CN110648251A - Energy utilization prediction system and method for supply and demand bilateral game - Google Patents
Energy utilization prediction system and method for supply and demand bilateral game Download PDFInfo
- Publication number
- CN110648251A CN110648251A CN201910913765.7A CN201910913765A CN110648251A CN 110648251 A CN110648251 A CN 110648251A CN 201910913765 A CN201910913765 A CN 201910913765A CN 110648251 A CN110648251 A CN 110648251A
- Authority
- CN
- China
- Prior art keywords
- energy
- supply
- demand
- game
- operator
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000002146 bilateral effect Effects 0.000 title claims abstract description 62
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000008901 benefit Effects 0.000 claims abstract description 25
- 238000005265 energy consumption Methods 0.000 claims abstract description 25
- 238000006243 chemical reaction Methods 0.000 claims abstract description 14
- 230000003993 interaction Effects 0.000 claims abstract description 11
- 239000007789 gas Substances 0.000 claims description 77
- 230000005611 electricity Effects 0.000 claims description 29
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 17
- 239000003345 natural gas Substances 0.000 claims description 9
- 238000010438 heat treatment Methods 0.000 claims description 3
- 230000015654 memory Effects 0.000 abstract description 4
- 230000006403 short-term memory Effects 0.000 abstract description 3
- 230000007787 long-term memory Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Tourism & Hospitality (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an energy consumption prediction system and method for supply and demand bilateral game, which comprises the following steps of firstly, comprehensively considering influence factors such as economy, weather and price, and adopting a long-short term memory network to predict the load of an electrical interconnection system; secondly, a supply and demand bilateral game model of supply and demand interaction is established, a preference coefficient benefit model is introduced to a user side, an energy operator comprehensively considers operation benefits and operation costs of electric gas conversion equipment and a gas turbine, a load predicted value is taken as a game basis, an energy price is taken as a game variable, and economic benefits of both supply and demand parties are maximized; and finally, correcting the long-term and short-term memory network according to the game energy price, and predicting the load again, and repeating the steps until the load predicted value and the energy price are stable. The invention comprehensively considers the relation between supply and demand interaction and energy demand prediction in the multi-energy system, improves the load prediction precision and improves the economy of both supply and demand parties in the future energy market.
Description
Technical Field
The invention relates to the field of power markets, in particular to an energy utilization prediction system and method for a supply and demand bilateral game.
Background
In recent years, with the gradual depletion of traditional energy sources, environmental problems become more prominent, and the concept of energy internet comes into play; by adjusting energy production, transportation and consumption modes, a novel energy system which has the advantages of multi-energy complementation, multi-network coupling, support of wide participation of users and deep fusion of information technology is constructed with the aim of improving energy utilization efficiency. In 7 months in 2018, the national institute of development and improvement and the national energy agency jointly release ' notice on actively promoting electric power marketization trading and further perfecting a trading mechanism ' on the basis of ' Zhongzha ' (2015) nine characters ', which marks that the energy internet formally steps into a comprehensive implementation stage in China.
Load prediction is an important component in energy management systems and is crucial to the development of energy internet systems. The coupling enhancement of the energy system enables the use energy prediction to be independent, the traditional load prediction method is not suitable any more, along with the success of a machine learning analysis method in other fields, artificial intelligent algorithms such as a neural network, deep learning, a support vector machine and the like are gradually used for load prediction, but the common problem of the artificial intelligent algorithms is lack of time setting data correlation consideration; the Long Short-Term Memory network (LSTM) is used as an improved recurrent neural network, can give consideration to data time sequence and correlation, and can effectively improve load prediction accuracy.
At present, the natural Gas consumption is continuously increased worldwide, the gradual maturity of Gas Turbine (GT) and Power to Gas (P2G) technologies enables the continuous coupling of an electric Power system and a natural Gas system, and an electric-Gas interconnection system becomes an important component of the future energy internet. The release of the energy trading market indicates that the energy market is no longer a single monopoly, and the market operation mechanism of the non-incoming-electricity-gas interconnection system is determined by the energy operators mainly using electricity and natural gas and the users with energy utilization requirements.
