Multi-temporal-spatial-scale optimization operation strategy of distributed integrated energy system

Abstract

The invention discloses a multi-temporal-spatial-scale optimization operation strategy of a distributed integrated energy system, and aims to solve the operation optimization problem of the distributed energy system in high volatility and complementarity. The method is specifically realized through the following technical scheme: firstly, constructing a multi-energy coupling model of the integrated energy system, and realizing refined modeling of equipment units and user side demand response; secondly, based on renewable energy source day-ahead prediction data, performing day-ahead scheduling by adopting an LSTM model, and constructing an energy supply and demand balance mechanism; renewable energy fluctuation is coped with through a real-time scheduling strategy, and real-time energy balance is guaranteed. In addition, comprehensive energy system long-time scale optimization considering equipment capacity planning is provided, and the overall cost of the system is reduced. And finally, solving the model by adopting a particle swarm optimization algorithm to realize joint optimization of long-term planning and real-time scheduling of the integrated energy system. The operation efficiency and economical efficiency of the distributed integrated energy system are effectively improved, and the method is suitable for integration and management of energy systems of various scales.

Description

Technical Field

[0001] The present invention relates to the technical field of distributed energy systems, and in particular to a multi-temporal and spatial scale optimization operation strategy for a distributed integrated energy system. Background Art

[0002] At present, distributed integrated energy systems are increasingly gaining widespread attention as a key means to improve energy efficiency and promote sustainable energy development. Technological innovation in this field not only covers traditional energy systems such as power systems and natural gas networks, but also gradually expands to hydrogen production and transportation, regional heating and cooling systems, electrified transportation, and related information and communication infrastructure.

[0003] The introduction of carbon emission targets and the rapid advancement of urbanization have brought unprecedented momentum for change to the energy system. These changes have not only introduced a large number of new components and network configurations, but also spawned new design concepts and operating models, as well as corresponding incentive mechanisms and business models. These changes have significantly increased the degree of coupling and interaction between different types of energy carriers such as electricity, natural gas, hydrogen, heating and cooling, and have put forward higher requirements for the optimized operation of the energy system.

[0004] In distributed integrated energy systems, multi-energy coupling units are the key link to achieve conversion and coordination between different energy forms. These units include but are not limited to (Combined Cooling Heating and Power, combined cooling, heating and power), (combined heat and power, cogeneration), (Gas turbine, gas turbine), (Electric boiler, electric boiler), (Gas boiler, gas boiler), etc. The efficient operation and coordinated scheduling of these equipment are crucial to improving the energy utilization efficiency and reliability of the entire system.

[0005] However, the existing distributed integrated energy system optimization operation strategies have the following shortcomings: first, there is a lack of refined modeling methods that comprehensively consider the complementary relationships of various energy forms; second, they fail to effectively deal with the impact of distributed renewable energy forecast deviations on the real-time scheduling of the system; third, there is a lack of optimization mechanisms that combine long-term equipment capacity planning with short-term scheduling strategies; fourth, the solution methods mostly use a single optimization algorithm, which makes it difficult to comprehensively balance multiple objectives of system operation.

[0006] Therefore, there is an urgent need for an optimized operation strategy that can comprehensively consider the multi-temporal and spatial scale characteristics of distributed integrated energy systems, and optimize the overall performance of the system through the combination of refined modeling, real-time scheduling, long-time scale optimization and efficient solution algorithms. This strategy will help improve the energy utilization efficiency of the system, reduce operating costs, and provide strong support for the widespread application of distributed integrated energy systems. Summary of the invention

[0007] The technical problem to be solved by the present invention is to provide a multi-temporal and spatial scale optimization operation strategy for a distributed integrated energy system to solve the multi-temporal and spatial scale operation optimization problem existing in the distributed integrated energy system in the prior art, especially in the context of the increasing complexity and diversification of energy systems, how to achieve efficient utilization of energy and balance supply and demand, while considering the uncertainty of renewable energy and the reasonable planning of equipment capacity.

[0008] In order to solve the above technical problems, the technical solution adopted by the present invention is a multi-temporal and spatial scale optimization operation strategy for a distributed integrated energy system, comprising: Step 1: Construction of multi-energy coupling model of integrated energy system; Step 2: Day-ahead dispatch strategy for integrated energy system based on day-ahead forecast data of distributed renewable energy; Step 3: Real-time dispatch strategy of integrated energy system considering prediction deviation of distributed renewable energy; Step 4: Long-term optimization of the integrated energy system considering equipment capacity planning; Step 5: Use particle swarm optimization algorithm to solve the proposed model.

[0009] In a preferred solution, the specific steps of constructing the multi-energy coupling model of the integrated energy system in step 1 include: Step 1.1: Analyze the energy demand in the area where the integrated energy system is located, determine the load type, including different forms of energy demand such as electricity, heat, cooling, and gas, and determine the equipment type; Step 1.2: Model the multi-energy coupling unit, which includes a combined cooling, heating and power system. , combined heat and power system ,gas turbine , Electric boiler , Gas boiler , and establish the corresponding mathematical model; Step 1.3: Build a user-side demand response model, including a demand response mechanism that can time-shift and reduce loads; Step 1.4: Source side With lotus side Conduct joint modeling to realize the modeling of distributed integrated energy systems.

