A method and system for distributed autonomy and collaborative optimization of multi-regional integrated energy systems

Abstract

The present invention belongs to the field of regional integrated energy system operation, and discloses a distributed autonomy and collaborative optimization method and system for multi-regional integrated energy systems, the method comprising: collecting dynamic data and static data in each park integrated energy system, inputting a pre-established park integrated energy system autonomous operation model based on multi-agent reinforcement learning in each park integrated energy system, and obtaining the control strategy of the equipment in each park integrated energy system; based on the control strategy of the equipment in each park integrated energy system, calling a pre-established evolutionary game model, and obtaining the purchase electricity price and retail electricity price of the regional integrated energy system, as well as the electricity transaction volume and transaction price between the park integrated energy systems. The present invention divides the operation optimization problem of the regional integrated energy system into two stages: park autonomous operation and regional collaborative optimization, and uses the integrated energy system to achieve multi-energy complementarity and mutual assistance, so as to improve the overall energy efficiency and energy supply reliability of the regional integrated energy system.

Description

Technical Field

[0001] The present invention belongs to the field of regional integrated energy system operation, and in particular relates to a method and system for distributed autonomy and collaborative optimization of a multi-regional integrated energy system. Background Art

[0002] The safe supply of energy is the premise for ensuring the sustainable development of society. How to achieve reliable energy supply under the heavy pressure of the substantial growth of energy demand and the increasingly urgent environmental protection is one of the key research focuses in this field. The uncertainty of new energy itself makes it difficult to meet the reliability requirements of energy supply by relying solely on a single energy form. Therefore, the integrated energy system will become the main energy carrier form of human society in the future.

[0003] An integrated energy system refers to a new type of integrated energy system that uses advanced physical information technology and innovative management models to integrate multiple energy sources such as electricity, natural gas, and thermal energy in a certain area, and achieve coordinated planning, optimized operation, collaborative management, interactive response, and mutual complementarity among multiple heterogeneous energy subsystems. While meeting the diversified energy needs within the system, it is necessary to effectively improve energy utilization efficiency and promote sustainable energy development. An integrated energy system is an energy system that integrates generation, use, storage, and coupling equipment. It mainly includes combined heat and power (CHP) units, electric energy storage, photovoltaic power generation, gas boilers, energy-consuming equipment, etc. Among them, electrical loads include air conditioning, lighting, power, etc., and gas loads and thermal loads include residential gas and residential heating, etc., respectively. See Figure 1 shown.

[0004] The integrated energy system helps eliminate the bottleneck of the power transmission and distribution system, delay the construction of the power generation / transmission / distribution system, and improve the utilization efficiency of various energy equipment through the organic coordination of multiple energy systems; when the power or gas system is interrupted due to weather or unexpected disasters, local energy can be used to achieve uninterrupted power supply to important users, and provide power support for the rapid recovery of the power supply system after the failure, so as to effectively improve the energy reliability supply capacity. It is of great significance to carry out research on the multi-energy coordinated operation optimization technology of regional integrated energy systems and realize multi-energy complementarity and mutual assistance. Therefore, a regional integrated energy system distributed autonomy and collaborative optimization method and system are urgently needed to realize the autonomous operation of the internal equipment layer of the integrated energy system and the complementarity and mutual assistance of external energy forms, so as to improve the overall energy efficiency and energy supply reliability of the regional integrated energy system.

[0005] Chinese patent application CN202111135601.X discloses a method for optimizing the coordinated operation of an integrated energy microgrid group based on double-layer optimization, which provides an integrated energy microgrid group consisting of a large power grid and multiple integrated energy microgrids, each of which has a corresponding distributed power generation subsystem, energy storage subsystem, and energy consumption subsystem; a mixed integer nonlinear optimization model of the local and regional scheduling layers is constructed, and solved using the Lindo solver. Among them, the local optimization of the double-layer optimization takes the maximum electricity sales revenue as the optimization goal, and the optimization model of the regional layer takes the minimization of the total operating cost as the goal.

[0006] Disadvantages of existing technology:

[0007] 1. The local dispatching layer of the two-layer dispatching optimization model only takes the maximum electricity sales revenue as the optimization goal, without considering the uncertainty of new energy and the access and consumption goals, and cannot meet the requirements of a high proportion of new energy access and consumption in the new power system;

[0008] 2. The two-layer scheduling optimization model is a mixed integer nonlinear model based on simplified construction, which is solved by using Lindo solver. On the one hand, there is still a gap between the simplified model and the actual scenario. On the other hand, the method of solving by using solver takes a lot of time to iterate and there is a risk of failure to solve.

[0009] 3. This two-layer dispatch optimization model does not take into account the game relationship between the local dispatch layer and the regional dispatch layer, which does not conform to the actual situation, does not reflect the guiding role of market prices, and does not conform to the future development trend of using the market to regulate energy supply. Summary of the invention

[0010] The object of the present invention is to provide a method and system for distributed autonomy and collaborative optimization of a multi-regional integrated energy system to solve at least one of the above-mentioned technical problems.

[0011] In order to achieve the above object, the present invention adopts the following technical solution:

[0012] In a first aspect, the present invention provides a method for distributed autonomy and collaborative optimization of a multi-region integrated energy system, comprising:

[0013] Collect dynamic and static data from the integrated energy system of each park, input the pre-established autonomous operation model of the integrated energy system of each park based on multi-agent reinforcement learning, and obtain the control strategy of the equipment in the integrated energy system of each park;

[0014] Based on the control strategies of the equipment in the integrated energy systems of each park, the pre-established evolutionary game model is called to obtain the purchase electricity price, retail electricity price of the regional integrated energy system, as well as the electricity transaction volume and transaction price between the integrated energy systems of each park.

[0015] A further improvement of the present invention is that in the step of collecting dynamic data and static data in each park integrated energy system, the dynamic data includes electricity data, gas data and heat data; the static data includes parameters of each device in the park integrated energy system, network topology and external parameters of the park integrated energy system.