The release of the energy trading market indicates that the energy market is no longer a single monopoly, and the market operation mechanism of the non-incoming-electricity-gas interconnection system is determined by the energy operators mainly using electricity and natural gas and the users with energy utilization requirements. However, the uncertainty of load prediction is increased by the characteristics of the supply and demand bilateral game, so that the accuracy of the load prediction value obtained by the supply and demand bilateral game model is not high.
Therefore, providing an energy consumption prediction system and method for bilateral game on demand is a technical problem to be solved by those skilled in the art.
Disclosure of Invention
The invention discloses an energy consumption prediction system and method for supply and demand bilateral game, which solve the problem of low precision of a load prediction value in a supply and demand bilateral game model of the current energy market.
In order to solve the technical problems, the invention is realized by the following technical scheme:
an energy consumption prediction system and method for supply and demand bilateral game comprises the following steps:
carrying out energy utilization load prediction by using an LSTM network, wherein the LSTM network is trained by using a learning sample;
establishing a supply and demand bilateral game model for supply and demand interaction according to a benefit model of demand side participation in supply and demand bilateral game and a benefit model of energy operators participating in supply and demand bilateral game;
performing supply and demand bilateral game by using the supply and demand bilateral game model, judging whether a stable condition is met, and if so, judging whether a convergence condition is met; if not, the supply and demand bilateral game is carried out again;
judging whether a convergence condition is met, if so, outputting a load predicted value; if not, the load prediction is carried out again until the load prediction value and the energy price are stable.
Further, the benefit model of the demand side participating in the supply and demand bilateral game further comprises: f. ofj＝Ej-Bj；
Wherein f isjNet utility for class j users, BjEnergy cost for class j users, EjThe energy utilization efficiency function is a j-type user;
Bj＝pjPj+qjQj，Ej＝kjln(1+Pj+eQj)，pj、qjelectricity and gas prices, P, for class j users respectivelyj、QjElectricity and gas consumption, k, for j-class users respectivelyjAnd the preference coefficient represents the preference coefficient of j types of users for consuming electric energy, and epsilon is a gas/electricity conversion coefficient.
Further, the supply and demand bilateral game is carried out by utilizing the supply and demand bilateral game model, and whether the stable condition is met or not is judged; the user adjusts the energy value and feeds back the energy value to the operator; and the operator judges whether the energy utilization value of the user reaches a stable condition.
Further, the step of judging whether the convergence condition is met further comprises the step of judging whether the energy consumption predicted value after the game and the energy consumption predicted value of the LSTM network meet the convergence condition.
Further, the participation of the energy operator in the benefit model of the supply and demand bilateral game further comprises: f. ofsup＝Esup-Csup-Cp2g-Cgt；
Wherein E issupFor the energy sales profits of the operator, Cp2g、CgtOperating costs, C, of the P2G plant and the gas boiler, respectively, in the electrical interconnection systemsupAs a function of the cost of energy supply to the operator.
Further, the supply and demand bilateral gaming model may be,
G＝{U∪S,{un},{sk},{fusers},{fsup}}n∈U,k∈S
wherein u isnFor user policy sets, including power consumption P of class j usersjAnd gas usage Q of class j usersj；SkFor operator policy set, including pj、qj、φjAndpj、qjrespectively the electricity price and the gas price of the j-class users, phi j is the proportion of the electricity consumption of the j-class users from the power supply of the gas turbine,
the gas consumption for the j-type users is derived from the proportion of the gas supply of the P2G equipment; f. ofusersThe sum of the net benefits of all users.
