edge nodes in real time.

Task segmentation and distribution, namely, task segmentation, namely, dividing a centralized task into subtasks (such as water level prediction, salt spray diffusion simulation and path planning).

The distribution rule is that a priority task, namely a high real-time task (such as typhoon path prediction) is distributed to the nearby edge nodes. Data intensive tasks-salt spray concentration analysis is assigned to nodes where storage resources are sufficient.

And performing edge node task execution, namely performing salt spray diffusion simulation, namely running a Gaussian diffusion model on the edge node based on temperature shock data, obtaining a specific salt spray diffusion simulation condition according to the Gaussian diffusion model, constructing a diffusion dynamics model based on a Navier-Stokes equation, and simulating the influence of wind speed and temperature on salt spray migration. And training an DQN model, defining a reward function (obstacle avoidance, low energy consumption and short time delay), and generating a global optimal path. The automated dispatch transport vehicle transports through the globally optimal path.

The adjustment scheme of the port cargo intelligent scheduling system called by starting the distributed resource scheduling is exemplified by the task priority reassignment, wherein when the temperature rises to be more than thirty degrees, the salt spray anti-corrosion operation priority is increased to the highest level, and the low-priority tasks (such as inventory) are suspended. When the temperature drop is greater than thirty degrees, the scheduling frequency of the antifreeze spraying equipment is increased by 3 times.

And (3) linkage of automatic equipment:

The edge node directly controls the wharf gantry crane to decelerate (when the wind speed is larger than 15 m/s) and the container stacking machine to lock (when the salt fog concentration is larger than 100 mu g/m 3).

And (3) energy management:

the edge computing node dynamically adjusts power consumption (e.g., enters a low power mode when idle) based on the task load.

And (3) incremental learning, namely periodically uploading local data to the cloud end by the edge node, and updating global model parameters.

Through the scheme, the centralized calculation bottleneck can be effectively relieved, and the instantaneity and the environmental adaptability of the intelligent port scheduling system are improved.

In this embodiment, for the collected device parameters, the distributed computing power scheduling device invoked by the distributed resource scheduling is specifically targeted for the above.

The monitoring points of the distributed port scheduling facility are numbered,A number representing the monitoring point of the distributed port dispatch,,And the total number of the number numbers of the monitoring points of the distributed port scheduling equipment is represented.

Represent the firstIntelligent dispatching environment monitoring point for distributed port cargoesThe port distributed scheduling equipment performance evaluation fluctuation mutation value of each distributed port scheduling equipment monitoring point is used for quantifying mutation degree value of environment inside software and hardware equipment required by port cargo intelligent scheduling.

The distributed port cargo intelligent dispatching environment monitoring points at least correspond to one distributed port dispatching equipment monitoring point, in actual deployment, a plurality of distributed port dispatching equipment monitoring points are arranged inside specific distributed port dispatching equipment, and at least one distributed port cargo intelligent dispatching environment monitoring point is arranged outside the distributed port dispatching equipment.

;

And (3) carrying out real-time packet grabbing analysis on the built-in network probe of the port distributed scheduling equipment to obtain the network delay of the port distributed scheduling equipment and the network error rate of the port distributed scheduling equipment.

Represent the firstIntelligent dispatching environment monitoring point for distributed port cargoesAnd the port distributed scheduling equipment network of the monitoring points of the distributed port scheduling equipment delays.

The network delay threshold value of the port distributed scheduling equipment is expressed and is directly extracted from the port cargo intelligent scheduling environment evaluation database.

Represent the firstIntelligent dispatching environment monitoring point for distributed port cargoesAnd the network error rate of the port distributed scheduling equipment at the monitoring points of the distributed port scheduling equipment.

The threshold value of the network error rate of the distributed scheduling equipment of the port is expressed and is directly extracted from the port cargo intelligent scheduling environment evaluation database.