[0016] A further improvement of the present invention is that in the step of inputting the autonomous operation model of the park integrated energy system based on multi-agent reinforcement learning established in advance by each park integrated energy system to obtain the control strategy of the equipment in each park integrated energy system, the state space, action space, interaction process and reward function of the autonomous operation model of the park integrated energy system based on multi-agent reinforcement learning are specifically:

[0017] State Space:

[0018] The state space S includes the wind power output P within the energy hub area. pv , Photovoltaic output P so , electrical load L e , heat load L h 、Electricity price e Gas price g 、Hot price h 、Power system node voltage U E 、Gas system node pressure π G 、Thermodynamic system node temperature T H ;

[0019] S={P pv ,P so ,L e ,L h ,c e ,c g ,c h ,U E ,π G ,T H} (15)

[0020] Action Space:

[0021] The variables in the action space A include the power of the energy hub interacting with the electric power system, thermal system, and natural gas system respectively:

[0022] A={P e ,P h ,P g} (16)

[0023] Interaction process:

[0024] The park integrated energy system model is used as the environment. After each energy hub takes action at each moment, a comprehensive energy system flow calculation is performed, and the relevant state quantities of the power system, thermal system, and natural gas system nodes are fed back to calculate the reward function and transferred to the next moment.

[0025] Reward function:

[0026] The opposite of the objective function of the park integrated energy system model is used as the instant reward of each energy hub. According to the constraints described in formula (5), if the corresponding variable does not meet the constraints, the penalty value r is set. push , together with the immediate reward, serves as the final reward function of the energy hub:

[0027] R={F+r push} (17)

[0028] Among them, the park comprehensive energy system model is:

[0029]

[0030] Where: L e , L h are the electrical load and thermal load within the energy hub area, η is the equipment efficiency factor, υ is the allocation factor, subscripts e, g, h represent the types of electricity, gas, and heat energy, respectively, and the superscript represents the conversion device. new Represents photovoltaic or wind power;

[0031] Constraints on the park's integrated energy system include:

[0032]

[0033]

[0034]

[0035]

[0036]

[0037]

[0038]

[0039]

[0040]

[0041] In the formula, They are respectively the upper and lower limits of active power obtained from the regional integrated energy system, To obtain active power from the regional integrated energy system, They are respectively used to obtain the upper and lower limits of reactive power from the regional integrated energy system. To obtain reactive power from the regional integrated energy system, are the upper and lower limits of the power system branch power, is the power system branch power, are the upper and lower limits of the voltage of the power system network nodes, U i is the voltage of the power system network node, are the upper and lower limits of gas pressure at natural gas network nodes, π i is the gas network node pressure, They are the upper and lower limits of gas supply at the gas source point, is the gas supply volume at the gas source point, are the upper and lower limits of the natural gas system pipeline flow, is the pipeline flow rate of the natural gas system, They are the upper and lower limits of the heat supply of the heat source point in the centralized heating network. The heat supply for the heat source point of the central heating network, T i max 、T i min are the upper and lower limits of node temperature in the central heating network, T i is the node temperature in the district heating network;

[0042] The objective function of the park's integrated energy system is:

[0043] F=min(c e P e +c g P g +c h P h )

[0044] Where: c e 、c h 、c g are the cost coefficients of energy interaction between the energy hub and the power system, thermal system and natural gas system respectively.

[0045] A further improvement of the present invention is that it also includes the step of sending the obtained control strategies of the equipment in each park comprehensive energy system to each equipment in the district comprehensive energy system for execution; the control strategies of the equipment include the output of the energy unit, the playback of the energy storage device and the conversion power of the coupling device.

[0046] A further improvement of the present invention is that: in the step of calling a pre-established evolutionary game model based on the control strategy of the equipment in each park integrated energy system to obtain the purchase electricity price, retail electricity price of the regional integrated energy system, and the electricity transaction volume and transaction price between the integrated energy systems of each park, the evolutionary game model is:

[0047]

[0048]

[0049] In the formula, I DSO Net profit for the regional integrated energy system; are the buying wholesale price and selling wholesale price of the energy market in period t, are the retail buying price and retail selling price set by the regional integrated energy system in period t, denoted as P t DSO,s , P t DSO,b are the wholesale power sold and the wholesale power bought in the energy market during period t; P ex,t , P im,t is the retail buying power and retail selling power of the regional comprehensive energy system during period t; Ω DSO is the set of constraints on electricity prices.

[0050] A further improvement of the present invention is that: in the step of calling the pre-established evolutionary game model to obtain the purchase electricity price, retail electricity price of the regional integrated energy system, and the electricity transaction volume and transaction price between the integrated energy systems of each park, specifically:

[0051] The pre-established evolutionary game model is called, with the regional integrated energy system and the integrated energy systems of each park as the two parties of the game. The regional integrated energy system uses the purchase and sale price of electricity as the decision variable, and the integrated energy system of each park uses the purchase and sale of electricity and the output of each equipment as the decision variable. The regional integrated energy system uses the net profit of the regional integrated energy system I DSO As the profit function, the park integrated energy system minimizes the operating cost C RIES The revenue function is solved to obtain the purchase electricity price, retail electricity price of the regional integrated energy system, and the electricity transaction volume and transaction price between the integrated energy systems of each park.

[0052] In a second aspect, the present invention provides a multi-region integrated energy system distributed autonomy and collaborative optimization system, comprising:

[0053] Data collection module, used to collect dynamic and static data from the integrated energy system of each park;

[0054] The autonomous operation module is used to input the collected dynamic data and static data from each park integrated energy system into the autonomous operation model of the park integrated energy system based on multi-agent reinforcement learning pre-established by each park integrated energy system, and obtain the control strategy of the equipment in each park integrated energy system;

[0055] The collaborative optimization module is used to call the pre-established evolutionary game model based on the control strategy of the equipment in the integrated energy system of each park, to obtain the purchase electricity price, retail electricity price of the regional integrated energy system, and the electricity transaction volume and transaction price between the integrated energy systems of each park.

[0056] A further improvement of the present invention is that in the data acquisition module, the dynamic data includes electricity data, gas data and heat data; the static data includes parameters of each device in the park comprehensive energy system, network topology and external parameters of the park comprehensive energy system.