Further, satisfy
(ρ, δ) of the condition is an equilibrium point of the offer-demand bilateral game;
wherein,
for other balancing policies of the operator than policy k,
balancing the user except the strategy n;
the minimum value and the maximum value of the electricity price are respectively;
the minimum value and the maximum value of the gas price are respectively; ρ represents the operator's balancing policy vector, δ represents the optimal load prediction vector for the user.
Further, CsupThe cost function of energy supply to the operator further comprises:
Csup＝fP(Psup)+fQ(Qsup)，
wherein f isP(Psup)、fQ(Qsup) The costs of power supply and gas supply for the operator respectively;
cost coefficient for supplying power and gas to the operator. Psup、QsupRespectively the total electricity and gas consumption of the operator.
Further, Psup、QsupThe total electricity and gas usage, respectively, for the operator further comprises:
phi j is the proportion of j types of user power consumption from power supply of the gas turbine;
the gas consumption for the j-type users is derived from the proportion of the gas supply of the P2G equipment; eta P2g is the overall conversion efficiency of P2G equipment, and can reach 60-70% at present; vE is the conversion coefficient of electric energy and heat energy, unit: MJ/kWh; hg is the high heating value of natural gas, unit: MJ/m 3; and alpha, beta and gamma are respectively the energy consumption coefficients of the gas turbine.
An energy use prediction system for a bilateral game based on any one of claims 1 to 9, comprising:
the load prediction module is used for predicting the energy load of the predicted year by using the LSTM network;
the energy operator module is used for optimizing a target function according to the energy load predicted value of the user module and formulating the energy selling price facing the user module;
the user module is used for adjusting the load predicted value according to the price formulated by the energy operator module and feeding back information to the energy operator module;
and the judging module is used for judging whether the energy load predicted value and the energy price reach stability.
The invention provides an energy consumption prediction system and method for supply and demand bilateral game, which comprises the following steps of firstly, comprehensively considering influence factors such as economy, weather and price, and adopting a long-short term memory network to predict the load of an electric-gas interconnection system; secondly, a supply and demand bilateral game model of supply and demand interaction is established, a preference coefficient benefit model is introduced to a user side, an energy operator comprehensively considers operation benefits and operation costs of electric gas conversion equipment and a gas turbine, a load predicted value is taken as a game basis, an energy price is taken as a game variable, and economic benefits of both supply and demand parties are maximized; and finally, correcting the long-term and short-term memory network according to the game energy price, and predicting the load again, and repeating the steps until the load predicted value and the energy price are stable.
The energy demand forecasting method considering the supply and demand bilateral game comprehensively considers the relation between supply and demand interaction and energy demand forecasting in the multi-energy system, and considers the supply and demand interaction game in the load forecasting process of the multi-energy system, so that the load forecasting value is more accurate, the load forecasting precision is improved, and the economy of supply and demand parties in the future energy market is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is an algorithm flow diagram of an energy consumption prediction system and method for a supply and demand bilateral game of the present invention;
FIG. 2 is a block diagram of an electrical interconnect system for an energy use prediction system and method for a bilateral game for supply and demand in accordance with the present invention;
FIG. 3 is a system diagram of an energy usage prediction system and method for a bilateral game for supply and demand in accordance with the present invention;
FIG. 4 is a diagram illustrating changes in the values of objective functions according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to achieve the purpose, the invention provides an energy utilization prediction system and method for a supply and demand bilateral game, which specifically comprise the following steps:
And 2, establishing a supply and demand bilateral game model for supply and demand interaction.
Wherein, the benefit model of the demand side participating in the supply and demand bilateral game is as follows:
fj＝Ej-Bj (1)
wherein f isjNet utility for class j users, BjThe user energy cost is calculated according to the following formula (2); ejThe user's energy utilization efficiency function is used for describing the satisfaction value obtained by the user consuming energy, and has the characteristics of nondecreasing performance and non-increasing performance of marginal benefit, so the invention adopts the formula (3) to describe the satisfaction value obtained by the user.