[0010] In a preferred solution, the specific steps of the Step 1.2 for modeling the multi-energy coupling unit include: Step1.2.1: Modeling, establishing a mathematical model of the gas turbine; When working, the relationship between output power and natural gas consumption is as follows: (1) in, yes exist Natural gas consumption at the time, is the power generation, and is the gas-to-electricity conversion coefficient, is the number of hours in a day; The output power has output constraints and ramp constraints, as shown below: (2) in, , They are The minimum output power and maximum output power; is the maximum power change value; for exist Output power at the moment; Cost The calculation is as follows: (3) in, , They are the cost of purchasing natural gas and the operation and maintenance cost; Step1.2.2: Modeling, establishing the mathematical model of the electric boiler; Capable of recovering heat from the heat generated by the gas turbine. as follows: (4) in, for The efficiency of heat recovery, for The ratio of electricity generation to heat rejection, for Heat loss; at the same time The output heat is subject to the following constraints: (5) in, , They are Maximum output and maximum power change; Cost The calculation is as follows: (6) in, for The maintenance factor; Step1.2.3: Modeling, establishing the mathematical model of the gas boiler; In an integrated energy system, The model is a key part of heat supply, the following is Constraints: (7) in, , , , , They are Natural gas consumption, at time The output thermal power, the minimum value of the output thermal power, the maximum value of the output thermal power and the maximum change value of the thermal power; for The ratio coefficient between natural gas consumption and thermal power output; for exist Thermal power output at any time; The cost and Similarly, it is calculated as follows: (8) in, for The maintenance factor; Step1.2.4: and Modeling, establish mathematical models of air compressors and electric compressors; It is a device that can convert heat into cold energy. It can convert electrical power into gas power, and its output characteristics are as follows: (9) in, , They are The cooling power generated is Input thermal power, for Refrigeration heat consumption coefficient; , They are The cooling power generated and the electrical power consumed, for Refrigeration power consumption coefficient; and The output constraints are as follows: (10) in, for The maximum value of heat power that can be input; for The maximum value of the electrical power that can be input; and In terms of cost, there is only operation and maintenance cost, which is calculated as follows: (11) in , They are and maintenance costs, , for and The maintenance factor; Step 1.2.5: Electric energy storage , Thermal Energy Storage , Cold Energy Storage Modeling, establish the mathematical model of energy storage equipment, including its capacity, charging and discharging power, efficiency, etc.; , , The capacity of a battery has the following relationship with its own charging, discharging, heating and cooling power: (12) in, , , They are , , exist The remaining capacity at the moment, , , They are , , exist The remaining capacity at the moment, , , They are , , The charging and discharging power; For charging efficiency; , A binary variable for charging and discharging the energy storage. , is a binary variable for thermal energy storage charging and thermal energy storage discharging, , A binary variable for charging and discharging cold energy storage; is the time interval; at the same time , , There are the following constraints: (13) in, , , for , , is the maximum power of each charge and discharge; , , They are , , Minimum safe capacity; , , They are , , The maximum safe capacity of the binary variable of charging and discharging has the following constraints: (14) Energy storage has operation and maintenance costs, which are calculated as follows: (15) in, , , They are , , The energy storage maintenance factor.

[0011] In the preferred solution, the construction of the user-side demand response model in Step 1.3 includes: Step 1.3.1: Time-shiftable load constraints include constraints on electrical time-shifting loads, thermal time-shifting loads, and cold time-shifting loads. The constraints are as follows: (16) in, , , Respectively in The electrical time-shifting load, heat time-shifting load and cooling time-shifting load at each moment; , , are the maximum values ​​of the time-shifted loads of electricity, heat, and cold respectively; the time-shiftable load must satisfy the requirement that the sum of the load transferred in and out during a day is 0, and there is a maximum value constraint on the load that can be transferred in each period; Step 1.3.2: Constraints on the reducible loads, including the reducible loads of electricity, heat, and cooling and their maximum values. The constraints are as follows: (17) in, , , They are the curtailable loads of electricity, heat and cooling respectively; , , They are the maximum loads that can be reduced for electricity, heating and cooling respectively.

[0012] In a preferred solution, the step 2 of the integrated energy system day-ahead scheduling strategy based on the distributed renewable energy day-ahead forecast data includes: Step 2.1: Input the renewable energy power data of the day before, and predict the renewable energy power through data collection and preprocessing, feature engineering, model selection and model deployment; Step 2.2: Construct an energy supply and demand balance mechanism for the integrated energy system to ensure the day-ahead power balance of the integrated energy system.

[0013] In the preferred solution, the step 2.2 constructs the energy supply and demand balance mechanism of the integrated energy system based on the renewable energy day-ahead forecast results, and the mechanism is as follows: (18) in, , , They are user electrical load, user heat load and user cooling load. The electrical load includes the electrical energy consumed by electric refrigeration, and the heat load includes the heat energy consumed by the absorption chiller. , They are photovoltaic power and wind turbine power respectively; Power interaction between integrated energy systems and power grids; There are interactive upper and lower power constraints: (19) Maximum power interaction between the integrated energy system and the grid; In addition, the day-ahead dispatch strategy has the following energy storage safety margin constraints: (20) The energy storage safety margin constraint can ensure that when there is a fluctuation in the power of renewable energy in the real-time scheduling link, the energy storage charging and discharging power can achieve the energy supply and demand balance in real-time scheduling; The energy objective function of the designed integrated energy system is the sum of all equipment costs, as shown in the following formula: (20) in, The cost of buying and selling electricity to the grid is calculated as follows: (twenty one) in, The unit price for purchasing and selling electricity; This achieves day-ahead power balance in the integrated energy system.

[0014] In the preferred solution, the real-time dispatch strategy of the integrated energy system taking into account the prediction deviation of distributed renewable energy in step 3 includes: Step 3.1: Based on the output of various equipments planned by the day-ahead dispatch strategy and the real-time fluctuation of renewable energy, a real-time energy supply and demand balance mechanism is set: (twenty two) in, , It is the grid interaction power and energy storage charging and discharging power in the real-time dispatching link; Step 3.2: The objective function of real-time scheduling only considers electric energy storage The loss is calculated as follows: (twenty three).

[0015] In the preferred solution, the long-term optimization of the integrated energy system considering equipment capacity planning in Step 4 includes: Step 4.1: Define the decision variables of the long-term equipment capacity of the integrated energy system as the capacity of electric energy storage, thermal energy storage, and cold energy storage, and set the constraints as follows: (twenty four) in, , , They are the capacities of electrical energy storage, thermal energy storage, and cold energy storage equipment respectively; , , , , , They are the lower limit of electric energy storage capacity configuration, the lower limit of thermal energy storage capacity configuration, the lower limit of cold energy storage capacity configuration, the upper limit of electric energy storage capacity configuration, the upper limit of thermal energy storage capacity configuration, and the upper limit of cold energy storage capacity configuration; Step 4.2: Considering the investment in energy storage equipment and the day-ahead dispatching cost, set the objective function for the long-term planning of the integrated energy system: (25) in, , , They are the daily investment cost of electric energy storage, the daily investment cost of thermal energy storage, and the daily investment cost of cold energy storage. is the day-ahead scheduling cost.

[0016] In a preferred solution, the Step 5 uses a particle swarm optimization algorithm to solve the proposed model, including: Step 5.1: Joint optimization of long-term planning and day-ahead scheduling of the integrated energy system. The decision variables are defined as the capacity of the energy storage equipment and the output of various functional equipment. The constraints are consistent with the constraints of the day-ahead scheduling of the long-term plan, and the objective function is consistent with the objective function of the long-term plan. Step 5.2: Based on the optimized energy storage capacity and the output configuration of each device, real-time optimization scheduling is performed. Specifically, the objective function and constraints of Step 4 are used for optimization. In this stage, the decision variables are , ; Step 5.3: Based on the above objective function, constraints and decision variables, particle swarm optimization algorithm is used for optimization.