The historical operation data of the corresponding equipment comprises the operation time of the equipment, the occurrence time of faults, the type of the faults and the like. Such data may be obtained through equipment maintenance records, fault logs, or equipment monitoring systems. From the collected data, the run time between each fault is calculated. This can be calculated by the difference between the points in time when the fault occurred. And adding up the running time among all faults, dividing the running time by the number of faults to obtain average fault interval time, and obtaining the average fault rate of the equipment.

Represent the firstIntelligent dispatching environment monitoring point for distributed port cargoesAnd the average fault rate of the port distributed scheduling equipment at the monitoring points of the distributed port scheduling equipment.

The average fault rate threshold value of the distributed port scheduling equipment is expressed and is directly extracted from the intelligent port cargo scheduling environment evaluation database.

The basic rate (unit μm/year) of salt fog corrosion of the terminal interface of the port distributed scheduling equipment is measured by an electrochemical corrosion rate probe (such as Rohrback Cosasco) built in the port distributed scheduling equipment.

The deployment position is that an equipment interface panel (such as the side of an RJ45/USB port) or a power distribution cabinet grounding copper bar is used for monitoring the corrosion risk of a grounding system.

Represent the firstIntelligent dispatching environment monitoring point for distributed port cargoesAnd the correction factors of the port distributed scheduling equipment terminal interface salt spray corrosion of the monitoring points of the distributed port scheduling equipment for the use time length are extracted from the port cargo intelligent scheduling environment evaluation database.

The correction factor of the port distributed scheduling equipment terminal interface salt spray corrosion to the service time is a dynamic parameter used for quantifying the influence of the port distributed scheduling equipment terminal interface corrosion rate on the service life of the equipment in a salt spray environment. The method has the core purpose of predicting the service life attenuation degree of the equipment interface by monitoring the environmental corrosion intensity, the equipment material characteristics and the historical data model in real time.

When (when)When the corrosion rate is larger than 1, the current corrosion rate exceeds a reference value, the service life of the equipment is accelerated and attenuated, and the maintenance period is required to be shortened or the task load is required to be reduced. When (when)Below 1, indicating that the corrosion rate is lower than expected, the equipment life may be suitably extended.

The concentration of salt fog is that a laser scattering sensor is adopted to monitor the concentration of chloride ions (unit: microgram/cubic meter) in the air, and the concentration is positively correlated with the corrosion rate.

Humiture, high temperature and high humidity environment can significantly accelerate corrosion, and the corrosion speed of the interface is accelerated by 10% under the environment of humidity of more than 40 ℃ and more than 80% by acquiring the corrosion in real time through a humiture sensor.

The calculation example of the correction factor of the port distributed scheduling equipment terminal interface salt spray corrosion to the use duration is as follows:

reference corrosion rate was determined by accelerated aging tests under laboratory standard conditions (salt spray concentration 50. Mu.g/cubic meter, temperature 25 ℃, humidity 60%).

Material corrosion resistance coefficient-different materials correspond to different corrosion resistance (e.g. the corrosion resistance of a gold plated interface is 3 times that of a tin plated interface).

And (3) setting up a joint mapping model of the corrosion rate of the temperature and humidity and the salt fog concentration fitted based on historical data to obtain a joint mapping model of the salt fog concentration, the temperature and the humidity and the corresponding correction factors of the port distributed scheduling equipment terminal interface salt fog corrosion to the use duration, and inputting the real-time salt fog concentration, the temperature and the humidity to obtain the corresponding correction factors of the port distributed scheduling equipment terminal interface salt fog corrosion to the use duration.

The first scheduling proportion factor representing the scheduling characteristic change of the port equipment is directly extracted from the port cargo intelligent scheduling environment evaluation database.

And the second scheduling proportion factor representing the scheduling characteristic change of the port equipment is directly extracted from the port cargo intelligent scheduling environment evaluation database.

And the third scheduling proportion factor representing the scheduling characteristic change of the port equipment is directly extracted from the port cargo intelligent scheduling environment evaluation database.