Bj＝pjPj+qjQj (2)
Ej＝kj ln(1+Pj+εQj) (3)
Wherein p isj、qjElectricity and gas prices, P, for different users respectivelyj、QjThe electricity consumption and the gas consumption of the user; k is a radical ofjThe preference coefficient of the user for consuming the electric energy is expressed, the preference of the user for the energy is reflected, and the preference coefficients of different users are different; ε is the gas/electricity conversion coefficient.
The benefit model of the energy operator participating in the supply and demand bilateral game is as follows:
fsup＝Esup-Csup-Cp2g-Cgt (4)
wherein E issupThe energy selling income of the operator, namely the energy cost of the user is shown as a formula (2); cp2g、CgtThe operating costs of the P2G equipment and the gas boiler in the electric-gas interconnection system are respectively; csupThe energy supply cost function for the operator consists of two parts, as shown in formula (5):
Csup＝fP(Psup)+fQ(Qsup) (5)
wherein f isP(Psup)、fQ(Qsup) The power supply and gas supply costs for the operator are expressed as polynomials (6) and (7), respectively.
Wherein,
cost coefficient for supplying power and gas to the operator. Psup、QsupTotal electricity and gas consumption, respectively, of the operator, in an electricity-gas interconnected system considering P2G plant and gas boiler, Psup、QsupThe calculation formula is shown in formula (8) and formula (9):
wherein phi isjThe electricity consumption for the j-type users is derived from the proportion of the power supply of the gas turbine;
the gas consumption for the j-type users is derived from the proportion of the gas supply of the P2G equipment; etap2gThe overall conversion efficiency of the P2G equipment can reach 60% -70% at present; vE is the conversion coefficient of electric energy and heat energy, unit: MJ/kWh; hgIs the high heating value of natural gas, unit: MJ/m 3; and alpha, beta and gamma are respectively the energy consumption coefficients of the gas turbine.
Wherein, the supply and demand bilateral game for establishing supply and demand interaction is shown as formula (10):
G＝{U∪S,{un},{sk},{fusers},{fsup}} n∈U,k∈S (10)
wherein u isnFor a set of user policies, including power consumption PjAnd gas consumption Qj；skFor operator policy set, including pj、qj、φjAndfusersthe sum of the net benefits of all users.
Wherein ρ represents an equilibrium policy vector of the operator, δ represents an optimal load prediction vector of the user, and when the condition shown in formula (11) is satisfied, (ρ, δ) is a supply and demand double equilibrium point of the supply and demand double game.
Wherein,for other balancing policies of the operator than policy k,
balancing the user except the strategy n;the minimum value and the maximum value of the electricity price are respectively;the minimum and maximum gas prices, respectively.
And 3, solving the game model by adopting a differential evolution algorithm.
And (3) the operator is used as a leading person of the supply and demand bilateral game, and the benefit function provided in the step 2 is optimized according to the load predicted value in the step 1 to formulate the energy price.
The user is used as a game follower, aiming at the price of an operator, the net effect is the maximum target, the energy consumption is adjusted on the basis of the load predicted value, and the adjusted energy consumption value Lj, g is fed back to the operator; and (4) judging whether the energy utilization value fed back by the user reaches a stable value or not by the operator, if not, re-formulating the energy price and re-playing the game, and if so, turning to the step (4).
Wherein, the stable condition is judged as: lj,m-lj,m-1|<ε，Wherein lj,mEnergy price for class j users for mth game, lj,m-1For the m-1 game, the energy price of the class j users is equal to the value of epsilon, the value of epsilon is close to 0, and the value of epsilon is 10-6And if the energy prices obtained by the two previous and next games are almost the same, judging that the stable condition is achieved.
Step 4, judging the energy consumption predicted value | L of the game and the LSTM networkj,g-Lj,g-1If the condition is satisfied, | the prediction effect is achieved if the condition is satisfied, the load prediction result is output, otherwise, the step 1 is carried out, the energy price is updated to correct the LSTM network influence factor, the load is predicted again, and the steps are repeated until the load prediction value and the energy price are stable.