[0017] In the preferred solution, the specific steps of optimizing using the particle swarm optimization algorithm in Step 5.3 are as follows: Step 5.3.1: Definition of population size and number of iterations Step 5.3.2: Population initialization, use the following formula to initialize the population: (26) in, For the The decision variables of individuals in the initialization stage, is a random number between 0 and 1. is the upper bound of the decision variable, is the lower bound of the decision variable; Step 5.3.3: Enter the iteration phase and first calculate the objective function of each individual in the population; Step 5.3.4: Based on the objective function, select the global optimal individual and the historical optimal value of each individual. Step 5.3.5: Update the speed using the following formula: (27) in, For individuals In the The speed of iterations, is the inertia weight, is the optimal weight of the individual, is the global optimal weight; , are the historical optimal value of each individual and the global optimal individual; For the Individuals in The decision variables at the moment; Step 5.3.6: After updating the speed, determine whether the speed exceeds the upper and lower limits of the speed limit. If the speed exceeds the upper limit, set the speed to the upper limit; if it is lower than the lower limit, set it to the lower limit. Use the following formula to update the position: (28) in, For the Individuals in The decision variables at the moment; Determine whether the position exceeds the limit range and correct the position in a similar way to the speed correction method; Step 5.3.7: After the iteration is completed, the optimal decision variables are output to obtain the output configuration data of the energy storage equipment capacity and various types of equipment in the integrated energy system, thereby realizing the multi-time scale optimization of the integrated energy system.

[0018] Furthermore, the energy storage safety margin constraint of the day-ahead scheduling strategy is used to ensure that when renewable energy power fluctuations occur in the real-time scheduling link, the energy supply and demand balance of real-time scheduling is achieved through the energy storage charging and discharging power.

[0019] Furthermore, the objective function of real-time scheduling only considers the loss of the electric energy storage ES, and its calculation method is based on the charging and discharging efficiency and actual charging and discharging power of the electric energy storage.

[0020] Furthermore, the objective function of long-time-scale optimization comprehensively considers the investment in energy storage equipment and the day-ahead dispatching cost to achieve economically optimized operation of the integrated energy system.

[0021] The multi-temporal and spatial scale optimization operation strategy of a distributed integrated energy system provided by the present invention has the following beneficial effects: 1. The present invention solves the multi-time and space scale operation optimization problem existing in the prior art distributed integrated energy system, especially how to achieve efficient energy utilization and supply and demand balance under the background of increasingly complex and diversified energy systems, while considering the uncertainty of renewable energy and the reasonable planning of equipment capacity; 2. The present invention improves the accuracy and adaptability of the system model and the matching ability of the system to energy supply and demand by modeling the multi-energy coupling unit and the user-side demand response in detail; 3. The present invention combines day-ahead scheduling, real-time scheduling and long-time scale optimization to achieve coordinated optimization of energy systems on different time scales; 4. The present invention takes energy storage safety margin into consideration and introduces energy storage safety margin constraints into the day-ahead dispatching strategy, thereby enhancing the system's ability to cope with renewable energy power fluctuations; 5. The present invention reduces system operating costs, improves energy efficiency, and improves system operation reliability and economy through multi-time and space scale optimization; 6. The present invention enables the system to better cope with different energy demands and renewable energy power fluctuations through multi-energy coupling and user-side demand response, thereby enhancing the flexibility and adaptability of the system; 7. The optimized operation strategy proposed in the present invention provides a feasible solution for the intelligent management of distributed integrated energy systems; 8. The user-side demand response modeling construction of the present invention includes a demand response mechanism that can shift and reduce loads in time, and deeply explores the adjustable potential of user-side flexible loads. This user-side refined modeling method improves the flexibility and response speed of the system and demonstrates technical novelty; 9. The LSTM model of the present invention is used for renewable energy prediction. The Long Short-Term Memory Network (LSTM) model is used to predict the power of distributed renewable energy, which improves the accuracy and reliability of the prediction and provides more accurate data support for the day-ahead scheduling of the system. This is also a new highlight in the application of technology. 10. The application of the particle swarm optimization algorithm of the present invention, when solving the optimization model, introduces the particle swarm optimization algorithm, realizes the effective solution of complex optimization problems, and the application of this algorithm in the optimization of distributed integrated energy systems is also innovative; by dynamically adjusting the particle speed and position, the algorithm can quickly converge to the global optimal solution, significantly improve the operating efficiency and resource utilization of the energy system, and provide strong support for the realization of green and sustainable development; 11. The present invention studies the optimized operation strategy of the distributed integrated energy system and constructs a refined model of the integrated energy system, thereby realizing the precise characterization of the energy supply and flow mode of the integrated energy system; it proposes optimization schemes for the integrated energy system at different time scales, and provides distributed integrated energy system operators with optimization strategies at different time scales, thereby effectively reducing the system operation cost, facilitating the complementarity of various energy sources, and effectively improving the energy utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The present invention will be further described below in conjunction with the accompanying drawings and implementation examples: Figure 1 This is a schematic diagram of electric energy dispatching in Example 2 of the present invention; Figure 2 This is a schematic diagram of thermal energy scheduling in Example 2 of the present invention; Figure 3 This is a schematic diagram of cold energy scheduling in Example 2 of the present invention; Figure 4 This is a schematic diagram of real-time power scheduling in Example 2 of the present invention; Figure 5 This is the long time scale optimization iteration curve of Example 2 of the present invention; Figure 6 It is the real-time scheduling optimization iteration curve of embodiment 2 of the present invention; Figure 7 The particle swarm algorithm flow chart of the present invention. DETAILED DESCRIPTION

[0023] The technical solution of the present invention is further described below in conjunction with the embodiments and drawings: Example 1 like Figure 7 As shown in FIG. 1 , a multi-temporal and spatial scale optimization operation strategy for a distributed integrated energy system includes: Step 1: Construction of multi-energy coupling model of integrated energy system; Step 2: Day-ahead dispatch strategy for integrated energy system based on day-ahead forecast data of distributed renewable energy; Step 3: Real-time dispatch strategy of integrated energy system considering prediction deviation of distributed renewable energy; Step 4: Long-term optimization of the integrated energy system considering equipment capacity planning; Step 5: Use particle swarm optimization algorithm to solve the proposed model.