[0057] A further improvement of the present invention is that in the autonomous operation module, the state space, action space, interaction process and reward function of the autonomous operation model of the park integrated energy system based on multi-agent reinforcement learning are specifically:

[0058] State Space:

[0059] The state space S includes the wind power output P within the energy hub area. pv , Photovoltaic output P so , electrical load L e , heat load L h 、Electricity price e Gas price g 、Hot price h 、Power system node voltage U E 、Gas system node pressure π G 、Thermodynamic system node temperature T H ;

[0060] S={P pv ,P so ,L e ,L h ,c e ,c g ,c h ,U E ,π G ,T H} (twenty two)

[0061] Action Space:

[0062] The variables in the action space A include the power of the energy hub interacting with the electric power system, thermal system, and natural gas system respectively:

[0063] A={Pe ,P h ,P g} (twenty three)

[0064] Interaction process:

[0065] The park integrated energy system model is used as the environment. After each energy hub takes action at each moment, a comprehensive energy system flow calculation is performed, and the relevant state quantities of the power system, thermal system, and natural gas system nodes are fed back to calculate the reward function and transferred to the next moment.

[0066] Reward function:

[0067] The opposite of the objective function of the park integrated energy system model is used as the instant reward of each energy hub. According to the constraints described in formula (5), if the corresponding variable does not meet the constraints, the penalty value r is set. push , together with the immediate reward, serves as the final reward function of the energy hub:

[0068] R={F+r push} (twenty four)

[0069] Among them, the park comprehensive energy system model is:

[0070]

[0071] Where: L e , L h are the electrical load and thermal load within the energy hub area, η is the equipment efficiency factor, υ is the allocation factor, subscripts e, g, h represent the types of electricity, gas, and heat energy, respectively, and the superscript represents the conversion device. new Represents photovoltaic or wind power;

[0072] Constraints on the park's integrated energy system include:

[0073]

[0074]

[0075]

[0076]

[0077]

[0078]

[0079]

[0080]

[0081]

[0082] In the formula, They are respectively the upper and lower limits of active power obtained from the regional integrated energy system, To obtain active power from the regional integrated energy system, They are respectively used to obtain the upper and lower limits of reactive power from the regional integrated energy system. To obtain reactive power from the regional integrated energy system, are the upper and lower limits of the power system branch power, is the power system branch power, are the upper and lower limits of the voltage of the power system network nodes, U i is the voltage of the power system network node, are the upper and lower limits of gas pressure at natural gas network nodes, π i is the gas network node pressure, They are the upper and lower limits of gas supply at the gas source point, is the gas supply volume at the gas source point, are the upper and lower limits of the natural gas system pipeline flow, is the pipeline flow rate of the natural gas system, They are the upper and lower limits of the heat supply of the heat source point in the centralized heating network. The heat supply for the heat source point of the central heating network, T i max 、T i min are the upper and lower limits of node temperature in the central heating network, T i is the node temperature in the district heating network;

[0083] The objective function of the park's integrated energy system is:

[0084] F=min(c e P e +c g P g +c h P h )

[0085] Where: c e 、c h 、c g are the cost coefficients of energy interaction between the energy hub and the power system, thermal system and natural gas system respectively.

[0086] A further improvement of the present invention is that it also includes:

[0087] The instruction issuing module is used to issue the control strategies of the equipment in each park comprehensive energy system to each equipment in the district comprehensive energy system for execution; the control strategies of the equipment include the output of the energy unit, the playback of the energy storage device and the conversion power of the coupling device.

[0088] A further improvement of the present invention is that in the collaborative optimization module, the evolutionary game model is:

[0089]

[0090]

[0091] In the formula, I DSO Net profit for the regional integrated energy system; are the buying wholesale price and selling wholesale price of the energy market in period t, are the retail buying price and retail selling price set by the regional integrated energy system in period t, denoted as P t DSO,s , P t DSO,b are the wholesale power sold and the wholesale power bought in the energy market during period t; P ex,t , P im,t is the retail buying power and retail selling power of the regional comprehensive energy system during period t; Ω DSO is the set of constraints on electricity prices.

[0092] The present invention is further improved in that the collaborative optimization module calls the pre-established evolutionary game model to obtain the purchase electricity price and retail electricity price of the regional integrated energy system, as well as the electricity transaction volume and transaction price between the integrated energy systems of each park, specifically including:

[0093] The pre-established evolutionary game model is called, with the regional integrated energy system and the integrated energy systems of each park as the two parties of the game. The regional integrated energy system uses the purchase and sale price of electricity as the decision variable, and the integrated energy system of each park uses the purchase and sale of electricity and the output of each equipment as the decision variable. The regional integrated energy system uses the net profit of the regional integrated energy system I DSO As the profit function, the park integrated energy system minimizes the operating cost C RIES The revenue function is solved to obtain the purchase electricity price, retail electricity price of the regional integrated energy system, and the electricity transaction volume and transaction price between the integrated energy systems of each park.

[0094] Compared with the prior art, the present invention has the following beneficial effects:

[0095] The present invention provides a method and system for distributed autonomy and collaborative optimization of a multi-regional integrated energy system, which collects dynamic data and static data from the integrated energy systems of each park, inputs the autonomous operation model of the integrated energy system of each park based on multi-agent reinforcement learning pre-established in the integrated energy system of each park, and obtains the control strategy of the equipment in the integrated energy system of each park; thereby realizing the autonomy of the integrated energy system of each park; further, based on the control strategy of the equipment in the integrated energy system of each park, calling the pre-established evolutionary game model, obtaining the purchase electricity price and retail electricity price of the regional integrated energy system, as well as the electricity transaction volume and transaction price between the integrated energy systems of each park; on the basis of the distributed autonomy of each region, based on the mathematical idea of ​​evolutionary game, under the assumption of limited rationality, the collaborative optimization of each subject is realized based on evolutionary game; the problem that the operation optimization of the regional integrated energy system has non-convex nonlinearity due to the multi-energy coupling characteristics, and the traditional method is difficult to meet its operation optimization needs is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0097] Figure 1 This is a schematic diagram of the structure of the integrated energy system;

[0098] Figure 2 A schematic diagram of a regional integrated energy system distribution autonomy and collaborative optimization method of the present invention;

[0099] Figure 3 A schematic diagram of a regional integrated energy system distributed autonomy and collaborative optimization system architecture of the present invention;

[0100] Figure 4 This is a schematic diagram of the autonomous operation model of the park integrated energy system based on multi-agent reinforcement learning;

[0101] Figure 5 The present invention is a flowchart of a method for distributed autonomy and collaborative optimization of a regional integrated energy system. DETAILED DESCRIPTION

[0102] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present invention can be combined with each other without conflict.