Wherein, the convergence condition is judged as: lj,g-Lj,g-1|<θ, wherein Lj,gPredicted value of energy for class j users at the g-th time, Lj,g-1The predicted value of energy for the g-1 th time of j-class users is theta which is a value close to 0 and can be taken as 10-6That is, if the predicted values of the energy consumption obtained by the two previous and subsequent predictions are almost the same, it is determined that the convergence condition is reached.
DETAILED DESCRIPTION OF EMBODIMENT (S) OF INVENTION
The basic data of the embodiment of the invention is from a certain garden in Bay of Australia, Guangdong province, the garden consists of an electric power system and a natural gas system and comprises energy conversion equipment such as P2G, a gas turbine and the like, wherein the conversion efficiency of P2G is 0.64, the electric energy-heat energy conversion coefficient is 1.043kJ/kWh, and the high heat value of the natural gas is 35.88MJ/m 3; the values of alpha, beta and gamma in the gas turbine model are 0, 0.17 and 0 respectively.
The users in the garden are abundant, and besides the electricity and gas consumption of general industry, business and residential users, there are few electricity and gas consumption users of the first industry. Data from 2013 to 2017 are used as basic data, and through data preprocessing and correlation analysis, the weight coefficients of all the influencing factors are shown in table 1.
TABLE 1
Training the LSTM network to obtain a training network; and predicting electricity/gas consumption of each industry year by taking the data of 2018 as test data, wherein model parameters of the LSTM network are set as follows: 8 layers of hidden layers, and the number of iterations is 600.
And solving the target function to be the minimum value by the differential evolution algorithm, taking the negative of the target utility functions of the load side and the operator as the target function, and taking the inverse number of the calculation result as the actual benefit. Under the supply and demand bilateral game mechanism, the calculation objective functions of the load side and the operator are changed as shown in fig. 4, and as can be seen from fig. 4, when the net effectiveness of the user side is reduced to 73871 ten thousand yuan, the net benefit of the operator is hardly increased, and the game balance is achieved at this time.
The income condition pair of each subject before and after the game is shown in table 2, and the predicted value of the user electricity/gas pricing and energy consumption demand after the game is shown in table 3. As can be seen from Table 2, after the supply and demand bilateral game, the comprehensive benefits of the user side are improved compared with those of the game.
TABLE 2
| First industry | Industrial process | Commerce | Residents | |
| Price of electricity/[ Yuan/kWh] | 0.4798 | 0.8011 | 0.9377 | 0.5051 |
| Gas value/[ Yuan/m 3] | / | 3.1158 | 3.1158 | 3.4153 |
| Electricity consumption/thousands kWh | 95.68 | 320.66 | 4070.4 | 982.01 |
| Gas consumption/m 3 | / | 117.83 | 1596 | 330.33 |
TABLE 3
Before the game, the electricity prices of the first industry, business and residents are respectively: 0.516 yuan/kwh, 0.875 yuan/kwh, 0.938 yuan/kwh, 0.628 yuan/kwh, and the gas prices of industry, business, and residents are respectively: 3.12 yuan/m 3, 3.12 yuan/m 3, 3.45 yuan/m 3. It can be known from table 3 that, because the electricity/gas price is reduced compared with that before the game, the income of the operator is reduced, but after the game, the operator reduces the use of the P2G equipment with higher operation cost by adjusting the energy supply mode, increases the operation of the gas turbine, effectively reduces the operation cost of the energy supply side, and increases 448.69 ten thousand yuan compared with that before the game. The predicted load value and the error value are shown in table 4, and it can be seen from table 4 that the energy demand of industrial and commercial users is increased before and after the game, and the energy demand of residential and commercial users is reduced compared with that before the game in consideration of the utility of the residential users.