Relative humidity is another natural factor in port environments that can have a significant impact on the network delay, network error rate, and average failure rate of the distributed scheduling devices at the same time. And the heat dissipation inhibition is that the heat conduction efficiency of air is reduced in a high humidity environment, so that the heat dissipation capacity of equipment is reduced, the temperature of a chip is increased, and further the performance frequency reduction is caused. And the electrical performance is degraded, moisture permeates into the electronic element, leakage current and signal noise are increased, and the communication stability is affected. The material corrosion is accelerated, the high humidity and the environmental factors such as salt fog are synergistic, the metal oxidation and electrochemical corrosion are accelerated, and the service life of equipment is shortened.

The increase in humidity results in a decrease in heat sink efficiency, with an increase in processing delay of about 5% for every 10 ℃ increase in chip junction temperature. When the ambient humidity increases from 50% to 90%, the FPGA task processing delay increases by 20% to 35%. Through constant humidity experiments, the heat dissipation efficiency of the equipment is reduced by 2 to 5 percent and the temperature of the chip is increased by 3 to 8 ℃ every 10 percent of the humidity.

The moisture reduces the signal-to-noise ratio by 3 to 6dB when the insulation resistance of the device communication module is reduced from 1gΩ to 100mΩ. Condensation on the end face of the optical fiber connector causes the optical reflection loss to be increased by 0.2 to 0.8dB, and the error rate is obviously increased. When the humidity is greater than 80%, the optical fiber error rate is increased by 1 order of magnitude.

The high humidity accelerates electrochemical migration, causes dendrite shorting of the device communication module, and the copper ion migration rate increases exponentially when the humidity is greater than 70%. The service life of the aluminum electrolytic capacitor in the environment with the humidity of 90 percent is shortened by 60 percent to 80 percent compared with the service life of the aluminum electrolytic capacitor in the environment with the humidity of 50 percent.

The extraction and calculation method of the scheduling specific gravity factor is exemplified as follows:

environmental simulation-simulating 30% to 95% humidity environment in a constant humidity box, and recording equipment performance data.

And the key test is that a thermal infrared imager is used for monitoring the temperature change of the chip, an LCR meter is used for measuring the insulation resistance of the PCB, and a HALT test is used for evaluating the failure rate.

And (3) parameter calibration, namely determining sensitivity coefficients of humidity to delay, error rate and failure rate through multiple regression analysis. Normalizing the three types of scheduling specific gravity factors to be in a range of 0 to 1, ensuring that the total specific gravity sum is 1, constructing and obtaining a mapping relation between the environmental humidity of the monitoring point of the distributed port scheduling equipment and the corresponding port scheduling characteristic change first scheduling specific gravity factor, the port scheduling characteristic change second scheduling specific gravity factor and the port scheduling characteristic change third scheduling specific gravity factor, inputting the environmental humidity of the monitoring point of the distributed port scheduling equipment in real time, and obtaining the corresponding port scheduling characteristic change first scheduling specific gravity factor, port scheduling characteristic change second scheduling specific gravity factor and port scheduling characteristic change third scheduling specific gravity factor.

In this embodiment, as shown in fig. 3, a flow chart of comparative analysis adjustment according to the fluctuation parameters of the port scheduling equipment according to the embodiment of the present application is shown.

And carrying out corrosion prevention and dehumidification emergency treatment, for example, starting a high-pressure nitrogen corrosion prevention spray device, triggering corrosion prevention spray by each Zhong Yici, and starting a dehumidifier to maintain humidity less than 60%.

And gradually migrating the corresponding computing tasks to the first nodes to be regulated of the port distributed scheduling equipment according to the descending order of the second nodes to be regulated of the port distributed scheduling equipment after arrangement, namely migrating the computing tasks of the high-load nodes to the low-load or low-environmental risk nodes. Task migration is achieved through 5G TSN networks (end-to-end delay less than 10 ms). Task-to-node matching model based on hungarian algorithm, minimizing migration cost (delay + energy consumption).