[0024] In this embodiment, the specific steps of constructing the multi-energy coupling model of the integrated energy system in step 1 include: Step 1.1: Analyze the energy demand in the area where the integrated energy system is located, determine the load type, including different forms of energy demand such as electricity, heat, cooling, and gas, and determine the equipment type; Step 1.2: Model the multi-energy coupling unit, which includes a combined cooling, heating and power system. , combined heat and power system ,gas turbine , Electric boiler , Gas boiler , and establish the corresponding mathematical model; Step 1.3: Build a user-side demand response model, including a demand response mechanism that can time-shift and reduce loads; Step 1.4: Source side (Absorption Chillers, absorption refrigeration machine) and load side (Electric Cooling) is jointly modeled to achieve the modeling of distributed integrated energy systems.

[0025] Furthermore, the specific steps of modeling the multi-energy coupling unit in Step 1.2 include: Step1.2.1: Modeling, establishing a mathematical model of the gas turbine; When working, the relationship between output power and natural gas consumption is as follows: (1) in, yes exist Natural gas consumption at the time, is the power generation, and is the gas-to-electricity conversion coefficient, is the number of hours in a day; The output power has output constraints and ramp constraints, as shown below: (2) in, , They are The minimum output power and maximum output power; is the maximum power change value; for exist Output power at the moment; Cost The calculation is as follows: (3) in, , They are the cost of purchasing natural gas and the operation and maintenance cost; Step1.2.2: Modeling, establishing the mathematical model of the electric boiler; Capable of recovering heat from the heat generated by the gas turbine. as follows: (4) in, for The efficiency of heat recovery, for The ratio of electricity generation to heat rejection, for Heat loss; at the same time The output heat is subject to the following constraints: (5) in, , They are Maximum output and maximum power change; Cost The calculation is as follows: (6) in, for The maintenance factor; Step1.2.3: Modeling, establishing the mathematical model of the gas boiler; In an integrated energy system, The model is a key part of heat supply, the following is Constraints: (7) in, , , , , They are Natural gas consumption, at time The output thermal power, the minimum value of the output thermal power, the maximum value of the output thermal power and the maximum change value of the thermal power; for The ratio coefficient between natural gas consumption and thermal power output; for exist Thermal power output at any time; The cost and Similarly, it is calculated as follows: (8) in, for The maintenance factor; Step1.2.4: and Modeling, establish mathematical models of air compressors and electric compressors; It is a device that can convert heat into cold energy. It can convert electrical power into gas power, and its output characteristics are as follows: (9) in, , They are The cooling power generated is Input thermal power, for Refrigeration heat consumption coefficient; , They are The cooling power generated and the electrical power consumed, for Refrigeration power consumption coefficient; and The output constraints are as follows: (10) in, for The maximum value of heat power that can be input; for The maximum value of the electrical power that can be input; and In terms of cost, there is only operation and maintenance cost, which is calculated as follows: (11) in , They are and maintenance costs, , for and The maintenance factor; Step1.2.5: Furthermore, the construction of the user-side demand response model in Step 1.3 includes: Step 1.3.1: Time-shiftable load constraints include constraints on electrical time-shifting loads, thermal time-shifting loads, and cold time-shifting loads. The constraints are as follows: (16) in, , , Respectively in The electrical time-shifting load, heat time-shifting load and cooling time-shifting load at each moment; , , are the maximum values ​​of the time-shifted loads of electricity, heat, and cold respectively; the time-shiftable load must satisfy the requirement that the sum of the load transferred in and out during a day is 0, and there is a maximum value constraint on the load that can be transferred in each period; Step 1.3.2: Constraints on the reducible loads, including the reducible loads of electricity, heat, and cooling and their maximum values. The constraints are as follows: (17) in, , , They are the curtailable loads of electricity, heat and cooling respectively; , , They are the maximum loads that can be reduced for electricity, heating and cooling respectively.

[0026] Furthermore, the step 2, based on the distributed renewable energy day-ahead forecast data, the day-ahead dispatch strategy of the integrated energy system includes: Step 2.1: Input the renewable energy power data of the day before, and predict the renewable energy power through data collection and preprocessing, feature engineering, model selection and model deployment; Step 2.2: Construct an energy supply and demand balance mechanism for the integrated energy system to ensure the day-ahead power balance of the integrated energy system.

[0027] Furthermore, the energy supply and demand balance mechanism of the integrated energy system constructed in step 2.2 is based on the day-ahead forecast results of renewable energy, and its mechanism is as follows: (18) in, , , They are user electrical load, user heat load and user cooling load. The electrical load includes the electrical energy consumed by electric refrigeration, and the heat load includes the heat energy consumed by the absorption chiller. , They are photovoltaic power and wind turbine power respectively; Power interaction between integrated energy systems and power grids; There are interactive upper and lower power constraints: (19) Maximum power interaction between the integrated energy system and the grid; In addition, the day-ahead dispatch strategy has the following energy storage safety margin constraints: (20) The energy storage safety margin constraint can ensure that when there is a fluctuation in the power of renewable energy in the real-time scheduling link, the energy storage charging and discharging power can achieve the energy supply and demand balance in real-time scheduling; The energy objective function of the designed integrated energy system is the sum of all equipment costs, as shown in the following formula: (20) in, The cost of buying and selling electricity to the grid is calculated as follows: (twenty one) in, The unit price for purchasing and selling electricity; This achieves day-ahead power balance in the integrated energy system.

[0028] Furthermore, the real-time dispatch strategy of the integrated energy system taking into account the prediction deviation of distributed renewable energy in step 3 includes: Step 3.1: Based on the output of various equipments planned by the day-ahead dispatch strategy and the real-time fluctuation of renewable energy, a real-time energy supply and demand balance mechanism is set: (twenty two) in, , It is the grid interaction power and energy storage charging and discharging power in the real-time dispatching link; Step 3.2: The objective function of real-time scheduling only considers electric energy storage The loss is calculated as follows: (twenty three).

[0029] Furthermore, the long-term optimization of the integrated energy system considering equipment capacity planning in Step 4 includes: Step 4.1: Define the decision variables of the long-term equipment capacity of the integrated energy system as the capacity of electric energy storage, thermal energy storage, and cold energy storage, and set the constraints as follows: (twenty four) in, , , They are the capacities of electrical energy storage, thermal energy storage, and cold energy storage equipment respectively; , , , , , They are the lower limit of electric energy storage capacity configuration, the lower limit of thermal energy storage capacity configuration, the lower limit of cold energy storage capacity configuration, the upper limit of electric energy storage capacity configuration, the upper limit of thermal energy storage capacity configuration, and the upper limit of cold energy storage capacity configuration; Step 4.2: Considering the investment in energy storage equipment and the day-ahead dispatching cost, set the objective function for the long-term planning of the integrated energy system: (25) in, , , They are the daily investment cost of electric energy storage, the daily investment cost of thermal energy storage, and the daily investment cost of cold energy storage. is the day-ahead scheduling cost.