| Actual value | Prediction value | Relative error | |
| Total power consumption | 5344.47 | 5468.75 | 2.32％ |
| First industrial power consumption | 96.86 | 95.68 | 1.21％ |
| Electric power for industry | 318.49 | 320.66 | 0.68％ |
| Commercial electricity consumption | 3939.34 | 4070.4 | 3.33％ |
| Electricity consumption of residents | 989.78 | 982.01 | 0.78％ |
| Total gas consumption | 2064.11 | 2044.16 | 1.06％ |
| Gas consumption in industry | 120.87 | 117.83 | 2.51％ |
| Commercial gas consumption | 1569.69 | 1596 | 1.67％ |
| Gas consumption for residents | 342.55 | 330.33 | 3.44％ |
TABLE 4
The invention provides an energy consumption prediction system and method for a supply and demand bilateral game, which are an energy consumption demand prediction method for an electric-gas interconnection system considering the supply and demand bilateral game and can predict energy consumption demands from different time scales. The invention is equally applicable if the multi-energy system includes not only electrical/gas loads but also other demand forecasts such as cold, hot, hydraulic loads. Similarly, if the game subject is increased in the multi-energy system, for example, the energy producer, the energy operator and the user all participate in the energy market game, the invention is also applicable. The prediction method and the method for solving the game model are respectively an LSTM network and a differential evolution algorithm, the relation between supply and demand interaction and energy demand prediction in the multi-energy system is comprehensively considered, and the supply and demand interaction game is considered in the load prediction process of the multi-energy system, so that the load prediction value is more accurate.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. An energy utilization prediction method for a supply and demand bilateral game is characterized by comprising the following steps:
s1: carrying out energy utilization load prediction by using an LSTM network, wherein the LSTM network is trained by using a learning sample;
s2: establishing a supply and demand bilateral game model for supply and demand interaction according to a benefit model of a user participating in a supply and demand bilateral game and a benefit model of an energy operator participating in the supply and demand bilateral game;
s3: performing a supply and demand bilateral game by using the supply and demand bilateral game model, judging whether a stable condition is met, and if so, executing S4; if not, updating the load and carrying out the supply and demand double-side game again;
s4: judging whether a convergence condition is met, if so, outputting a load predicted value; if not, go to S5;
s5: and updating the energy price, correcting the LSTM network influence factor, and repeatedly executing S3 until the load predicted value and the energy price are stable.
2. The method for predicting the energy consumption of the supply and demand bilateral game as claimed in claim 1, wherein the benefit model of the demand side participating in the supply and demand bilateral game further comprises: f. ofj＝Ej-Bj；
Wherein f isjNet utility for class j users, BjEnergy cost for class j users, EjThe energy utilization efficiency function is a j-type user;
Bj＝pjPj+qjQj，Ej＝kjln(1+Pj+eQj)，pj、qjelectricity and gas prices, P, for class j users respectivelyj、QjElectricity and gas consumption, k, for j-class users respectivelyjAnd the preference coefficient represents the preference coefficient of j types of users for consuming electric energy, and epsilon is a gas/electricity conversion coefficient.
3. The energy utilization prediction method of the supply and demand bilateral game as claimed in claim 2, wherein the supply and demand bilateral game is executed by using the supply and demand bilateral game model, and the determination of whether the stability condition is satisfied further comprises that the operator optimizes the energy utilization function according to the predicted load value to formulate the energy price; the user adjusts the energy value and feeds back the energy value to the operator; and the operator judges whether the energy utilization value of the user reaches a stable condition.
4. The energy consumption prediction method for the supply and demand bilateral game as claimed in claim 1, wherein determining whether the convergence condition is satisfied further comprises determining whether the predicted energy consumption value after the game and the predicted energy consumption value of the LSTM network satisfy the convergence condition.