In this embodiment, as shown in fig. 4, a flow chart of comprehensive evaluation analysis on port scheduling distributed computing node devices according to an embodiment of the present application is shown. The distributed port cargo intelligent dispatching environment monitoring points are numbered,The number of the monitoring points of the intelligent dispatching environment of the distributed port cargoes is represented,,And the total number of the number numbers of the monitoring points of the intelligent dispatching environment of the distributed port cargoes is represented.

;

Represent the firstIntelligent dispatching environment monitoring point for distributed port cargoesAnd the intelligent port cargo scheduling equipment of the monitoring points of the distributed port scheduling equipment is distributed with an integrated risk value of the power resource.

Represent the firstAnd evaluating the abrupt change value of the intelligent port cargo scheduling environment monitoring points.

Represent the firstIntelligent dispatching environment monitoring point for distributed port cargoesThe performance evaluation fluctuation mutation value of the port distributed scheduling equipment of each monitoring point of the distributed port scheduling equipment.

Represent the firstIntelligent dispatching environment monitoring point for distributed port cargoesAnd the correction factors of the port distributed scheduling equipment local temperature rising rate and the port distributed scheduling equipment local temperature rising rate of the port distributed scheduling equipment monitoring points on the port cargo intelligent scheduling equipment distributed computing power resource comprehensive risk value are extracted from the port cargo intelligent scheduling environment evaluation database by the port distributed scheduling equipment terminal interface salt spray corrosion correction factors on the using time, the mapping relation between the port distributed scheduling equipment local temperature rising rate and the port distributed scheduling equipment local temperature rising rate on the port cargo intelligent scheduling equipment distributed computing power resource comprehensive risk value correction factors is obtained through actual port historical data, the real-time port distributed scheduling equipment local temperature rising rate is input, and the port distributed scheduling equipment local temperature rising rate on the port cargo intelligent scheduling equipment distributed computing power resource comprehensive risk value correction factors are obtained.

The local temperature rise rate, the rise amplitude of the temperature of the equipment or the environment monitoring point in unit time reflects the heat accumulation and heat dissipation unbalance state. The high temperature gradient causes local airflow disturbance to make wind speed sensor data abnormal. The local temperature rise rate accelerates the evaporation of the surrounding seawater so that the concentration of the near-shore salt mist rises. Hardware frequency reduction, namely triggering CPU emergency frequency reduction when the local temperature rising rate exceeds a corresponding threshold value, and improving the cracking risk of welding spots due to mismatch of the thermal expansion coefficients of the PCB. The high temperature speed-up causes the wavelength drift acceleration of the light-emitting module to greatly improve the error rate of the optical fiber. The coupling effect of the local temperature rise rate with other factors, high Wen Shengsu in combination with salt spray, results in an increase in corrosion rate. Interaction with humidity, high temperature rise causes condensed water to accumulate inside the device, resulting in an increased probability of short circuit. Interaction with network load when the calculated force load is high, the local temperature rise rate is linearly and positively correlated with the load.The distributed computing power resources representing the intelligent port cargo scheduling equipment synthesize the first scheduling specific gravity factor and are directly extracted from the intelligent port cargo scheduling environment evaluation database.The distributed computing power resources representing the intelligent port cargo scheduling equipment synthesize the second scheduling specific gravity factors and are directly extracted from the intelligent port cargo scheduling environment evaluation database. The distributed computing power resource comprehensive second scheduling specific gravity factor of the port cargo intelligent scheduling device is used for correcting the current load and temperature change of the monitoring device, quantifying the sudden fault risk and facilitating triggering of a load diversion mechanism.

The distributed computing power resource comprehensive first scheduling specific gravity factor of the intelligent port cargo scheduling equipment is used for combining historical load data and salt spray corrosion environment, predicting equipment life attenuation, and long-term high load can accelerate salt spray corrosion and hardware fatigue.