[0030] Furthermore, the Step 5 uses a particle swarm optimization algorithm to solve the proposed model, including: Step 5.1: Joint optimization of long-term planning and day-ahead scheduling of the integrated energy system. The decision variables are defined as the capacity of the energy storage equipment and the output of various functional equipment. The constraints are consistent with the constraints of the day-ahead scheduling of the long-term plan, and the objective function is consistent with the objective function of the long-term plan. Step 5.2: Based on the optimized energy storage capacity and the output configuration of each device, real-time optimization scheduling is performed. Specifically, the objective function and constraints of Step 4 are used for optimization. In this stage, the decision variables are , ; Step 5.3: Based on the above objective function, constraints and decision variables, particle swarm optimization algorithm is used for optimization.

[0031] Furthermore, the specific steps of optimizing Step 5.3 using the particle swarm optimization algorithm are as follows: Step 5.3.1: Definition of population size and number of iterations Step 5.3.2: Population initialization, use the following formula to initialize the population: (26) in, For the The decision variables of individuals in the initialization stage, is a random number between 0 and 1. is the upper bound of the decision variable, is the lower bound of the decision variable; Step 5.3.3: Enter the iteration phase and first calculate the objective function of each individual in the population; Step 5.3.4: Based on the objective function, select the global optimal individual and the historical optimal value of each individual; Step 5.3.5: Update the speed using the following formula: (27) in, For individuals In the The speed of iterations, is the inertia weight, is the optimal weight of the individual, is the global optimal weight; , are the historical optimal value of each individual and the global optimal individual; For the Individuals in The decision variables at the moment; Step 5.3.6: After updating the speed, determine whether the speed exceeds the upper and lower limits of the speed limit. If the speed exceeds the upper limit, set the speed to the upper limit; if it is lower than the lower limit, set it to the lower limit. Use the following formula to update the position: (28) in, For the Individuals in The decision variables at the moment; Determine whether the position exceeds the limit range and correct the position in a similar way to the speed correction method; Step 5.3.7: After the iteration is completed, the optimal decision variables are output to obtain the output configuration data of the energy storage equipment capacity and various types of equipment in the integrated energy system, thereby realizing the multi-time scale optimization of the integrated energy system.

[0032] Example 2 In another preferred embodiment, based on the above embodiment 1, Figures 1 to 7 As shown, the technical solution and implementation methods of the present invention are described in detail using data from an industrial park in Shandong.

[0033] S01: System Modeling: S01.1: Energy analysis and planning: Construct energy needs in different forms including electricity, heat, cooling, gas, etc. and determine the equipment types for the integrated energy system.

[0034] S01.2: Modeling of multi-energy coupling units: The construction includes: gas turbine (GT), waste heat recovery boiler (WHB), gas boiler (GB), absorption chiller (AC), photovoltaic (PV), fan (WT), electric air conditioner (EC), electric energy storage (ES), thermal energy storage (TS), cold energy storage (CS); among them, gas turbine, waste heat recovery boiler, absorption chiller are combined cooling, heating and power (CCHP) system. At the same time, the energy input and output relationship of various equipment, the constraints of equipment operating conditions, as well as energy conversion efficiency and coupling coefficient are negotiated, so as to realize the refined modeling of the energy supply side of the comprehensive energy system.

[0035] (1) Modeling When working, the relationship between output power and natural gas consumption is as follows: (1) in, yes At the moment Natural gas consumption, is the power generation, and is the gas-to-electricity conversion coefficient, is the number of hours in a day; The output power has output constraints and ramp constraints, as shown below: (2) in, , They are The minimum output power and maximum output power; is the maximum power change value; for exist Output power at the moment; Cost The calculation is as follows: (3) in, , They are the cost of purchasing natural gas and the operation and maintenance cost respectively.

[0036] (2) Modeling Capable of recovering heat from the heat generated by the gas turbine. as follows: (4) in, for The efficiency of heat recovery, for The ratio of electricity generation to heat rejection, for Heat loss; at the same time The output heat is subject to the following constraints: (5) in, , They are Maximum output and maximum power change; Cost The calculation is as follows: (6) in, for The maintenance factor.

[0037] (3) Modeling In an integrated energy system, The model is a key part of heat supply, the following is Constraints: (7) in, , , , , They are Natural gas consumption, at time The output thermal power, the minimum value of the output thermal power, the maximum value of the output thermal power and the maximum change value of the thermal power; for The ratio coefficient between natural gas consumption and thermal power output; for exist Thermal power output at any time; The cost and Similarly, it is calculated as follows: (8) in, for The maintenance factor.

[0038] (4) and Modeling It is a device that can convert heat into cold energy. It can convert electrical power into gas power, and its output characteristics are as follows: (9) in, , They are The cooling power generated is Input thermal power, for Refrigeration heat consumption coefficient; , They are The cooling power generated and the electrical power consumed, for Refrigeration power consumption coefficient; and The output constraints are as follows: (10) in, for The maximum value of heat power that can be input; for The maximum value of the electrical power that can be input; and In terms of cost, there is only operation and maintenance cost, which is calculated as follows: (11) in , They are and maintenance costs, , for and The maintenance factor.

[0039] (5) Electric energy storage , Thermal Energy Storage , Cold Energy Storage Modeling , , The capacity of a battery has the following relationship with its own charging, discharging, heating and cooling power: (12) in, , , They are , , exist The remaining capacity at the moment, , , They are , , exist The remaining capacity at the moment, , , They are , , The charging and discharging power; For charging efficiency; , A binary variable for charging and discharging the energy storage. , is a binary variable for thermal energy storage charging and thermal energy storage discharging, , A binary variable for charging and discharging cold energy storage; is the time interval; at the same time , , There are the following constraints: (13) in, , , for , , is the maximum power of each charge and discharge; , , They are , , Minimum safe capacity; , , They are , , The maximum safe capacity of the binary variable of charging and discharging has the following constraints: (14) Energy storage has operation and maintenance costs, which are calculated as follows: (15) in, , , They are , , The energy storage maintenance factor.