[0103] The following detailed description is an exemplary description, which is intended to provide further detailed description of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present invention belongs. The terms used in the present invention are only for describing specific embodiments, and are not intended to limit the exemplary embodiments according to the present invention.

[0104] Example 1

[0105] The purpose of the present invention is to propose a method and system for distributed autonomy and collaborative optimization of a regional integrated energy system, and to use the integrated energy system to achieve multi-energy complementarity and mutual assistance, so as to improve the overall energy efficiency and energy supply reliability of the regional integrated energy system.

[0106] See also Figure 2 As shown, the present invention proposes a regional integrated energy system distributed autonomy and collaborative optimization system, whose architecture includes three levels: energy market, regional integrated energy system (energy operator) and park integrated energy system (energy microgrid), and divides the operation optimization problem of the regional integrated energy system into two stages: park autonomous operation and regional collaborative optimization. Among them, the park autonomous operation is solved based on a multi-agent deep reinforcement learning model, with the dual goals of maximizing the use of new energy and minimizing operating costs, generating equipment-level operation strategies such as energy output, energy storage charging and discharging, and coupled equipment conversion power; regional collaborative optimization is based on the results of autonomous operation and evolutionary game models, with the goal of achieving comprehensive maximization of the benefits of energy operators and the benefits of each park integrated energy system, solving the energy transaction volume and transaction price of each park, and ultimately improving the overall energy efficiency of the regional integrated energy system.

[0107] See also Figure 3 As shown in the figure, this system mainly includes 3 layers and 5 modules: the equipment layer includes 2 modules: data acquisition and control instruction issuance; the platform layer is an energy trading sharing platform; the algorithm layer includes 2 modules: autonomous operation and collaborative optimization.

[0108] (1) Equipment layer

[0109] 1) Data acquisition module: mainly includes data acquisition devices such as smart electricity meters, gas meters and heat meters. Since the collected data is needed to carry out source and load identification, the collection cycle is set to 1 minute, and the data used is fine-grained integrated energy system data.

[0110] 2) Control instruction sending model: It mainly implements the device control strategy instructions generated by the algorithm layer and sends them to the controllable devices in the integrated energy system, such as cogeneration units, electric energy storage, heat storage tanks, ice storage, etc.

[0111] (2) Platform layer

[0112] Energy trading sharing platform: mainly receives energy data uploaded by the data acquisition module of the device layer, provides it to the algorithm layer after data processing, and receives the output of the algorithm layer and converts it into control instructions to be sent to the instruction sending module of the device layer;

[0113] Data processing includes:

[0114] 1) Preprocessing: De-noise and normalize the collected energy data to obtain data types that meet the requirements of load monitoring;

[0115] 2) Feature extraction: Input the sliding window data into the set deep neural network model to extract the features of multi-function devices;

[0116] 3) Source and load identification: Identify multi-energy devices based on the extracted features and identify the operating status and operating power of the devices.

[0117] The main workflow of the energy trading sharing platform:

[0118] 1) Receive and store static and dynamic data of the integrated energy system;

[0119] 2) Process the data;

[0120] 3) Transmit the processed data to the autonomous operation and collaborative optimization algorithm module;

[0121] 4) Receive the integrated energy system equipment action strategy given by the algorithm module;

[0122] 5) Convert the device control strategy into specific device control instructions and send them to the device for execution.

[0123] (3) Algorithm layer

[0124] 1) Autonomous operation module: Aiming at the high-dimensional nonlinear and non-convex problems in the multi-energy flow coupling system, a multi-energy flow optimization scheduling model based on multi-agent deep reinforcement learning (MADDPG) is proposed based on the basic elements of environment, state, action, and reward to achieve regional autonomy.

[0125] The characteristic of this method is that an energy hub is set up in each park comprehensive energy system. The energy hub is the core equipment for realizing gas-electricity, electricity-heat, and gas-heat energy conversion in the comprehensive energy system. The energy hub is taken as the main decision-making subject. The internal conversion equipment of the energy hub is mainly transformer, cogeneration (Cogeneration, combined heat and power, CHP), heat exchanger (Heat exchanger, HE) and electric boiler (Electric boiler, EB). It is assumed that under steady-state conditions, the energy loss in the energy hub only occurs in the conversion equipment. The electric, gas, and thermal power interacting from the power system, natural gas system, and heating system, as well as the electric power provided by the distributed energy in the region itself, are used as the input of the energy hub. The output of the energy hub is mainly electric power and thermal power to meet the internal electric and thermal load requirements of the region. The specific model is as follows:

[0126]

[0127] Where: L e , L h are the electrical load and thermal load within the energy hub area, η is the equipment efficiency factor, υ is the allocation factor, subscripts e, g, h represent the types of electricity, gas, and heat energy, respectively, and the superscript represents the conversion device. new Represents photovoltaic or wind power.

[0128] In order to ensure the safe and stable operation of the integrated energy system, in addition to satisfying the energy balance equation constraints of the electricity, gas and heat systems themselves, the following inequality constraints also need to be satisfied:

[0129]

[0130]

[0131]

[0132]

[0133]

[0134]

[0135]

[0136]

[0137]

[0138] In the formula They are respectively the upper and lower limits of active power obtained from the regional integrated energy system, To obtain active power from the regional integrated energy system, They are respectively used to obtain the upper and lower limits of reactive power from the regional integrated energy system. To obtain reactive power from the regional integrated energy system, are the upper and lower limits of the power system branch power, is the power system branch power, are the upper and lower limits of the voltage of the power system network nodes, U i is the voltage of the power system network node, are the upper and lower limits of gas pressure at natural gas network nodes, π i is the gas network node pressure, They are the upper and lower limits of gas supply at the gas source point, is the gas supply volume at the gas source point, are the upper and lower limits of the natural gas system pipeline flow, is the pipeline flow rate of the natural gas system, They are the upper and lower limits of the heat supply of the heat source point in the centralized heating network. The heat supply for the heat source point of the central heating network, T i max 、T i min are the upper and lower limits of node temperature in the central heating network, T i is the node temperature in the district heating network;

[0139] The objective function of the park's comprehensive energy system is to optimize the economic efficiency of each energy hub's region. The cost of each region is set as the cost of the energy hub's energy interaction with the power system, thermal system, and natural gas system, respectively, calculated as follows:

[0140] F=min(c e P e +c g P g +c h P h )

[0141] Where: c e 、c h 、c g are the cost coefficients of energy interaction between the energy hub and the power system, thermal system and natural gas system respectively.