The method comprises the steps of constructing a relation between a distributed computing power utilization rate of the intelligent port cargo scheduling equipment and a distributed computing power resource comprehensive first scheduling specific gravity factor of the intelligent port cargo scheduling equipment and a distributed computing power resource comprehensive second scheduling specific gravity factor of the intelligent port cargo scheduling equipment, obtaining a mapping model of the distributed computing power utilization rate of the intelligent port cargo scheduling equipment and the distributed computing power resource comprehensive first scheduling specific gravity factor of the intelligent port cargo scheduling equipment and the distributed computing power resource comprehensive second scheduling specific gravity factor of the intelligent port cargo scheduling equipment, inputting the distributed computing power utilization rate of the intelligent port cargo scheduling equipment, and obtaining a corresponding distributed computing power resource comprehensive first scheduling specific gravity factor of the intelligent port cargo scheduling equipment and a corresponding distributed computing power resource comprehensive second scheduling specific gravity factor of the intelligent port cargo scheduling equipment.

In this embodiment, when the system integrated risk value is lower than the preset threshold, it indicates that the current operating environment is relatively stable, but preventive measures are still required to maintain the system efficiency and safety.

And (3) intelligent task scheduling, namely monitoring the use condition (such as CPU (Central processing Unit) and GPU (graphics processing Unit) utilization rate) of computing resources of each edge node in real time through a Kubernetes cluster management system. If the resource occupancy rate of a certain node exceeds 80%, part of tasks are automatically migrated to idle nodes, and overall load balancing is ensured.

And reserving a computing power resource with a predefined computing power percentage for the secondary high-order computing power node, for example, reserving 10% of computing power resources in advance, wherein the computing power resource is used for coping with sudden tasks such as typhoon early warning data processing, and response delay caused by resource occupation is avoided.

In this embodiment, the rotation speed of the cooling fan of the corresponding intelligent port cargo dispatching device is increased and the liquid cooling system of the corresponding intelligent port cargo dispatching device is started, for example, the rotation speed of the cooling fan is increased in advance, and meanwhile, the liquid cooling system is started, so that the maximum power consumption of the device is forcedly limited to 70% of the nominal value.

The chip is prevented from being protected by overheat triggering and frequency reduction, if the chip is protected by overheat triggering and frequency reduction, the distributed computing resources of the corresponding intelligent port cargo scheduling equipment are greatly reduced, and then the distributed computing resources are called again, so that the timeliness requirement cannot be met. And marking the corresponding port cargo intelligent scheduling equipment as a high-order computing power node according to the predefined percentage, stopping distributing computing power tasks to the high-order computing power node, sequencing the nodes according to the performance fluctuation value, marking the node with the predefined percentage before ranking as a high-risk node, and stopping distributing new tasks to the high-risk node. The failure rate of a certain node is increased rapidly due to the fact that the salt fog concentration is too high, and the system automatically freezes the task queue. And immediately switching a wireless link used for communication to an optical fiber private network, starting forward error correction coding, and reducing the error rate.

Through the hierarchical adjustment strategy, the system provides highly reliable and self-adaptive intelligent scheduling guarantee for port operation through deep fusion of environment awareness, real-time decision and multidimensional control.

As shown in fig. 5, the embodiment of the application provides a port cargo intelligent scheduling method based on big data analysis, which is characterized by comprising the following specific steps:

evaluating and analyzing the port cargo environment parameters, and comparing, analyzing and adjusting according to the port cargo environment parameters;

Evaluating and analyzing the fluctuation parameters of the port scheduling equipment, and comparing, analyzing and adjusting according to the fluctuation parameters of the port scheduling equipment;

And carrying out comprehensive evaluation analysis on the port dispatching distributed computing node equipment, and carrying out comparison analysis adjustment according to the comprehensive evaluation analysis result.

It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CDROM, optical storage, etc.) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of systems, apparatuses (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.