5. The method for predicting the energy consumption of the supply and demand bilateral game as claimed in claim 1, wherein the participation of the energy operator in the benefit model of the supply and demand bilateral game further comprises: f. ofsup＝Esup-Csup-Cp2g-Cgt；
Wherein E issupFor the energy sales profits of the operator, Cp2g、CgtOperating costs, C, of the P2G plant and the gas boiler, respectively, in the electrical interconnection systemsupAs a function of the cost of energy supply to the operator.
6. The method for predicting the availability of a bilateral game in supply and demand according to claim 1, wherein the bilateral game model in supply and demand is selected from the group consisting of,
G＝{U∪S,{un},{sk},{fusers},{fsup}} n∈U,k∈S
wherein u isnFor user policy sets, including power consumption P of class j usersjAnd gas usage Q of class j usersj；SkFor operator policy set, including pj、qj、φjAnd
pj、qjrespectively the electricity price and the gas price of the j-class users, phi j is the proportion of the electricity consumption of the j-class users from the power supply of the gas turbine,
the gas consumption for the j-type users is derived from the proportion of the gas supply of the P2G equipment; f. ofusersThe sum of the net benefits of all users.
7. The method for predicting the use of supply and demand bilateral gaming according to claim 1, wherein satisfaction of the supply and demand bilateral gaming is satisfied
(ρ, δ) of the condition is an equilibrium point of the offer-demand bilateral game;
wherein,
for other balancing policies of the operator than policy k,
balancing the user except the strategy n;
the minimum value and the maximum value of the electricity price are respectively;
the minimum value and the maximum value of the gas price are respectively; ρ represents the operator's balancing policy vector, δ represents the optimal load prediction vector for the user.
8. The method for predicting energy use in bilateral gaming of supply and demand as claimed in claim 5 wherein CsupThe cost function of energy supply to the operator further comprises:
Csup＝fP(Psup)+fQ(Qsup)，
wherein f isP(Psup)、fQ(Qsup) The costs of power supply and gas supply for the operator respectively;
cost coefficient for supplying power and gas to the operator. Psup、QsupRespectively the total electricity and gas consumption of the operator.
9. The method for predicting the availability of a bilateral game in accordance with claim 8, wherein the method comprisesIn that P issup、QsupThe total electricity and gas usage, respectively, for the operator further comprises:
phi j is the proportion of j types of user power consumption from power supply of the gas turbine;
the gas consumption for the j-type users is derived from the proportion of the gas supply of the P2G equipment; eta P2g is the overall conversion efficiency of P2G equipment, and can reach 60-70% at present; vE is the conversion coefficient of electric energy and heat energy, unit: MJ/kWh; hg is the high heating value of natural gas, unit: MJ/m 3; and alpha, beta and gamma are respectively the energy consumption coefficients of the gas turbine.
10. An energy use prediction system for a bilateral game based on any one of claims 1 to 9, comprising:
the load prediction module is used for predicting the energy load of the predicted year by using the LSTM network;
the energy operator module is used for optimizing a target function according to the energy load predicted value of the user module and formulating the energy selling price facing the user module;
the user module is used for adjusting the load predicted value according to the price formulated by the energy operator module and feeding back information to the energy operator module;
and the judging module is used for judging whether the energy load predicted value and the energy price reach stability.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910913765.7A CN110648251A (en) | 2019-09-25 | 2019-09-25 | Energy utilization prediction system and method for supply and demand bilateral game |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910913765.7A CN110648251A (en) | 2019-09-25 | 2019-09-25 | Energy utilization prediction system and method for supply and demand bilateral game |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110648251A true CN110648251A (en) | 2020-01-03 |
Family
ID=69011276
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910913765.7A Pending CN110648251A (en) | 2019-09-25 | 2019-09-25 | Energy utilization prediction system and method for supply and demand bilateral game |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110648251A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111476675A (en) * | 2020-03-16 | 2020-07-31 | 昆明电力交易中心有限责任公司 | Distributed balanced interactive control method of comprehensive energy system based on demand response |
| CN111489031A (en) * | 2020-04-09 | 2020-08-04 | 江苏方天电力技术有限公司 | Medium- and long-term load forecasting system and method for integrated energy system based on source-load evolutionary game |
| CN118134540A (en) * | 2024-05-07 | 2024-06-04 | 国网浙江省电力有限公司 | Multidimensional data interaction method and system based on energy power supply and demand prediction model |
-
2019
- 2019-09-25 CN CN201910913765.7A patent/CN110648251A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111476675A (en) * | 2020-03-16 | 2020-07-31 | 昆明电力交易中心有限责任公司 | Distributed balanced interactive control method of comprehensive energy system based on demand response |
| CN111476675B (en) * | 2020-03-16 | 2023-11-03 | 昆明电力交易中心有限责任公司 | Comprehensive energy system distributed equilibrium interactive control method based on demand response |
| CN111489031A (en) * | 2020-04-09 | 2020-08-04 | 江苏方天电力技术有限公司 | Medium- and long-term load forecasting system and method for integrated energy system based on source-load evolutionary game |
| CN111489031B (en) * | 2020-04-09 | 2022-06-03 | 江苏方天电力技术有限公司 | Medium- and long-term load forecasting system and method for integrated energy system based on source-load evolutionary game |
| CN118134540A (en) * | 2024-05-07 | 2024-06-04 | 国网浙江省电力有限公司 | Multidimensional data interaction method and system based on energy power supply and demand prediction model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108921329B (en) | An optimal matching method for food transactions based on blockchain technology | |
| CN110648251A (en) | Energy utilization prediction system and method for supply and demand bilateral game | |
| CN110378729A (en) | A kind of integration requirement response method based on dynamic energy price strategy | |
| Li et al. | Knee Point‐Guided Multiobjective Optimization Algorithm for Microgrid Dynamic Energy Management | |
| CN111476399A (en) | Electricity purchasing method and system for electricity selling company under spot transaction mechanism | |
| CN112132309B (en) | Electricity purchasing optimization method and system for electricity selling company under renewable energy power generation quota system | |
| CN113344651A (en) | Multi-energy-supply main body planning method for comprehensive energy market under carbon trading mechanism | |
| CN111178956A (en) | Trading model and quotation strategy applicable to cross-country electricity-carbon market | |
| CN109657869A (en) | High-latitude severe cold area transformer substation LCC prediction model based on SSA-LSSVM | |
| Liaquat et al. | Day‐ahead continuous double auction‐based peer‐to‐peer energy trading platform incorporating trading losses and network utilisation fee | |
| Yu et al. | Continuous group-wise double auction for prosumers in distribution-level markets | |
| Liu et al. | A scalable energy management mechanism for peer-to-peer electricity market | |
| CN112651544A (en) | Incremental power distribution multi-main-body coordination optimization method | |
| CN114529323B (en) | Demand response excitation decision optimization method based on efficiency loss ratio | |
| CN109344997A (en) | A method and system for multi-regional electric energy trading | |
| CN110189231B (en) | Method for determining optimal power supply scheme of power grid based on improved genetic algorithm | |
| CN116882771A (en) | Zero-carbon community energy sharing method and system considering carbon rewards and punishments under master-slave game | |
| Singh et al. | A reduced network representation suitable for fast nodal price calculations in electricity markets | |
| CN112488740A (en) | Processing method and device for target balance game | |
| CN117039982A (en) | Transaction method suitable for wind, light and fire coupling participating in monthly centralized market | |
| CN113570405A (en) | A method and device for modeling and analyzing the cost of generating and using electricity in a self-provided power plant | |
| Lan et al. | Scalable Peer-to-Peer Energy Trading System With Microgrid Coalitions | |
| CN111915351A (en) | TOPSIS (technique for order preference by similarity to similarity) method-based method for evaluating importance of users in photovoltaic user group | |
| CN119648260A (en) | A power grid topology optimization control method and its application | |
| CN116957163B (en) | A multi-microgrid transaction optimization method, system, device and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200103 |