[0040] S01.3: User-side demand response modeling: In order to fully tap the adjustable potential of flexible loads on the user side, a demand response mechanism including time-shiftable and time-reducible loads is constructed, thereby realizing refined modeling of the user side of the integrated energy system. The time-shiftable load constraints have the following constraints: (16) in, , , are the electric time-shifted load, thermal time-shifted load and cooling time-shifted load at time t respectively; , , are the maximum values ​​of the time-shifted loads of electricity, heat, and cold respectively; the time-shiftable load must satisfy the requirement that the sum of the load transferred in and out during a day is 0, and there is a maximum value constraint on the load that can be transferred in each period; Step 1.3.2: The load reduction constraints are as follows: (17) in, , , They are the curtailable loads of electricity, heat and cooling respectively; , , They are the maximum loads that can be reduced for electricity, heating and cooling respectively.

[0041] S01.4: Jointly model the source side and the load side to realize the modeling of distributed integrated energy systems.

[0042] S02: The steps of the day-ahead dispatch strategy of the integrated energy system based on the day-ahead forecast data of distributed renewable energy are as follows: S02.1: Input of day-ahead renewable energy power data (1) Data collection and preprocessing: Collect historical power data and meteorological observation data. These data may include temperature, humidity, wind speed, solar radiation, etc. At the same time, divide the data set.

[0043] (2) Feature engineering: Select features related to power output. Feature engineering can generate a feature set that reflects the characteristics of power output.

[0044] (3) Model selection: Select the long short-term memory network (LSTM) model to predict renewable energy power.

[0045] (4) Model training: Use the training dataset to train the selected neural network model.

[0046] (5) Model validation and testing: Use the validation set to fine-tune the model to prevent overfitting. The test set is used to finally evaluate the performance of the model.

[0047] (6) Model deployment: The trained model is used for day-ahead power forecasting of renewable energy.

[0048] S02.2: Construction of energy supply and demand balance of integrated energy system: Based on the day-ahead forecast results of renewable energy, the energy supply and demand balance mechanism of the integrated energy system is constructed as follows: (18) in, , , They are user electrical load, user heat load and user cooling load. The electrical load includes the electrical energy consumed by electric refrigeration, and the heat load includes the heat energy consumed by the absorption chiller. , They are photovoltaic power and wind turbine power respectively; Power interaction between integrated energy systems and power grids; There are interactive upper and lower power constraints: (19) Maximum power interaction between the integrated energy system and the grid; In addition, the day-ahead dispatch strategy has the following energy storage safety margin constraints: (20) The energy storage safety margin constraint can ensure that when there is a fluctuation in the power of renewable energy in the real-time scheduling link, the energy storage charging and discharging power can achieve the energy supply and demand balance in real-time scheduling; The energy objective function of the designed integrated energy system is the sum of all equipment costs, as shown in the following formula: (20) in, The cost of buying and selling electricity to the grid is calculated as follows: (twenty one) in, The unit price for purchasing and selling electricity; This achieves day-ahead power balance in the integrated energy system.

[0049] S03: Day-ahead dispatch strategy for integrated energy system based on day-ahead forecast data of distributed renewable energy sources: S03.1: Based on the output of various equipments proposed by the day-ahead dispatch strategy in step 2 and the real-time fluctuation of renewable energy, the following real-time energy supply and demand balance mechanism is set: (twenty two) in, , It is the grid interaction power and energy storage charging and discharging power in the real-time dispatching link; S03.2: The objective function of real-time dispatch only considers electric energy storage The loss is calculated as follows: (twenty three).

[0050] S04: The steps for long-term optimization of integrated energy systems considering equipment capacity planning are as follows: S04.1: Definition of decision variables and constraints for long-term equipment capacity of integrated energy systems: The decision variables for long-term equipment capacity optimization of the integrated energy system are set as the capacity of electric energy storage, thermal energy storage, and cold energy storage, and the constraints are as follows: (twenty four) in, , , They are the capacities of electrical energy storage, thermal energy storage, and cold energy storage equipment respectively; , , , , , They are the lower limit of electric energy storage capacity configuration, the lower limit of thermal energy storage capacity configuration, the lower limit of cold energy storage capacity configuration, the upper limit of electric energy storage capacity configuration, the upper limit of thermal energy storage capacity configuration, and the upper limit of cold energy storage capacity configuration; S04.2: Objective function of long-term planning of integrated energy systems: The long-term planning of the integrated energy system needs to consider the investment in energy storage equipment and the day-ahead dispatching cost. Its objective function is as follows: (25) in, , , They are the daily investment cost of electric energy storage, the daily investment cost of thermal energy storage, and the daily investment cost of cold energy storage. is the day-ahead scheduling cost.

[0051] S05: Particle swarm optimization algorithm is used to solve the proposed model: S05.1: Joint optimization of long-term planning and day-ahead scheduling of integrated energy systems The decision variables are defined as the capacity of the energy storage equipment and the output of various functional equipment. The constraints are consistent with those of long-term planning and day-ahead scheduling, and the objective function is consistent with the objective function of long-term planning. S05.2: Real-time optimization and dispatching of integrated energy systems. Based on the energy storage capacity optimized in S05.2 and the output configuration of each device, the objective function and constraints of step 4 are used for optimization. In this stage, the decision variables are , ; S05.3: Based on the above objective function, constraints and decision variables, particle swarm optimization algorithm is used for optimization S05.4: After the iteration is completed, the optimal decision variables are output to obtain the output configuration data of the energy storage equipment capacity and various types of equipment in the integrated energy system, thereby realizing the multi-time scale optimization of the integrated energy system.

[0052] The results of comprehensive energy multi-time scale optimization are as follows Figures 1 to 7 As shown, Figure 1 The power dispatch information in the industrial park is displayed. It can be seen from the figure that all the energy supply equipment and processing in the figure meet the load demand and achieve the balance of power supply and demand, that is, power load + demand response = renewable energy + gas turbine + electric energy storage + power grid; Figure 2 The thermal energy dispatch information of the industrial park is displayed. The thermal power data meets the following requirements: thermal load + thermal demand response = gas boiler + waste heat recovery boiler + thermal energy storage; Figure 3 The cooling energy dispatch information is displayed, and the cooling power satisfies: cooling load + cooling demand response = cooling energy storage + electric refrigeration + absorption chiller. The above energy dispatch picture shows that the dispatch using this scheme can meet the energy supply and demand balance in the industrial park; Figure 4 Displays real-time dispatch information of industrial parks, Figure 4 It can be seen that: renewable energy power deviation = electric energy storage adjustment + grid adjustment, which shows that in the real-time scheduling link, the proposed scheme can still meet the balance of cooling supply and demand; Figure 5 , Figure 6 The fitness of each iteration of the particle swarm algorithm in the long time scale and real-time scheduling process is respectively demonstrated, indicating that as the iteration proceeds, the costs of each item are reduced until they stabilize; thus, it is shown that the particle swarm algorithm has a faster iteration speed and better solution effect.

