CN115423161A - Multi-energy coupling optimization scheduling method and system based on digital twin - Google Patents

Abstract

The invention belongs to the technical field of energy optimization scheduling, and provides a digital twin-based multi-energy coupling optimization scheduling method and system. The method comprises the steps of obtaining historical operation data, equipment constraint conditions and initial states of the multi-energy-flow comprehensive energy system, and predicting similar daily load and power generation data based on a deep neural network; correcting the coefficient of the virtual space twin model corresponding to the multi-energy flow comprehensive energy system according to the predicted similar daily load and the predicted power generation data; and performing multi-objective optimization decision based on the maintenance cost function, the transaction cost function and the environmental protection cost function according to the electricity price and the equipment constraint condition of each time period to obtain an optimal solution set, and finally determining the charge and discharge power of the energy storage device, the output power of each unit and the power of a connecting line.

Description

Multi-energy coupling optimization scheduling method and system based on digital twin

technical field

The invention belongs to the technical field of energy optimization scheduling, and in particular relates to a digital twin-based multi-energy coupling optimization scheduling method and system.

Background technique

The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

The traditional mode of independent operation of electricity, heat and gas can no longer meet the needs of current energy development. To realize the open and interconnected multi-energy flow system of multiple energy sources is an important development direction of the current energy industry. The multi-energy flow system reduces energy consumption and waste, improves comprehensive energy utilization efficiency, reduces energy costs, and improves the economy and reliability of energy supply through the cascade development and intelligent utilization management of various energy sources.

Multi-energy flow systems can effectively improve energy efficiency but also increase the complexity of the energy system. The multi-energy flow system is composed of multiple energy flow subsystems, and various energies are tightly coupled, which increases the complexity of the analysis. At present, the existing technology has established the theoretical framework and technical practice route of the multi-energy microgrid distributed control system. In order to improve the utilization rate of the integrated energy system, and in order to improve the utilization rate of the integrated energy system, considering the uncertainty of the source load, vertical optimization is carried out to realize the horizontal coupling of electricity-cold-heat-gas energy. In the existing technology, an efficient integrated energy system modeling method is applied to the optimization modeling of electric cooling and hot air multi-energy flow, which can not only improve the system optimization of integrated energy, but also realize the planning and analysis of integrated energy innovation.

The inventors found that most of the existing research is limited to simple microgrids or combined cooling, heating and power systems, and there are few studies considering the optimal configuration of hydrogen energy flow in the multi-energy flow integrated energy system; there is no research on the source and storage In addition, the installed capacity and utilization rate of renewable energy in the traditional multi-stream integrated energy system are still relatively low.

Contents of the invention

In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a multi-energy coupling optimization scheduling method and system based on digital twins, which predicts and optimizes future behavior trends according to corresponding information, and uses The difference between the simulation operation and the physical entity, adjust the coefficient of the simulation operation model, and realize the synchronization of the digital twin and the physical entity.

In order to achieve the above object, the present invention adopts the following technical solutions:

The first aspect of the present invention provides a digital twin-based multi-energy coupling optimization scheduling method, which includes:

Obtain the historical operation data, equipment constraints and initial state of the multi-energy flow integrated energy system, and predict similar daily load and power generation data based on the deep neural network;

Correct the coefficients of the virtual space twin model corresponding to the multi-energy flow integrated energy system according to the predicted similar daily load and power generation data;

According to the electricity price and equipment constraints in each period, the multi-objective optimization decision is made based on the maintenance cost function, transaction cost function and environmental protection cost function, and the optimal solution set is obtained, and finally the charging and discharging power of the energy storage device and the output of each unit are determined. Power and tie-line power.

The second aspect of the present invention provides a digital twin-based multi-energy coupling optimization scheduling system, which includes:

Data prediction module, which is used to obtain the historical operation data, equipment constraints and initial state of the multi-energy flow integrated energy system, and predict similar daily load and power generation data based on the deep neural network;

A coefficient correction module, which is used to correct the coefficient of the virtual space twin model corresponding to the multi-energy flow integrated energy system according to the predicted similar daily load and power generation data;

The objective optimization module is used to make multi-objective optimization decisions based on the maintenance cost function, transaction cost function and environmental protection cost function according to the electricity price and equipment constraints in each period, obtain the optimal solution set, and finally determine the charging capacity of the energy storage device. Discharge power, output power of each unit and power of tie line.

The third aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps in the above-mentioned digital twin-based multi-energy coupling optimization scheduling method are implemented.

A fourth aspect of the present invention provides a computer device, including a memory, a processor, and a computer program stored on the memory and operable on the processor. When the processor executes the program, the above-mentioned based Steps in a multi-energy coupled optimal scheduling method for digital twins.

Compared with prior art, the beneficial effect of the present invention is:

Based on the digital twin drive, a multi-energy flow comprehensive energy system simulation modeling and optimization control strategy is proposed, a mirror image collaborative interaction mechanism including physical digital space is established, and a multi-energy flow virtual entity containing electric, hot gas and hydrogen is constructed. According to the distribution and depth of equipment status information Neural network power prediction, proposed a multi-objective optimal scheduling strategy based on digital twins, realized the overall adjustment of the source end and energy storage end, and improved the installed capacity and utilization rate of renewable energy in the multi-stream integrated energy system; thus reasonable Plan and utilize energy, reduce energy consumption, and improve economic efficiency.

Advantages of additional aspects of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.

Description of drawings

The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention, and the schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations to the present invention.

Fig. 1 is a structure diagram of a confrontational network generated based on deep convolution according to an embodiment of the present invention;

Fig. 2 is an operation scene diagram of an integrated energy system according to an embodiment of the present invention;

Fig. 3 is a flow chart of generating an adversarial network training based on deep convolution in an embodiment of the present invention;

Fig. 4 is a sample comparison of the cooling load scene of the embodiment of the present invention and a typical real scene;

Fig. 5 is a sample comparison of the heat load scene of the embodiment of the present invention and a typical real scene;

Fig. 6 is a sample comparison of a new energy output generation scenario according to an embodiment of the present invention and a typical real scenario;

Fig. 7 is a sample comparison of the temperature scene of the embodiment of the present invention and a typical real scene;

FIG. 8 is a flowchart of multi-objective optimization decision-making using the NSGA-II algorithm according to an embodiment of the present invention.

detailed description

The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

It should be noted that the following detailed description is exemplary and intended to provide further explanation of the present invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

It should be noted that the terminology used here is only for describing specific embodiments, and is not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly dictates otherwise, the singular is intended to include the plural, and it should also be understood that when the terms "comprising" and/or "comprising" are used in this specification, they mean There are features, steps, operations, means, components and/or combinations thereof.

Embodiment one

This embodiment provides a digital twin-based multi-energy coupling optimization scheduling method, which specifically includes the following steps:

Step 1: Obtain the historical operation data, equipment constraints and initial state of the multi-energy flow integrated energy system, and predict the similar daily load and power generation data based on the deep neural network.

Among them, equipment constraints include network power flow constraints, energy storage charge and discharge constraints, and equipment maximum output constraints.

In the specific implementation process of step 1, the input of the deep neural network includes meteorological information such as light conditions, humidity, temperature, and wind speed, and outputs similar daily load and power generation forecast data through multiple hidden layers.

In some embodiments, the deep neural network can be a deep convolutional neural network or other existing deep neural network models, which can be selected by those skilled in the art according to actual conditions, and will not be described in detail here.

Step 2: Correct the coefficients of the virtual space twin model corresponding to the multi-energy flow integrated energy system according to the predicted similar daily load and power generation data.

The key to digital twins is to construct high-fidelity virtual entities of physical entities based on virtual space to simulate behaviors in the real world, and to predict and optimize future behavioral trends based on corresponding information. During the simulation operation, the coefficients of the simulation operation model are adjusted by using the difference between the simulation operation and the physical entity to realize the synchronization of the digital twin and the physical entity. The digital twin can also be fed back to the physical entity to realize the optimized operation of the physical entity, as shown in Figure 1.

Based on the digital twin, the virtual space test entity generates panoramic information on equipment status, network framework topology, line parameters, electricity, heat, gas, hydrogen energy flow, etc., and inputs the simulation optimization results into the control equipment for testing. The actual running status of can also be fed back to the twin for improvement and optimization.

The established virtual space twin is shown in Figure 2. Through various energy conversion devices and communication devices, different networks such as electricity, heat, gas, hydrogen and transportation are integrated together. The system is connected with the electricity network (Electricity Network, EN) and Natural Gas Network (NGN) connected. The interior includes photovoltaic (Photovoltaic, PV), wind turbine (Wind Turbine, WT), combined heat and power system (Combined Heating and Power, CHP), electric hydrogen production device (Power to Hydrogen, P2H), hydrogen storage tank (Hydrogen Tank, HT) , fuel cells (Fuel Cells, FC), thermal energy storage devices (Thermal storage Tank, TT), storage batteries (Storage Battery, SB) and other equipment.

Step 3: According to the electricity price and equipment constraints in each time period, multi-objective optimization decision-making is carried out based on the maintenance cost function, transaction cost function and environmental protection cost function to obtain the optimal solution set, and finally determine the charging and discharging power of the energy storage device, each The output power of the unit and the power of the tie line.

The power flow model in the integrated energy system is constructed using the traditional AC power flow model. This embodiment is based on the node power balance equation, uses the Newton-Raphson algorithm to iteratively solve by constructing the Jacobian matrix, and calculates the state quantities of each node, thereby obtaining the power flow distribution of the power network. The calculation formula is given:

代表节点电压，Y为节点导纳矩阵。Re和Im代表实部和虚部，星号表示共轭。In the formula, P _i and Q _i respectively represent the injected active and reactive power of node i,

Represents the node voltage, and Y is the node admittance matrix. Re and Im represent real and imaginary parts, and asterisks indicate conjugation.

The heat network structure is similar to the radial structure of the distribution network, and is divided into two parts, the hydraulic model and the thermal model. The state quantities to be sought in the hydraulic model mainly include pipeline flow and pressure loss h _f :

In the formula, A represents the node-branch correlation matrix; B represents the branch cycle correlation matrix, m represents the branch flow of each pipeline; m _q is the flow through the heat source or load node; K is the pipeline resistance coefficient matrix.

The thermal model describes the heat balance behavior of the heating system at the nodes and in the heating pipes

In the formula, T _start and T _end respectively represent the temperature at the beginning and end of the pipeline, T _a is the ambient temperature, _α is the proportional coefficient related to the pipeline parameters; L is the length of the pipeline; T _in and T _cut represent the heat injected into and out of a certain node, respectively Medium temperature, _min and m _out respectively represent the flow rate of heat medium injected into and out of a certain node; P _h is the heat power required by the load or the heat power provided by the heat source; C _p is the specific heat capacity of the heat medium, T _s is the node water supply temperature; T _o is the node thermal mass outlet temperature.

The natural gas system satisfies Kirchhoff's law, and the flow equation of the pipeline model without considering the compressor is:

Among them, F _bd is the natural gas flow rate of pipeline bd; k _bd is a parameter of pipeline; s _bd is a parameter indicating the direction of natural gas flow; p _b and p _d are the pressures of nodes b and d, respectively.

When the integrated energy system operates economically, it is necessary to consider the maintenance cost of distributed energy, the transaction cost with the power grid, natural gas network and load, and the environmental protection cost of CO ₂ , SO ₂ and NO _x emissions.

Maintenance cost function:

Among them, c _i,t is the operation and maintenance cost coefficient of distributed energy source i at time t; P _i,t is the output power of micro source i at time t;

Energy cost function:

f ₂ ＝c _buy,t P _buy,t +c _gas,t G _buy,t -c _sell,t P _sell,t (6)

Among them, c _{buy, t} and c _{sell, t} are the electricity purchase price and electricity sale price at time t; P _{buy, t} and P _{sell, t} are the power purchase and sales of the integrated energy system; c _{gas, t} is the purchase of natural gas at time t price; G _buy,t is the amount of natural gas purchased.

Environmental protection cost function:

Among them, c _i,k is the number of pollutant types (NO _x , SO ₂ or CO ₂ ), λ _i,k is the unit treatment cost of the kth type of pollutant; P _i,t is the emission coefficient of the pollutant.

In the optimization process, firstly, panoramic information such as load, wind energy, photovoltaic power generation historical data, and meteorological data are input into the database management module. Set the initial state and constraints of each device to create a virtual image of the integrated energy system. Then, based on the deep neural network algorithm, the load and wind power generation data are predicted. And the twin model is corrected based on the physical model and similar daily data. Afterwards, according to the electricity price and constraint conditions in each time period, the NSGA-II algorithm is used for multi-objective optimization decision-making. As shown in Figure 8, finally, on the basis of the obtained optimal Pareto solution set, the charging and discharging power of the energy storage device, the output power of each unit and the power of the tie line are determined.

In order to verify the effectiveness of the method proposed in this example, an actual industrial park in a certain area is taken as an example for calculation and analysis. The integrated energy system includes electricity, heat, gas, and hydrogen loads. Typical days are selected for 24-hour optimal scheduling. According to the meteorological data of the environment where the equipment is located, the power of the neural network is initially predicted, and the twin database is updated synchronously. In addition, through the similar day weather retrieval method, the actual value and predicted value of solar power generation under similar conditions are compared, and the final predicted value of the digital twin is obtained after error algorithm correction. The typical daily load curve and the maximum wind power output obtained through historical data prediction are shown in Figure 3 and Figure 4.

The optimization method proposed in this example is used to solve the system, and the optimization results of hydrogen energy, electric energy, and thermal energy balance are obtained as shown in Figures 5-7. The hydrogen production by P2H equipment provides the hydrogen demand in the park, and the hydrogen storage tanks cooperate to improve the utilization rate of wind and light and reduce operating costs. As shown in Figure 5, the energy conversion efficiency of fuel cells is low, so they are only used in the evening peak period. In the rest of the time, the P2H equipment is in working condition to meet the load demand and hydrogen storage tank demand. At the same time, it can also be used as a transferable electric load to realize the peak regulation function and absorb the excess electric energy of wind power and photovoltaic. Compared with hydrogen storage equipment, although the cost of environmental pollution increases, the energy conversion efficiency of the battery is higher at the same time, so it has a more flexible scheduling strategy during the day to smooth some short-term load fluctuations, as shown in Figure 6 . The CHP unit needs to ensure the balance of thermal energy and electric energy at the same time, select the appropriate output, and the vacant part of the thermal energy can be supplemented by the gas boiler and thermal energy storage, so as to avoid the waste of thermal energy as much as possible, so as to achieve the overall optimization of the system. According to the calculation results, the economic cost of the integrated energy system before and after optimization has been reduced by 2137 yuan. Through the reasonable planning of hydrogen energy storage and batteries, the utilization rate of wind and solar energy has increased by more than 40%, and thermal energy storage has also effectively reduced the waste of heat energy.

Embodiment two

This embodiment provides a digital twin-based multi-energy coupling optimization scheduling system, which includes:

Data prediction module, which is used to obtain the historical operation data, equipment constraints and initial state of the multi-energy flow integrated energy system, and predict similar daily load and power generation data based on the deep neural network;

A coefficient correction module, which is used to correct the coefficient of the virtual space twin model corresponding to the multi-energy flow integrated energy system according to the predicted similar daily load and power generation data;

The objective optimization module is used to make multi-objective optimization decisions based on the maintenance cost function, transaction cost function and environmental protection cost function according to the electricity price and equipment constraints in each period, obtain the optimal solution set, and finally determine the charging capacity of the energy storage device. Discharge power, output power of each unit and power of tie line.

It should be noted here that each module in this embodiment corresponds to each step in Embodiment 1, and the specific implementation process is the same, so it will not be repeated here.

Embodiment three

This embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps in the digital twin-based multi-energy coupling optimization scheduling method as described above are implemented.

Embodiment four

This embodiment provides a computer device, including a memory, a processor, and a computer program stored on the memory and operable on the processor. When the processor executes the program, the above-mentioned digital twin-based Steps in the Multi-Energy Coupling Optimization Scheduling Method.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It should be understood that each procedure and/or block in the flowchart and/or block diagram and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims (10)

1. A digital twin-based multi-energy coupling optimal scheduling method is characterized by comprising the following steps:

acquiring historical operating data, equipment constraint conditions and initial states of the multi-energy flow comprehensive energy system, and predicting similar daily loads and power generation data based on a deep neural network;

correcting the coefficient of the virtual space twin model corresponding to the multi-energy flow comprehensive energy system according to the predicted similar daily load and the predicted power generation data;

and performing multi-objective optimization decision based on a maintenance cost function, a transaction cost function and an environmental protection cost function according to the electricity price and the equipment constraint conditions of each time interval to obtain an optimal solution set, and finally determining the charge and discharge power of the energy storage device, the output power of each unit and the power of a connecting line.

2. The digital twin based multi-energy coupling optimized scheduling method of claim 1, wherein the virtual space twin model connects the multi-energy flow integrated energy system with the power network and the natural gas grid through various energy conversion devices and communication devices.

3. The digital twin-based multi-energy coupling optimization scheduling method of claim 1, wherein an NSGA-II algorithm is adopted to perform multi-objective optimization decision to obtain an optimal Pareto solution set.

4. The digital twin based multi-energy coupling optimized scheduling method of claim 1, wherein the device constraints include network power flow constraints, energy storage charge and discharge constraints, and device maximum output constraints.

5. A digital twin based multi-energy coupling optimized dispatch system, comprising:

the data prediction module is used for acquiring historical operating data, equipment constraint conditions and initial states of the multi-energy flow comprehensive energy system and predicting similar daily loads and power generation data based on a deep neural network;

the coefficient correction module is used for correcting the coefficient of the virtual space twin model corresponding to the multi-energy flow comprehensive energy system according to the predicted similar daily load and the predicted power generation data;

and the target optimization module is used for carrying out multi-target optimization decision based on the maintenance cost function, the transaction cost function and the environmental protection cost function according to the electricity price and the equipment constraint condition of each time interval to obtain an optimal solution set, and finally determining the charging and discharging power of the energy storage device, the output power of each unit and the power of a connecting line.

6. The digital twin based multi-energy coupling optimized dispatch system of claim 5, wherein the virtual space twin model connects the multi-energy flow integrated energy system with the power network and the natural gas grid through various energy conversion devices and communication devices.

7. The digital twin-based multi-energy coupling optimization scheduling system of claim 5, wherein an NSGA-II algorithm is used to perform multi-objective optimization decision to obtain an optimal Pareto solution set.

8. The digital twin based multi-energy coupling optimized dispatch system of claim 5, wherein the device constraints include network power flow constraints, energy storage charge-discharge constraints, and device maximum output constraints.

9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method for optimized scheduling of a digital twin based multi-energy coupling according to any of the claims 1-4.

10. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor when executing the program carries out the steps of the method of digitally twin based multi-energy coupling optimized scheduling according to any of the claims 1-4.

Images