[0142] Based on the above integrated energy system model and constraints, a park integrated energy system autonomous operation model based on multi-agent reinforcement learning is proposed. Figure 4 .

[0143] Its state space, action space, interaction process and reward function are designed as follows:

[0144] A) State Space

[0145] The state space S of the system mainly includes the output P of renewable energy in each energy hub area. new (including wind power P pv or Photovoltaic P so ), electrical load L e , heat load L h 、Electricity price e Gas price g 、Hot price h 、Power system node voltage U E 、Gas system node pressure π G 、Thermodynamic system node temperature T H ,Right now

[0146] S={P pv ,P so ,L e ,L h ,c e ,c g ,c h ,U E ,π G ,T H} (31)

[0147] B) Action Space

[0148] The variables in its action space A include the power of the energy hub interacting with the power system, thermal system, and natural gas system in the regional integrated energy system, namely

[0149] A={P e ,P h ,P g} (32)

[0150] C) Interaction process

[0151] Taking the integrated energy system model as the environment, after each agent takes an action at each moment, a comprehensive energy system flow calculation is performed, and the relevant state quantities of the power system, thermal system and natural gas system nodes are fed back to calculate the reward function, and then transferred to the next moment, and this cycle is repeated.

[0152] D) Reward Function

[0153] The opposite of the objective function of the integrated energy system model is used as the instant reward of each agent. According to the constraints described in formula (5), if the corresponding variable does not meet the constraints, the penalty value r is set. push , together with the immediate reward, is used as the final reward function of the agent, namely

[0154] R={F+r push} (33)

[0155] 2) Collaborative optimization module: Aiming at the decision-making conflicts caused by different stakeholders in the integrated energy systems of multiple parks, a cluster collaborative optimization model based on evolutionary game under unbalanced power is established, and a multi-agent game framework of the integrated energy system under the assumption of limited rationality is proposed. Based on autonomous operation, energy complementarity between the integrated energy systems of multiple parks is carried out based on evolutionary game to achieve collaborative optimization under the balance of interests of multiple subjects.

[0156] The feature of the present invention is that it is based on the mathematical idea of ​​evolutionary game, and under the assumption of bounded rationality, starting from the participants, strategy sets, and payment functions, on the basis of the distributed autonomy of each region, the multi-regional collaborative optimization is transformed into a problem of seeking a multi-agent strategy equilibrium, and the coordination between the optimization goals of each subject can be regarded as an evolutionary process between the players. Introduce energy operators to act as leaders of regional integrated energy systems, summarize the purchase and sales electricity reported by the integrated energy systems of each park, combine the on-grid electricity price and the grid electricity price, and formulate transaction electricity prices with the goal of maximizing their own profits; each park integrated energy system acts as a follower, reasonably arranges the output of each internal distributed power source with the goal of minimizing operating costs, formulates transaction electricity, and constitutes a master-slave game; in order to coordinate the interaction of electric energy between regions, the competitive relationship between different regions is considered, and the evolution of behavior is simulated through evolutionary games. Figure 2 .

[0157] The energy operator aims to maximize its net profit. The benefit function includes the purchase and sale costs and benefits with the regional integrated energy system and energy market, as shown in the following formula.

[0158]

[0159]

[0160] In the formula, I DSO Net profit for the regional integrated energy system; are the buying wholesale price and selling wholesale price of the energy market in period t, are the retail buying price and retail selling price set by the regional integrated energy system in period t, denoted as P t DSO,s , P t DSO,b are the wholesale power sold and the wholesale power bought in the energy market during period t; P ex,t , P im,t is the retail buying power and retail selling power of the regional comprehensive energy system during period t; Ω DSOis the set of constraints on electricity prices. To ensure that all regions are willing to trade with distribution network operators, the prices set should be within a reasonable strategy space.

[0161] The formula mainly includes three parts:

[0162] a) Participants: Energy operators and park integrated energy system clusters are the two parties in the game.

[0163] b) Strategy: The decision variable of the energy operator is the electricity purchase and sales price; the decision variable of the park's comprehensive energy system is the electricity purchase and sales amount. However, since the gas turbine output in each period, the charging and discharging amount of the energy storage equipment, etc. are closely related to the electricity purchase and sales strategy, the equipment output is also regarded as a decision variable and they participate in the game together.

[0164] c) Profit function: The profit functions of energy operators and the park integrated energy system are to maximize the net profit I DSO and minimize the operating cost C RIES .

[0165] The objective function of the optimization within the region is to minimize the operating cost, which is expressed as follows:

[0166]

[0167] in, They are fuel cost, operation and maintenance cost, transaction cost and environmental pollution penalty cost. gas For gas costs, LHV is the power generation, power generation efficiency and lower heating value of natural gas of the gas turbine in region i during period t, c mk is the unit power operation and maintenance cost of the kth equipment, They are the purchased and sold power and electricity price of region i in period t; is the emission of the eth item of pollutant per unit electricity of the kth micro-source, V e , Y e The unit environmental value of the pollutant in item e and the fine received.

[0168] Example 2

[0169] See also Figure 5 As shown, the present invention provides a method for distributed autonomy and collaborative optimization of a multi-region integrated energy system, comprising:

[0170] S1. Collect dynamic data and static data from the integrated energy system of each park, input the autonomous operation model of the integrated energy system of each park based on multi-agent reinforcement learning established in advance, and obtain the control strategy of the equipment in the integrated energy system of each park;

[0171] S2. Based on the control strategies of the equipment in the integrated energy systems of each park, the pre-established evolutionary game model is called to obtain the purchase electricity price, retail electricity price of the regional integrated energy system, and the electricity transaction volume and transaction price between the integrated energy systems of each park.

[0172] In the specific implementation, in the step of collecting dynamic data and static data in the integrated energy system of each park in step S1, the dynamic data includes electricity data, gas data and heat data; the static data includes the parameters of each equipment in the integrated energy system of the park, the network topology and external parameters of the integrated energy system of the park (energy time-sharing price, new energy output forecast).

[0173] In the specific implementation, in step S1, the autonomous operation model of the park integrated energy system based on multi-agent reinforcement learning pre-established by each park integrated energy system is input to obtain the control strategy of the equipment in each park integrated energy system. The state space, action space, interaction process and reward function of the autonomous operation model of the park integrated energy system based on multi-agent reinforcement learning are specifically:

[0174] State Space:

[0175] The state space S includes the wind power output P within the energy hub area. pv , Photovoltaic output P so , electrical load L e , heat load L h 、Electricity price e Gas price g 、Hot price h 、Power system node voltage U E 、Gas system node pressure π G 、Thermodynamic system node temperature T H ;

[0176] S={P pv ,P so ,L e ,L h ,c e ,c g ,c h ,U E ,π G ,T H} (36)

[0177] Action Space:

[0178] The variables in the action space A include the power of the energy hub interacting with the electric power system, thermal system, and natural gas system respectively:

[0179] A={P e ,P h ,P g} (37)

[0180] Interaction process:

[0181] The park integrated energy system model is used as the environment. After each energy hub takes action at each moment, a comprehensive energy system flow calculation is performed, and the relevant state quantities of the power system, thermal system, and natural gas system nodes are fed back to calculate the reward function and transferred to the next moment.

[0182] Reward function:

[0183] The opposite of the objective function of the park integrated energy system model is used as the instant reward of each energy hub. According to the constraints described in formula (5), if the corresponding variable does not meet the constraints, the penalty value r is set. push , together with the immediate reward, serves as the final reward function of the energy hub:

[0184] R={F+r push} (38)

[0185] Among them, the park comprehensive energy system model is:

[0186]

[0187] Where: L e , L h are the electrical load and thermal load within the energy hub area, η is the equipment efficiency factor, υ is the allocation factor, subscripts e, g, h represent the types of electricity, gas, and heat energy, respectively, and the superscript represents the conversion device. new Represents photovoltaic or wind power;

[0188] Constraints on the park's integrated energy system include:

[0189]

[0190]

[0191]

[0192]

[0193]

[0194]

[0195]

[0196]

[0197]

[0198] In the formula, They are respectively the upper and lower limits of active power obtained from the regional integrated energy system, To obtain active power from the regional integrated energy system, They are respectively used to obtain the upper and lower limits of reactive power from the regional integrated energy system. To obtain reactive power from the regional integrated energy system, are the upper and lower limits of the power system branch power, is the power system branch power, are the upper and lower limits of the voltage of the power system network nodes, U i is the voltage of the power system network node, are the upper and lower limits of gas pressure at natural gas network nodes, π i is the gas network node pressure, They are the upper and lower limits of gas supply at the gas source point, is the gas supply volume at the gas source point, are the upper and lower limits of the natural gas system pipeline flow, is the pipeline flow rate of the natural gas system, They are the upper and lower limits of the heat supply of the heat source point in the centralized heating network. The heat supply for the heat source point of the central heating network, T i max 、T i min are the upper and lower limits of node temperature in the central heating network, T i is the node temperature in the district heating network;

[0199] The objective function of the park's comprehensive energy system is to optimize the economic efficiency of each energy hub's region. The cost of each region is set as the cost of the energy hub's energy interaction with the power system, thermal system, and natural gas system, respectively, calculated as follows:

[0200] F=min(c e P e +c g P g +c h P h )

[0201] Where: c e 、c h 、c g are the cost coefficients of energy interaction between the energy hub and the power system, thermal system and natural gas system respectively.

[0202] In the specific implementation, it also includes the step of sending the obtained control strategies of the equipment in each park comprehensive energy system to each equipment in the district comprehensive energy system for execution; the control strategies of the equipment include the output of the energy unit, the playback of the energy storage device and the conversion power of the coupling device.

[0203] In the specific implementation, in the step of calling the pre-established evolutionary game model based on the control strategy of the equipment in each park integrated energy system in step S2 to obtain the purchase electricity price, retail electricity price of the regional integrated energy system, and the electricity transaction volume and transaction price between the integrated energy systems of each park, the evolutionary game model is:

[0204]

[0205]

[0206] In the formula, I DSO Net profit for the regional integrated energy system; are the buying wholesale price and selling wholesale price of the energy market in period t, are the retail buying price and retail selling price set by the regional integrated energy system in period t, denoted as P t DSO,s , P t DSO,b are the wholesale power sold and the wholesale power bought in the energy market during period t; P ex,t , P im,t is the retail buying power and retail selling power of the regional comprehensive energy system during period t; Ω DSO is the set of constraints on electricity prices.

[0207] In the specific implementation, the step of calling the pre-established evolutionary game model in step S2 to obtain the purchase electricity price, retail electricity price of the regional comprehensive energy system, and the electricity transaction volume and transaction price between the comprehensive energy systems of each park, specifically: calling the pre-established evolutionary game model, taking the regional comprehensive energy system and the comprehensive energy systems of each park as the two parties of the game, the regional comprehensive energy system uses the purchase and sale electricity price as the decision variable, the comprehensive energy system of each park uses the purchase and sale electricity and the output of each equipment as the decision variable, and the regional comprehensive energy system uses the net profit I of the regional comprehensive energy system as the decision variable. DSO As the profit function, the park integrated energy system minimizes the operating cost C RIES The revenue function is solved to obtain the purchase electricity price, retail electricity price of the regional integrated energy system, and the electricity transaction volume and transaction price between the integrated energy systems of each park.