It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims

1. The port cargo intelligent dispatching system based on big data analysis is characterized by comprising an environment acquisition evaluation module, a cargo intelligent dispatching distributed computing node first comparison analysis calling module and a cargo intelligent dispatching distributed computing node second comparison analysis calling module;

The environment collection evaluation module is used for evaluating and analyzing the port cargo environment parameters and carrying out comparison analysis adjustment according to the port cargo environment parameters;

The first contrast analysis calling module of the cargo intelligent dispatching distributed computing node is used for evaluating and analyzing the fluctuation parameters of the port dispatching equipment and carrying out contrast analysis adjustment according to the fluctuation parameters of the port dispatching equipment;

And the second comparison analysis calling module of the cargo intelligent dispatching distributed computing node is used for carrying out comprehensive evaluation analysis on port dispatching distributed computing node equipment and carrying out comparison analysis adjustment according to comprehensive evaluation analysis results.

2. The intelligent port cargo scheduling system based on big data analysis according to claim 1, wherein the comparison analysis adjustment is performed according to the port cargo environment parameters, specifically comprising:

Acquiring and obtaining the port environment wind speed through a wind speed sensor, acquiring and obtaining the port environment seawater level maximum value through a water level sensor, and acquiring and obtaining the unit time rainfall maximum value through a rainfall sensor;

If the highest value of the port environment seawater level is smaller than the highest value threshold of the port environment seawater level and the highest value of the rainfall in unit time is smaller than the highest value threshold of the rainfall in unit time and the wind speed of the port environment is smaller than the wind speed threshold of the port environment, carrying out intelligent dispatching environment assessment mutation assessment on port goods, and if the highest value of the port environment seawater level is equal to or larger than the highest value threshold of the port environment seawater level or the highest value of the rainfall in unit time is equal to or larger than the highest value threshold of the rainfall in unit time or the wind speed of the port environment is equal to or larger than the wind speed threshold of the port environment, sending out early warning and notifying related personnel to improve the intelligent dispatching early warning level of the port goods to the highest level.

3. The intelligent port cargo scheduling system based on big data analysis according to claim 2, wherein the intelligent port cargo scheduling environment assessment mutation assessment is performed, specifically comprising:

acquiring the highest salt fog concentration value of the port environment by a salt fog on-line monitor by a laser scattering method;

extracting a port environment seawater level historical average value, a port environment salt spray concentration historical average value, a port environment seawater level correction factor for port environment seawater speed, a port environment rainfall historical average value, a port cargo environment characteristic change first scheduling specific gravity factor, a port cargo environment characteristic change second scheduling specific gravity factor and a port cargo environment characteristic change third scheduling specific gravity factor from a port cargo intelligent scheduling environment evaluation database;

performing duty ratio analysis on the highest value of the port environment seawater level and the historical average value of the port environment seawater level, correcting the port environment seawater level correction factor through the port environment seawater speed, and correcting the port cargo environment characteristic change first scheduling specific gravity factor to obtain a port cargo intelligent scheduling environment assessment mutation first component;

performing duty ratio analysis on the highest salt spray concentration value of the port environment and the historical average value of the salt spray concentration of the port environment, and correcting the second dispatching proportion factor through the characteristic change of the port cargo environment to obtain the intelligent dispatching environment assessment mutation second component of the port cargo;

performing duty ratio analysis on the highest value of the rainfall in the port environment and the historical average value of the rainfall in the port environment, and correcting the third scheduling proportion factor through the characteristic change of the port cargo environment to obtain an intelligent port cargo scheduling environment assessment abrupt third component;

And carrying out coupling analysis by the port cargo intelligent scheduling environment assessment mutation first component, the port cargo intelligent scheduling environment assessment mutation second component and the port cargo intelligent scheduling environment assessment mutation third component to obtain a port cargo intelligent scheduling environment assessment mutation value.