[0053] In summary, the multi-temporal and spatial scale optimization operation strategy of a distributed integrated energy system proposed in the present invention solves the multi-temporal and spatial scale operation optimization problem existing in the distributed integrated energy system in the prior art, especially in the context of increasingly complex and diversified energy systems, how to achieve efficient utilization of energy and balance supply and demand, while considering the uncertainty of renewable energy and the reasonable planning of equipment capacity; the present invention forms a comprehensive optimization strategy of multi-temporal and spatial scales by combining day-ahead prediction with real-time scheduling, long-term planning with short-term optimization. This fusion of multi-dimensional optimization methods is creative and can significantly improve the overall operation efficiency and economy of the system; the multi-energy coupling model constructed by it not only considers the conversion and coordination between different energy forms, but also models in detail the various energy equipment Performance and behavior make the model closer to the actual operation situation. This refined modeling method is creative and provides a more accurate model basis for the formulation of optimized operation strategies. It fully taps the adjustable potential of user-side flexible loads by building a demand response mechanism, and realizes two-way interaction between the supply and demand sides of the system. This method of deeply tapping user-side resources is innovative in the operation of distributed integrated energy systems and helps to improve the flexibility and stability of the system. The present invention applies the LSTM model to renewable energy power prediction, which improves the accuracy and reliability of the prediction. At the same time, the particle swarm optimization algorithm is used to solve the optimization model, which realizes the effective solution to complex problems. The innovative application of these two algorithms in the optimization of distributed integrated energy systems demonstrates the creativity and advancement of the technology.

Claims

1. A multi-temporal and spatial scale optimization operation strategy for a distributed integrated energy system, characterized in that: The strategies include: Step 1: Construction of multi-energy coupling model of integrated energy system; Step 2: Day-ahead dispatch strategy for integrated energy system based on day-ahead forecast data of distributed renewable energy; Step 3: Real-time dispatch strategy of integrated energy system considering prediction deviation of distributed renewable energy; Step 4: Long-term optimization of the integrated energy system considering equipment capacity planning; Step 5: Use particle swarm optimization algorithm to solve the proposed model.

2. The multi-temporal and spatial scale optimization operation strategy of a distributed integrated energy system according to claim 1 is characterized in that: The specific steps of constructing the multi-energy coupling model of the step 1 comprehensive energy system include: Step 1.1: Analyze the energy demand in the area where the integrated energy system is located, determine the load type, including different forms of energy demand such as electricity, heat, cooling, and gas, and determine the equipment type; Step 1.2: Model the multi-energy coupling unit, which includes a combined cooling, heating and power system. , combined heat and power system ,gas turbine , Electric boiler , Gas boiler , and establish the corresponding mathematical model; Step 1.3: Build a user-side demand response model, including a demand response mechanism that can time-shift and reduce loads; Step 1.4: Source side With lotus side Conduct joint modeling to realize the modeling of distributed integrated energy systems.

3. The multi-temporal and spatial scale optimization operation strategy of a distributed integrated energy system according to claim 1 is characterized in that: The specific steps of modeling the multi-energy coupling unit in Step 1.2 include: Step1.2.1: Modeling, establishing a mathematical model of the gas turbine; When working, the relationship between output power and natural gas consumption is as follows: （1）； in, yes exist Natural gas consumption at the time, is the power generation, and is the gas-to-electricity conversion coefficient, is the number of hours in a day; The output power has output constraints and ramp constraints, as shown below: （2）； in, , They are The minimum output power and maximum output power; is the maximum power change value; for exist Output power at the moment; Cost The calculation is as follows: （3）； in, , They are the cost of purchasing natural gas and the operation and maintenance cost; Step1.2.2: Modeling, establishing the mathematical model of the electric boiler; Capable of recovering heat from the heat generated by the gas turbine. as follows: （4）； in, for The efficiency of heat recovery, for The ratio of electricity generation to heat rejection, for Heat loss; at the same time The output heat is subject to the following constraints: （5）； in, , They are Maximum output and maximum power change; Cost The calculation is as follows: （6）； in, for The maintenance factor; Step1.2.3: Modeling, establishing the mathematical model of the gas boiler; In an integrated energy system, The model is a key part of heat supply, the following is Constraints: （7）； in, , , , , They are At the moment The natural gas consumed, the thermal power output, the minimum thermal power output, the maximum thermal power output and the maximum change in thermal power; for The ratio coefficient between natural gas consumption and thermal power output; for exist Thermal power output at any time; The cost and Similarly, it is calculated as follows: （8）； in, for The maintenance factor; Step1.2.4: and Modeling, establish mathematical models of air compressors and electric compressors; It is a device that can convert heat into cold energy. It can convert electrical power into gas power, and its output characteristics are as follows: （9）； in, , They are The cooling power generated is Input thermal power, for Refrigeration heat consumption coefficient; , They are The cooling power generated and the electrical power consumed, for Refrigeration power consumption coefficient; and The output constraints are as follows: （10）； in, for The maximum value of heat power that can be input; for The maximum value of the electrical power that can be input; and In terms of cost, there is only operation and maintenance cost, which is calculated as follows: （11）； in , They are and maintenance costs, , for and The maintenance factor; Step 1.2.5: Electric energy storage , Thermal Energy Storage , Cold Energy Storage Modeling, establish the mathematical model of energy storage equipment, including its capacity, charging and discharging power, efficiency, etc.; , , The capacity of a battery has the following relationship with its own charging, discharging, heating and cooling power: （12）； in, , , They are , , exist The remaining capacity at the moment, , , They are , , exist The remaining capacity at the moment, , , They are , , The charging and discharging power; For charging efficiency; , A binary variable for charging and discharging the energy storage. , is a binary variable for thermal energy storage charging and thermal energy storage discharging, , A binary variable for charging and discharging cold energy storage; is the time interval; at the same time , , There are the following constraints: （13）； in, , , for , , is the maximum power of each charge and discharge; , , They are , , Minimum safe capacity; , , They are , , The maximum safe capacity of the binary variable of charging and discharging has the following constraints: （14）； Energy storage has operation and maintenance costs, which are calculated as follows: （15）； in, , , They are , , The energy storage maintenance factor.

4. The multi-temporal and spatial scale optimization operation strategy of a distributed integrated energy system according to claim 2 is characterized in that: The construction of the Step 1.3 user-side demand response model includes: Step 1.3.1: Time-shiftable load constraints include constraints on electrical time-shifted loads, thermal time-shifted loads, and cold time-shifted loads. The constraints are as follows: （16）； in, , , Respectively in The electrical time-shifting load, heat time-shifting load and cooling time-shifting load at each moment; , , are the maximum values ​​of the time-shifted loads of electricity, heat, and cold respectively; the time-shiftable load must satisfy the requirement that the sum of the load transferred in and out during a day is 0, and there is a maximum value constraint on the load that can be transferred in each period; Step 1.3.2: Constraints on the reducible loads, including the reducible loads of electricity, heat, and cooling and their maximum values. The constraints are as follows: （17）； in, , , They are the curtailable loads of electricity, heat and cooling respectively; , , They are the maximum loads that can be reduced for electricity, heating and cooling respectively.

5. The multi-temporal and spatial scale optimization operation strategy of a distributed integrated energy system according to claim 1, characterized in that: The step 2 of the integrated energy system day-ahead dispatch strategy based on the distributed renewable energy day-ahead forecast data includes: Step 2.1: Input the renewable energy power data of the day before, and predict the renewable energy power through data collection and preprocessing, feature engineering, model selection and model deployment; Step 2.2: Construct an energy supply and demand balance mechanism for the integrated energy system to ensure the day-ahead power balance of the integrated energy system.

6. The multi-temporal and spatial scale optimization operation strategy of a distributed integrated energy system according to claim 5, characterized in that: The energy supply and demand balance mechanism of the integrated energy system in Step 2.2 is constructed based on the renewable energy day-ahead forecast results, and its mechanism is as follows: （18）； in, , , They are user electrical load, user heat load and user cooling load. The electrical load includes the electrical energy consumed by electric refrigeration, and the heat load includes the heat energy consumed by the absorption chiller. , are photovoltaic power and wind turbine power respectively; Power interaction between integrated energy systems and power grids; There are interactive upper and lower power constraints: （19）； Maximum power interaction between the integrated energy system and the grid; In addition, the day-ahead dispatch strategy has the following energy storage safety margin constraints: （20）； The energy storage safety margin constraint can ensure that when there is a fluctuation in the power of renewable energy in the real-time scheduling link, the energy storage charging and discharging power can achieve the energy supply and demand balance in real-time scheduling; The energy objective function of the designed integrated energy system is the sum of all equipment costs, as shown in the following formula: （20）； in, The cost of buying and selling electricity to the grid is calculated as follows: （21）； in, The unit price for purchasing and selling electricity; This achieves day-ahead power balance in the integrated energy system.

7. The multi-temporal and spatial scale optimization operation strategy of a distributed integrated energy system according to claim 1, characterized in that: The real-time dispatch strategy of the integrated energy system taking into account the prediction deviation of distributed renewable energy in Step 3 includes: Step 3.1: Based on the output of various equipments planned by the day-ahead dispatch strategy and the real-time fluctuation of renewable energy, a real-time energy supply and demand balance mechanism is set: （22）； in, , It is the grid interaction power and energy storage charging and discharging power in the real-time dispatching link; Step 3.2: The objective function of real-time scheduling only considers electric energy storage The loss is calculated as follows: （23）。 8. The multi-temporal and spatial scale optimization operation strategy of a distributed integrated energy system according to claim 1 is characterized in that: The long-term optimization of the integrated energy system considering equipment capacity planning in Step 4 includes: Step 4.1: Define the decision variables of the long-term equipment capacity of the integrated energy system as the capacity of electric energy storage, thermal energy storage, and cold energy storage, and set the constraints as follows: （24）； in, , , They are the capacities of electrical energy storage, thermal energy storage, and cold energy storage equipment respectively; , , , , , They are the lower limit of electric energy storage capacity configuration, the lower limit of thermal energy storage capacity configuration, the lower limit of cold energy storage capacity configuration, the upper limit of electric energy storage capacity configuration, the upper limit of thermal energy storage capacity configuration, and the upper limit of cold energy storage capacity configuration; Step 4.2: Considering the investment in energy storage equipment and the day-ahead dispatching cost, set the objective function for the long-term planning of the integrated energy system: （25）； in, , , They are the daily investment cost of electric energy storage, the daily investment cost of thermal energy storage, and the daily investment cost of cold energy storage. is the day-ahead scheduling cost.

9. The multi-temporal and spatial scale optimization operation strategy of a distributed integrated energy system according to claim 8, characterized in that: The Step 5 uses the particle swarm optimization algorithm to solve the proposed model, including: Step 5.1: Joint optimization of long-term planning and day-ahead scheduling of the integrated energy system. The decision variables are defined as the capacity of the energy storage equipment and the output of various functional equipment. The constraints are consistent with the constraints of the day-ahead scheduling of the long-term plan, and the objective function is consistent with the objective function of the long-term plan. Step 5.2: Based on the optimized energy storage capacity and the output configuration of each device, real-time optimization scheduling is performed. Specifically, the objective function and constraints of Step 4 are used for optimization. In this stage, the decision variables are , ; Step 5.3: Based on the above objective function, constraints and decision variables, particle swarm optimization algorithm is used for optimization.

10. The multi-temporal and spatial scale optimization operation strategy of a distributed integrated energy system according to claim 9, characterized in that: The specific steps of optimizing using the particle swarm optimization algorithm in Step 5.3 are as follows: Step 5.3.1: Definition of population size and number of iterations Step 5.3.2: Population initialization, use the following formula to initialize the population: （26）； in, For the The decision variables of individuals in the initialization stage, is a random number between 0 and 1. is the upper bound of the decision variable, is the lower bound of the decision variable; Step 5.3.3: Enter the iteration phase and first calculate the objective function of each individual in the population; Step 5.3.4: Based on the objective function, select the global optimal individual and the historical optimal value of each individual; Step 5.3.5: Update the speed using the following formula: （27）； in, For individuals In the The speed of iterations, is the inertia weight, is the optimal weight of the individual, is the global optimal weight; , are the historical optimal value of each individual and the global optimal individual; For the Individuals in The decision variables at the moment; Step 5.3.6: After updating the speed, determine whether the speed exceeds the upper and lower limits of the speed limit. If the speed exceeds the upper limit, set the speed to the upper limit; if it is lower than the lower limit, set it to the lower limit. Use the following formula to update the position: （28）； in, For the Individuals in The decision variables at the moment; Determine whether the position exceeds the limit range and correct the position in a similar way to the speed correction method; Step 5.3.7: After the iteration is completed, the optimal decision variables are output to obtain the output configuration data of the energy storage equipment capacity and various types of equipment in the integrated energy system, thereby realizing the multi-time scale optimization of the integrated energy system.

Images