[0208] The present invention proposes an energy trading architecture with three levels: energy market, energy operator, and energy microgrid, and divides the operation optimization problem of regional integrated energy system into two stages: park autonomous operation and regional collaborative optimization. This system mainly includes 3 layers and 5 modules: the equipment layer includes 2 modules of data acquisition and control instruction issuance; the platform layer is an energy trading sharing platform; the algorithm layer includes 2 modules of autonomous operation and collaborative optimization. The present invention proposes an autonomous operation algorithm model of park integrated energy system based on multi-agent reinforcement learning, including its state space, action space, interaction process and reward function design. The multi-agent game architecture of integrated energy system under the assumption of limited rationality proposed by the present invention includes participants, strategy sets, and payment functions. A distributed autonomy and collaborative optimization method and system of regional integrated energy system proposed by the present invention utilizes integrated energy system to achieve multi-energy complementarity and mutual assistance to improve the overall energy efficiency and energy supply reliability of regional integrated energy system.

[0209] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0210] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0211] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0212] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0213] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for distributed autonomy and collaborative optimization of a multi-regional integrated energy system, characterized in that: include: Collect dynamic and static data from the integrated energy system of each park, input the pre-established autonomous operation model of the integrated energy system of each park based on multi-agent reinforcement learning, and obtain the control strategy of the equipment in the integrated energy system of each park; Based on the control strategies of the equipment in the integrated energy systems of each park, the pre-established evolutionary game model is called to obtain the purchase electricity price, retail electricity price of the regional integrated energy system, and the electricity transaction volume and transaction price between the integrated energy systems of each park; In the step of calling a pre-established evolutionary game model based on the control strategy of the equipment in each park integrated energy system to obtain the purchase electricity price, retail electricity price of the regional integrated energy system, and the electricity transaction volume and transaction price between the integrated energy systems of each park, the evolutionary game model is: In the formula, I DSO Net profit for the regional integrated energy system; are the buying wholesale price and selling wholesale price of the energy market in period t, are the retail buying price and retail selling price set by the regional integrated energy system in period t, denoted as P t DSO,s , P t DSO,b are the wholesale power sold and the wholesale power bought in the energy market during period t; P ex,t , P im,t is the retail buying power and retail selling power of the regional comprehensive energy system during period t; Ω DSO is the set of constraints on electricity prices.

2. A method for distributed autonomy and collaborative optimization of a multi-regional integrated energy system according to claim 1, characterized in that: In the step of collecting dynamic data and static data in each park integrated energy system, the dynamic data includes electricity data, gas data and heat data; the static data includes parameters of each device in the park integrated energy system, network topology and external parameters of the park integrated energy system.

3. A method for distributed autonomy and collaborative optimization of a multi-regional integrated energy system according to claim 1, characterized in that: In the step of inputting the autonomous operation model of the park integrated energy system based on multi-agent reinforcement learning pre-established by each park integrated energy system to obtain the control strategy of the equipment in each park integrated energy system, the state space, action space, interaction process and reward function of the autonomous operation model of the park integrated energy system based on multi-agent reinforcement learning are specifically: State Space: The state space S includes the wind power output P within the energy hub area. pv , Photovoltaic output P so , electrical load L e , heat load L h 、Electricity price e Gas price g 、Hot price h 、Power system node voltage U E 、Gas system node pressure π G 、Thermodynamic system node temperature T H ; S={P pv ,P so ,L e ,L h ,c e ,c g ,c h ,U E ,π G ,T H } (3) Action Space: The variables in the action space A include the power of the energy hub interacting with the electric power system, thermal system, and natural gas system respectively: A={P e ,P h ,P g } (4) Interaction process: The park integrated energy system model is used as the environment. After each energy hub takes action at each moment, a comprehensive energy system flow calculation is performed, and the relevant state quantities of the power system, thermal system, and natural gas system nodes are fed back to calculate the reward function and transferred to the next moment. Reward function: The opposite of the objective function of the park integrated energy system model is used as the instant reward of each energy hub. According to the constraints described in formula (5), if the corresponding variable does not meet the constraints, the penalty value r is set. pus h , together with the immediate reward, serves as the final reward function of the energy hub: R={F+r push } (5) Among them, the park comprehensive energy system model is: Where: L e , L h are the electrical load and thermal load within the energy hub area, η is the equipment efficiency factor, υ is the allocation factor, subscripts e, g, h represent the types of electricity, gas, and heat energy, respectively, and the superscript represents the conversion device. new Represents photovoltaic or wind power; Constraints on the integrated energy system of the park include: In the formula, They are respectively the upper and lower limits of active power obtained from the regional integrated energy system, To obtain active power from the regional integrated energy system, They are respectively used to obtain the upper and lower limits of reactive power from the regional integrated energy system. To obtain reactive power from the regional integrated energy system, are the upper and lower limits of the power system branch power, is the power system branch power, are the upper and lower limits of the voltage of the power system network nodes, U i is the power system network node voltage, are the upper and lower limits of gas pressure at natural gas network nodes, π i is the gas network node pressure, They are the upper and lower limits of gas supply at the gas source point, is the gas supply volume at the gas source point, are the upper and lower limits of the natural gas system pipeline flow, is the pipeline flow rate of the natural gas system, They are the upper and lower limits of the heat supply of the heat source point in the centralized heating network. Provide heat to the heat source points of the central heating network. are the upper and lower limits of node temperature in the central heating network, T i is the node temperature in the district heating network; The objective function of the park's integrated energy system is: F=min(c e P e +c g P g +c h P h ) Where: c e 、c h 、c g are the cost coefficients of energy interaction between the energy hub and the power system, thermal system and natural gas system respectively.

4. A method for distributed autonomy and collaborative optimization of a multi-regional integrated energy system according to claim 1, characterized in that: It also includes the step of sending the obtained control strategies of the equipment in each park comprehensive energy system to each equipment in the district comprehensive energy system for execution; the control strategies of the equipment include the output of the energy unit, the playback of the energy storage device and the conversion power of the coupling device.

5. A method for distributed autonomy and collaborative optimization of a multi-regional integrated energy system according to claim 1, characterized in that: In the step of calling the pre-established evolutionary game model to obtain the purchase electricity price, retail electricity price of the regional integrated energy system, and the electricity transaction volume and transaction price between the integrated energy systems of each park, specifically: The pre-established evolutionary game model is called, with the regional integrated energy system and the integrated energy systems of each park as the two parties of the game. The regional integrated energy system uses the purchase and sale price of electricity as the decision variable, and the integrated energy system of each park uses the purchase and sale of electricity and the output of each equipment as the decision variable. The regional integrated energy system uses the net profit of the regional integrated energy system I DSO As the profit function, the park integrated energy system minimizes the operating cost C RIES The revenue function is solved to obtain the purchase electricity price, retail electricity price of the regional integrated energy system, and the electricity transaction volume and transaction price between the integrated energy systems of each park.

6. A multi-region integrated energy system distributed autonomy and collaborative optimization system, characterized in that: include: Data collection module, used to collect dynamic and static data from the integrated energy system of each park; The autonomous operation module is used to input the collected dynamic data and static data of each park integrated energy system into the autonomous operation model of the park integrated energy system based on multi-agent reinforcement learning pre-established by each park integrated energy system, and obtain the control strategy of the equipment in each park integrated energy system; The collaborative optimization module is used to call the pre-established evolutionary game model based on the control strategy of the equipment in the integrated energy system of each park, obtain the purchase price and retail price of the regional integrated energy system, and the electricity transaction volume and transaction price between the integrated energy systems of each park; In the collaborative optimization module, the evolutionary game model is: In the formula, I DSO Net profit for the regional integrated energy system; are the buying wholesale price and selling wholesale price of the energy market in period t, are the retail buying price and retail selling price set by the regional integrated energy system in period t, denoted as P t DSO,s , P t DSO,b are the wholesale power sold and the wholesale power bought in the energy market during period t; P ex,t , P im,t is the retail buying power and retail selling power of the regional comprehensive energy system during period t; Ω DSO is the set of constraints on electricity prices.

7. A multi-regional integrated energy system distributed autonomy and collaborative optimization system according to claim 6, characterized in that: In the data acquisition module, the dynamic data includes electricity data, gas data and thermal data; the static data includes parameters of each device in the park comprehensive energy system, network topology and external parameters of the park comprehensive energy system.

8. A multi-regional integrated energy system distributed autonomy and collaborative optimization system according to claim 6, characterized in that: In the autonomous operation module, the state space, action space, interaction process and reward function of the autonomous operation model of the park integrated energy system based on multi-agent reinforcement learning are specifically as follows: State Space: The state space S includes the wind power output P within the energy hub area. pv , Photovoltaic output P so , electrical load L e , heat load L h 、Electricity price e Gas price g 、Hot price h 、Power system node voltage U E 、Gas system node pressure π G 、Thermodynamic system node temperature T H ; S={P pv ,P so ,L e ,L h ,c e ,c g ,c h ,U E ,π G ,T H } (10) Action Space: The variables in the action space A include the power of the energy hub interacting with the electric power system, thermal system, and natural gas system respectively: A={P e ,P h ,P g } (11) Interaction process: The park integrated energy system model is used as the environment. After each energy hub takes action at each moment, a comprehensive energy system flow calculation is performed, and the relevant state quantities of the power system, thermal system, and natural gas system nodes are fed back to calculate the reward function and transferred to the next moment. Reward function: The opposite of the objective function of the park integrated energy system model is used as the instant reward of each energy hub. According to the constraints described in formula (5), if the corresponding variable does not meet the constraints, the penalty value r is set. pus h , together with the immediate reward, serves as the final reward function of the energy hub: R={F+r push } (12) Among them, the park comprehensive energy system model is: Where: L e , L h are the electrical load and thermal load within the energy hub area, η is the equipment efficiency factor, υ is the allocation factor, subscripts e, g, h represent the types of electricity, gas, and heat energy, respectively, and the superscript represents the conversion device. new Represents photovoltaic or wind power; Constraints on the integrated energy system of the park include: In the formula, They are respectively the upper and lower limits of active power obtained from the regional integrated energy system, To obtain active power from the regional integrated energy system, They are respectively used to obtain the upper and lower limits of reactive power from the regional integrated energy system. To obtain reactive power from the regional integrated energy system, are the upper and lower limits of the power system branch power, is the power system branch power, are the upper and lower limits of the voltage of the power system network nodes, U i is the voltage of the power system network node, are the upper and lower limits of gas pressure at natural gas network nodes, π i is the gas network node pressure, They are the upper and lower limits of gas supply at the gas source point, is the gas supply volume at the gas source point, are the upper and lower limits of the natural gas system pipeline flow, is the pipeline flow rate of the natural gas system, They are the upper and lower limits of the heat supply of the heat source point in the centralized heating network. Provide heat to the heat source points of the central heating network. are the upper and lower limits of node temperature in the central heating network, T i is the node temperature in the district heating network; The objective function of the park's integrated energy system is: F=min(c e P e +c g P g +c h P h ) Where: c e 、c h 、c g are the cost coefficients of energy interaction between the energy hub and the power system, thermal system and natural gas system respectively.

9. A multi-regional integrated energy system distributed autonomy and collaborative optimization system according to claim 6, characterized in that: Also includes: An instruction issuing module is used to issue the obtained control strategies of the equipment in each park integrated energy system to each equipment in the district integrated energy system for execution; The control strategy of the device includes the output of the energy unit, the playback of the energy storage device and the conversion power of the coupling device.

10. A multi-regional integrated energy system distributed autonomy and collaborative optimization system according to claim 6, characterized in that: The collaborative optimization module calls the pre-established evolutionary game model to obtain the purchase price and retail price of the regional integrated energy system, as well as the transaction volume and transaction price of electricity between the integrated energy systems of each park. The specific steps include: The pre-established evolutionary game model is called, with the regional integrated energy system and the integrated energy systems of each park as the two parties of the game. The regional integrated energy system uses the purchase and sale price of electricity as the decision variable, and the integrated energy system of each park uses the purchase and sale of electricity and the output of each equipment as the decision variable. The regional integrated energy system uses the net profit of the regional integrated energy system I DSO As the profit function, the park integrated energy system minimizes the operating cost C RIES The revenue function is solved to obtain the purchase electricity price, retail electricity price of the regional integrated energy system, and the electricity transaction volume and transaction price between the integrated energy systems of each park.

Images