4. The intelligent port cargo scheduling system based on big data analysis according to claim 1, wherein the specific process of performing comparative analysis adjustment according to the port cargo environment parameters is as follows:

If the assessment mutation value of the intelligent dispatching environment of the port cargo is smaller than the assessment mutation threshold value of the intelligent dispatching environment of the port cargo, not adjusting;

If the port cargo intelligent scheduling environment assessment mutation value is equal to or greater than the port cargo intelligent scheduling environment assessment mutation threshold, coupling analysis is carried out on the port cargo intelligent scheduling environment assessment mutation value and the real-time centralized computation load utilization rate of the port cargo intelligent scheduling resource center to obtain a port cargo intelligent scheduling resource center coupling value, the port cargo intelligent scheduling resource center coupling value is used for quantifying the relative scarce risk degree of the schedulable resources of the port cargo intelligent scheduling resource center, if the port cargo intelligent scheduling resource center coupling value is smaller than the port cargo intelligent scheduling resource center coupling threshold, notification is sent to related personnel and automatic distributed resource scheduling is not started temporarily, and if the port cargo intelligent scheduling resource center coupling value is equal to or greater than the port cargo intelligent scheduling resource center coupling threshold, distributed resource scheduling is started.

5. The intelligent port cargo scheduling system based on big data analysis according to claim 1, wherein the evaluation analysis for the fluctuation parameters of the port scheduling equipment specifically comprises:

acquiring network delay of the port distributed scheduling equipment and network error rate of the port distributed scheduling equipment by means of a tool arranged in the port distributed scheduling equipment;

directly extracting a port distributed scheduling equipment network delay threshold, a port distributed scheduling equipment network error rate threshold, a port distributed scheduling equipment average fault rate threshold, a port equipment scheduling characteristic change first scheduling proportion factor, a port equipment scheduling characteristic change second scheduling proportion factor, a port equipment scheduling characteristic change third scheduling proportion factor and a port distributed scheduling equipment terminal interface salt spray corrosion correction factor for the using time from a port cargo intelligent scheduling environment evaluation database;

Performing duty ratio analysis on the network delay of the port distributed scheduling equipment and the network delay threshold of the port distributed scheduling equipment, and correcting the first scheduling proportion factor through the scheduling characteristic change of the port equipment to obtain a first component of performance evaluation fluctuation of the port distributed scheduling equipment;

Performing duty ratio analysis on the network error rate of the port distributed scheduling equipment and the threshold value of the network error rate of the port distributed scheduling equipment, and correcting a second scheduling proportion factor through the scheduling characteristic change of the port equipment to obtain a second component of performance evaluation fluctuation of the port distributed scheduling equipment;

The average fault rate of the port distributed scheduling equipment and the average fault rate threshold value of the port distributed scheduling equipment are subjected to duty ratio analysis, and the third scheduling proportion factor is corrected through the scheduling characteristic change of the port equipment, so that the third component of the performance evaluation fluctuation of the port distributed scheduling equipment is obtained;

Coupling analysis is carried out through a first component of port distributed scheduling equipment performance evaluation fluctuation, a second component of port distributed scheduling equipment performance evaluation fluctuation and a third component of port distributed scheduling equipment performance evaluation fluctuation, and then correction factors of the using time length are corrected through port distributed scheduling equipment terminal interface salt spray corrosion, so that a port distributed scheduling equipment performance evaluation fluctuation mutation value is obtained.

6. The intelligent port cargo scheduling system based on big data analysis according to claim 1, wherein the comparison analysis adjustment is performed according to the fluctuation parameters of the port scheduling equipment, specifically comprising:

If the performance evaluation fluctuation mutation value of the port distributed scheduling equipment is smaller than the performance evaluation fluctuation mutation threshold value of the port distributed scheduling equipment, recording the corresponding port distributed scheduling equipment, and recording the corresponding port distributed scheduling equipment as a first node to be regulated of the port distributed scheduling equipment;

If the performance evaluation fluctuation mutation value of the port distributed scheduling equipment is equal to or greater than the performance evaluation fluctuation mutation threshold of the port distributed scheduling equipment, recording the corresponding port distributed scheduling equipment, recording the port distributed scheduling equipment as a second node to be regulated by the port distributed scheduling equipment, performing corrosion prevention and dehumidification emergency treatment, descending-order the performance evaluation fluctuation mutation value of the port distributed scheduling equipment corresponding to the second node to be regulated by the port distributed scheduling equipment, and gradually transferring corresponding calculation tasks to the first node to be regulated by the port distributed scheduling equipment according to descending-order arrangement sequence by sequentially arranging the second node to be regulated by the port distributed scheduling equipment.

7. The intelligent port cargo scheduling system based on big data analysis according to claim 1, wherein the comprehensive evaluation analysis is performed on port scheduling distributed computing node equipment, specifically comprising:

Directly extracting and obtaining a comprehensive first dispatching specific gravity factor of distributed computing resources of the intelligent port cargo dispatching equipment and a comprehensive second dispatching specific gravity factor of distributed computing resources of the intelligent port cargo dispatching equipment and a correction factor of the local temperature rising rate of the distributed computing resources of the intelligent port cargo dispatching equipment on the comprehensive risk value of the distributed computing resources of the intelligent port cargo dispatching equipment from an evaluation database of the intelligent port cargo dispatching environment;

coupling analysis is carried out on the port cargo intelligent scheduling environment assessment mutation value through a distributed computing power resource comprehensive first scheduling specific gravity factor of the port cargo intelligent scheduling equipment, so that a distributed computing power resource comprehensive risk first component of the port cargo intelligent scheduling equipment is obtained;

coupling analysis is carried out on the performance evaluation fluctuation mutation value of the port distributed scheduling equipment through the comprehensive second scheduling specific gravity factor of the distributed computing power resources of the port cargo intelligent scheduling equipment, so that the comprehensive risk second component of the distributed computing power resources of the port cargo intelligent scheduling equipment is obtained;

Coupling analysis is carried out on the first component of the distributed computing power resource comprehensive risk of the intelligent port cargo dispatching equipment and the second component of the distributed computing power resource comprehensive risk of the intelligent port cargo dispatching equipment, and then the correction factor of the distributed computing power resource comprehensive risk value of the intelligent port cargo dispatching equipment is corrected through the local temperature rising rate of the distributed port dispatching equipment, so that the distributed computing power resource comprehensive risk value of the intelligent port cargo dispatching equipment is obtained.

8. The intelligent port cargo scheduling system based on big data analysis according to claim 1, wherein the comparison analysis adjustment is performed according to the comprehensive evaluation analysis result, specifically comprising:

If the comprehensive risk value of the distributed computing power resources of the port cargo intelligent scheduling device is smaller than the comprehensive risk threshold value of the distributed computing power resources of the port cargo intelligent scheduling device, gradually transferring corresponding computing tasks to the first nodes to be regulated of the port distributed scheduling device according to the descending order of the second nodes to be regulated of the port distributed scheduling device after arrangement, marking the corresponding port cargo intelligent scheduling device as a secondary high-level computing power node according to the predefined percentage after arrangement according to the descending order, and reserving computing power resources of the predefined computing power percentage for the secondary high-level computing power node.

9. The intelligent port cargo scheduling system based on big data analysis according to claim 1, wherein the comparison analysis adjustment is performed according to the comprehensive evaluation analysis result, further comprising:

If the comprehensive risk value of the distributed computing power resources of the intelligent port cargo scheduling equipment is equal to or greater than the comprehensive risk threshold of the distributed computing power resources of the intelligent port cargo scheduling equipment, the rotating speed of a cooling fan of the corresponding intelligent port cargo scheduling equipment is increased, a liquid cooling system of the corresponding intelligent port cargo scheduling equipment is started, the intelligent port cargo scheduling equipment is arranged in a descending order according to the comprehensive risk value of the distributed computing power resources of the intelligent port cargo scheduling equipment, the intelligent port cargo scheduling equipment in the corresponding predefined percentage is recorded as a high-level computing power node according to the predefined percentage, a wireless link of the intelligent port cargo scheduling equipment is switched to an optical fiber private network, and computing power tasks are stopped being distributed to the intelligent port cargo scheduling equipment.

10. The port cargo intelligent scheduling method based on big data analysis is characterized by comprising the following specific steps: