A method and system for optimizing the configuration of energy stations with multi-energy synergy and complementarity.

By solving the bi-level programming model using genetic algorithms and branch-and-bound algorithms, the problem of coordination and complementarity among multiple energy stations was solved, improving the comprehensive utilization efficiency and flexibility of the energy system and achieving the goal of low-carbon and high-efficiency regional integrated energy.

CN123117568APending Publication Date: 2026-11-17NORTH CHINA BRANCH OF STATE GRID CORPORATION OF CHINA +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510622812.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-15
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

In existing technologies, the planning of multiple energy stations is only carried out in isolation for individual energy stations, without fully considering the synergy and complementarity between multiple energy stations, which leads to a reduction in the overall utilization efficiency of the energy system.

Method used

Genetic algorithm and branch and bound algorithm are used to solve the pre-constructed bi-level programming model, and the optimal capacity configuration and optimal output scheduling of multi-energy infrastructure in each energy station are output. The optimal configuration among multiple energy stations is realized through the bi-level programming model.

Benefits of technology

It has improved the overall utilization efficiency of the energy system, enhanced the flexibility and dispatchability of energy supply, and achieved the goal of a low-carbon, efficient, and intelligent regional integrated energy system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123117568A_ABST
    Figure CN123117568A_ABST
Patent Text Reader

Abstract

This invention provides a method and system for optimizing the configuration of energy stations through multi-energy synergy and complementarity, comprising: acquiring operational data of multi-energy infrastructure in each energy station; solving a pre-constructed bi-level programming model using a genetic algorithm and a branch-and-bound algorithm based on the operational data of the multi-energy infrastructure in each energy station, and outputting the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station; using the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station as the optimal configuration scheme among the energy stations; this invention achieves synergistic optimization among multiple energy stations by combining a genetic algorithm and a branch-and-bound algorithm to solve a pre-constructed bi-level programming model from different energy stations, which is beneficial to improving the overall energy utilization efficiency of the energy system.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of integrated energy system planning technology, specifically to a method and system for optimizing the configuration of energy stations with multi-energy synergy and complementarity. Background Technology

[0002] Currently, with economic and social development, the contradiction between increasing energy demand and energy shortage, and between energy utilization and environmental protection, is becoming increasingly prominent. Improving energy efficiency, exploring new energy sources, and realizing the planned development of renewable energy are inevitable choices for the energy sector. Solar and wind power are inherently intermittent, and related technologies are still immature, making large-scale effective utilization difficult. Traditional electricity, heat, and cooling energy industries are relatively closed, and isolated planning and operation are not conducive to improving the overall system energy efficiency. The synergistic complementarity of multiple energy systems (electricity, heat, and cooling) is of great significance in improving the comprehensive energy efficiency, operational reliability, and economy of energy systems. However, existing technologies have the following shortcomings:

[0003] For example, the literature [1] (“Three-level Coordinated Overall Optimization Design Method for Combined Cooling, Heating and Power Systems” Proceedings of the CSEE 35.015(2015):3785-3793.) published a three-level coordinated overall optimization method for combined cooling, heating and power systems. The first-level optimization uses the discrete particle swarm optimization algorithm to solve the optimal equipment selection problem with the goal of maximizing the annual primary energy utilization rate. The second-level optimization uses the particle swarm optimization algorithm to solve the optimal equipment capacity problem with the goal of minimizing the annual CO2 emissions. The third-level optimization uses the particle swarm optimization algorithm to solve the optimal operating parameter problem with the goal of minimizing the annual operating cost. However, this method only considers internal combustion engine combined cooling, heating and power units that use natural gas as a primary energy source, and does not take into account the integration of other energy sources, so it cannot realize the utilization of renewable energy and multi-energy complementarity on the production side.

[0004] For example, the literature [2] (“Optimization and Coordination Model and Solution Method of Wind, Solar and Gas Storage Complementary Power Generation” Proceedings of the CSEE) published an optimization and coordination model of cooling, heating and power generation considering different rate structures and wind, solar, natural gas and energy storage complementary power generation. It considers the joint supply of cooling, heating and electricity, as well as the different rate structures and seasonal differences of electricity and natural gas. The optimization model of complementary power generation of multiple energy forms is constructed. It adopts the typical load model of winter and summer and the third-order efficiency model of generator to accurately simulate the heat effect of power generation. The total cost of purchasing electricity and natural gas is used as the objective function. The constraints include cooling, heating and power load balance, tie line power and output characteristics of each equipment. However, this method is only for the optimization and coordination of the system operation within a single energy station and does not fully consider the multi-regional collaborative complementarity.

[0005] In summary, existing technologies for planning energy stations tend to focus on a single energy type and multi-energy flow coupling within a single energy station. They lack global optimization for multi-energy complementarity and coordination, making it difficult to achieve regional resource allocation among multiple energy stations and resulting in reduced overall utilization efficiency of the energy system. Summary of the Invention

[0006] To address the problem that existing multi-energy synergy technologies only plan and operate individual energy stations in isolation, failing to fully consider the synergy and complementarity between multiple energy stations, thus reducing the overall utilization efficiency of the energy system, this invention proposes a method for optimizing the configuration of energy stations through multi-energy synergy and complementarity, comprising:

[0007] Acquire operational data of multi-energy infrastructure equipment in each energy station;

[0008] Based on the operating data of the multi-energy infrastructure in each energy station, the pre-constructed bi-level programming model is solved using genetic algorithm and branch and bound algorithm, and the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station are output.

[0009] The optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station are used as the optimal configuration scheme among the energy stations.

[0010] The two-level planning model includes an upper-level planning model and a lower-level planning model. The upper-level planning model is constructed with the goal of minimizing the sum of investment costs and energy operating costs of the multi-energy infrastructure in each energy station. The lower-level planning model is constructed with the goal of minimizing the energy operating costs of the multi-energy infrastructure in each energy station.

[0011] Optionally, the step of solving a pre-constructed bi-level programming model using genetic algorithms and branch-and-bound algorithms based on the operating data of the multi-energy infrastructure in each energy station, and outputting the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station, includes:

[0012] Based on each energy station, and according to the operating data of the multi-energy infrastructure in the energy station, the operating boundaries of the multi-energy infrastructure are set;

[0013] A chromosome population is randomly generated, and each chromosome in the population is used as a set of capacity allocation schemes;

[0014] The chromosome population is binary-coded according to the operational boundaries of the multi-energy infrastructure.

[0015] The lower-level programming model in the pre-constructed bi-level programming model is converted into a mixed-integer linear programming model, and each chromosome after binary encoding is input into the mixed-integer linear programming model.

[0016] Based on each chromosome, the branch and bound algorithm is used to solve the mixed integer linear programming model to obtain the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station.

[0017] Optionally, the step of solving the mixed-integer linear programming model based on each chromosome using a branch-and-bound algorithm to obtain the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station includes:

[0018] Based on each chromosome, the mixed integer linear programming model is solved using the branch and bound algorithm to obtain the output scheduling scheme of the multi-energy infrastructure corresponding to the chromosome.

[0019] Calculate the energy operating cost of the multi-energy infrastructure corresponding to the chromosome based on the power output scheduling scheme of the multi-energy infrastructure corresponding to the chromosome.

[0020] The total operating cost of the multi-energy infrastructure corresponding to the chromosome is obtained by summing the energy operating cost and investment cost.

[0021] Based on the total operating cost of the multi-energy infrastructure corresponding to each chromosome, a genetic algorithm is used to obtain the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station.

[0022] Optionally, the step of using a genetic algorithm to obtain the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station based on the total operating cost of the multi-energy infrastructure corresponding to each chromosome includes:

[0023] The reciprocal of the total operating cost of the multi-energy infrastructure corresponding to each chromosome is used as the fitness function value of the corresponding chromosome.

[0024] Based on the fitness function value of each chromosome, select the chromosomes with the highest fitness function value from the chromosome population, which constitute the top preset proportion, as elite chromosomes.

[0025] The chromosome population is subjected to selection, crossover, and mutation operations to generate a new chromosome population, and the elite chromosomes and the new chromosome population are used as the next generation chromosome population;

[0026] Obtain the current iteration number. If the current iteration number is greater than the preset maximum iteration number, select the chromosome with the largest fitness function value in the new generation chromosome population as the optimal capacity configuration of the multi-energy infrastructure in the energy station.

[0027] Based on the optimal capacity configuration and the lower-level planning model, the optimal output scheduling of the multi-energy infrastructure is obtained.

[0028] Optionally, the upper-level planning model includes the following construction process:

[0029] The total operating cost of each energy station is obtained by summing the investment cost and energy operation cost of the multi-energy infrastructure in each energy station.

[0030] To minimize the total operating cost, a higher-level objective function is constructed.

[0031] Based on the aforementioned upper-level objective function, formulate the corresponding upper-level constraints for the upper-level objective function;

[0032] Based on the aforementioned upper-level objective function and upper-level constraints, an upper-level planning model is constructed.

[0033] The upper-level constraints include one or more of the following: equipment installation capacity constraints, equipment collaborative operation constraints, and reliability constraints.

[0034] Optionally, the lower-level planning model includes the following construction process:

[0035] The energy operating cost of each energy station is obtained by summing the operation and maintenance costs, fuel costs, electricity purchase costs, and carbon tax costs of the multi-energy infrastructure in each energy station.

[0036] To minimize the energy operating costs, a lower-level objective function is constructed.

[0037] Based on the lower-level objective function, formulate the lower-level constraint conditions corresponding to the lower-level objective function;

[0038] Based on the lower-level objective function and the lower-level constraints, a lower-level planning model is constructed;

[0039] The lower-level constraints include one or more of the following: power balance constraints, output constraints, charging constraints, and discharging constraints.

[0040] Optionally, the multi-energy infrastructure includes one or more of the following: energy production equipment, energy conversion equipment, and energy storage equipment;

[0041] The energy production equipment includes one or more of the following: combined heat and power units, gas boiler models, coal-fired boiler models, photovoltaic module models, and wind turbine output models;

[0042] The energy storage device includes one or more of the following: electrical storage device, thermal storage device, and cold storage device;

[0043] The operational data includes one or more of the following: equipment performance parameters, load data, and meteorological data;

[0044] The energy operating costs include one or more of the following: operation and maintenance costs, fuel costs, electricity purchase costs, and carbon tax costs;

[0045] The optimal capacity configuration includes one or more of the following: optimal installation capacity of equipment, transmission capacity of lines between different equipment, and transmission path;

[0046] The optimal power output scheduling includes one or more of the following: optimal power generation, optimal heating power, optimal cooling power, optimal energy storage status, and equipment switching status.

[0047] Based on the same inventive concept, this invention also provides a multi-energy synergistic and complementary energy station optimization configuration system, comprising:

[0048] The data acquisition module is used to acquire operational data of multi-energy infrastructure equipment in each energy station;

[0049] The model solving module is used to solve the pre-constructed bi-level programming model based on the operating data of the multi-energy infrastructure in each energy station, using genetic algorithms and branch and bound algorithms, and output the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station.

[0050] The optimization configuration module is used to use the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure equipment in each energy station as the optimal configuration scheme among the energy stations.

[0051] The two-level planning model includes an upper-level planning model and a lower-level planning model. The upper-level planning model is constructed with the goal of minimizing the sum of investment costs and energy operating costs of the multi-energy infrastructure in each energy station. The lower-level planning model is constructed with the goal of minimizing the energy operating costs of the multi-energy infrastructure in each energy station.

[0052] Optionally, the model solving module includes:

[0053] The boundary setting submodule is used to set the operating boundaries of the multi-energy infrastructure based on the operating data of the multi-energy infrastructure in each energy station.

[0054] The chromosome generation submodule is used to randomly generate a chromosome population, with each chromosome in the population serving as a set of capacity configuration schemes;

[0055] The population coding submodule is used to perform binary coding on the chromosome population based on the operating boundaries of the multi-energy infrastructure.

[0056] The model conversion submodule is used to convert the lower-level programming model in the pre-built bi-level programming model into a mixed-integer linear programming model, and input each chromosome after binary encoding as an input item into the mixed-integer linear programming model;

[0057] The model output submodule is used to solve the mixed integer linear programming model based on each chromosome using the branch and bound algorithm, so as to obtain the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station.

[0058] Optionally, the model output submodule includes:

[0059] The output scheduling unit is used to solve the mixed integer linear programming model based on each chromosome using a branch and bound algorithm to obtain the output scheduling scheme of the multi-energy infrastructure corresponding to the chromosome.

[0060] The cost calculation unit is used to calculate the energy operation cost of the multi-energy infrastructure corresponding to the chromosome based on the output scheduling scheme of the multi-energy infrastructure corresponding to the chromosome.

[0061] The total cost calculation unit is used to obtain the total operating cost of the multi-energy infrastructure corresponding to the chromosome based on the sum of the energy operating cost and investment cost of the multi-energy infrastructure corresponding to the chromosome.

[0062] The scheme output unit is used to obtain the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station based on the total operating cost of the multi-energy infrastructure corresponding to each chromosome and using a genetic algorithm.

[0063] Optionally, the scheme output unit includes:

[0064] The fitness setting subunit is used to take the reciprocal of the total operating cost of the multi-energy infrastructure corresponding to each chromosome as the fitness function value of the corresponding chromosome.

[0065] The elite retention subunit is used to select the chromosomes with the highest fitness function values ​​from the chromosome population as elite chromosomes based on the fitness function values ​​of each chromosome.

[0066] The population generation subunit is used to perform selection, crossover, and mutation operations on the chromosome population to generate a new chromosome population, and to use the elite chromosomes and the new chromosome population as the next generation chromosome population;

[0067] The capacity configuration subunit is used to obtain the current iteration number. If the current iteration number is greater than the preset maximum iteration number, the chromosome with the largest fitness function value in the new generation chromosome population is taken as the optimal capacity configuration of the multi-energy infrastructure in the energy station.

[0068] The output scheduling subunit is used to obtain the optimal output scheduling of the multi-energy infrastructure based on the optimal capacity configuration and the lower-level planning model.

[0069] Optionally, the optimized configuration system further includes: an upper-level model construction module, comprising:

[0070] The upper-level target calculation submodule is used to obtain the total operating cost of each energy station based on the sum of the investment cost and energy operation cost of the multi-energy infrastructure in each energy station;

[0071] The upper-level objective construction submodule is used to construct the upper-level objective function with the goal of minimizing the total running cost;

[0072] The upper-level constraint formulation submodule is used to formulate the upper-level constraint conditions corresponding to the upper-level objective function based on the upper-level objective function;

[0073] The upper-level model construction submodule is used to construct the upper-level planning model based on the upper-level objective function and the upper-level constraints.

[0074] The upper-level constraints include one or more of the following: equipment installation capacity constraints, equipment collaborative operation constraints, and reliability constraints.

[0075] Optionally, the optimized configuration system further includes: a lower-level model construction module, comprising:

[0076] The lower-level target calculation submodule is used to obtain the energy operation cost of each energy station based on the sum of the operation and maintenance costs, fuel costs, electricity purchase costs and carbon tax costs of the multi-energy infrastructure in each energy station;

[0077] The lower-level objective construction submodule is used to construct a lower-level objective function with the goal of minimizing the energy operating cost;

[0078] The lower-level constraint formulation submodule is used to formulate the lower-level constraint conditions corresponding to the lower-level objective function based on the lower-level objective function;

[0079] The lower-level model construction submodule is used to construct the lower-level planning model based on the lower-level objective function and the lower-level constraints.

[0080] The lower-level constraints include one or more of the following: power balance constraints, output constraints, charging constraints, and discharging constraints.

[0081] Optionally, the multi-energy infrastructure includes one or more of the following: energy production equipment, energy conversion equipment, and energy storage equipment;

[0082] The energy production equipment includes one or more of the following: combined heat and power units, gas boiler models, coal-fired boiler models, photovoltaic module models, and wind turbine output models;

[0083] The energy storage device includes one or more of the following: electrical storage device, thermal storage device, and cold storage device;

[0084] The operational data includes one or more of the following: equipment performance parameters, load data, and meteorological data;

[0085] The energy operating costs include one or more of the following: operation and maintenance costs, fuel costs, electricity purchase costs, and carbon tax costs;

[0086] The optimal capacity configuration includes one or more of the following: optimal installation capacity of equipment, transmission capacity of lines between different equipment, and transmission path;

[0087] The optimal power output scheduling includes one or more of the following: optimal power generation, optimal heating power, optimal cooling power, optimal energy storage status, and equipment switching status.

[0088] In another aspect, the present invention also provides an electronic device, comprising: at least one processor and a memory; the memory and the processor are connected via a bus;

[0089] The memory is used to store one or more programs;

[0090] When the one or more programs are executed by the at least one processor, the energy station optimization configuration method with multi-energy synergy and complementarity as described above is implemented.

[0091] In another aspect, the present invention also provides a computer device readable storage medium having an executable program stored thereon, wherein when the executable program is executed, it implements the aforementioned method for optimizing the configuration of a multi-energy synergistic and complementary energy station.

[0092] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0093] This invention provides a method and system for optimizing the configuration of energy stations through multi-energy synergy and complementarity, comprising: acquiring operational data of multi-energy infrastructure in each energy station; solving a pre-constructed bi-level programming model using a genetic algorithm and a branch-and-bound algorithm based on the operational data of the multi-energy infrastructure in each energy station, and outputting the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station; using the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station as the optimal configuration scheme among the energy stations; wherein, the bi-level programming model includes an upper-level programming model and a lower-level programming model; the upper-level programming model is constructed with the objective of minimizing the sum of investment costs and energy operating costs of the multi-energy infrastructure in each energy station; the lower-level programming model is constructed with the objective of minimizing the energy operating costs of the multi-energy infrastructure in each energy station; this invention achieves multi-energy synergy optimization among multiple energy stations by combining a genetic algorithm and a branch-and-bound algorithm to solve a pre-constructed bi-level programming model from different energy stations, which is beneficial to improving the overall energy utilization efficiency of the energy system. Attached Figure Description

[0094] Figure 1 A flowchart illustrating a method for optimizing the configuration of energy stations through multi-energy synergy and complementarity provided by the present invention;

[0095] Figure 2 This is a schematic diagram of chromosome coding configuration in a multi-energy synergistic and complementary energy station optimization configuration method provided by the present invention;

[0096] Figure 3 This is a schematic diagram illustrating the overall solution of the two-level programming model in the energy station optimization configuration method for multi-energy synergy and complementarity provided by the present invention.

[0097] Figure 4 A schematic diagram of the structural composition of an energy station optimization configuration system with multi-energy synergy and complementarity provided by the present invention;

[0098] Figure 5 This is a schematic diagram of the structure of an electronic device provided by the present invention. Detailed Implementation

[0099] This invention proposes a method, system, equipment, and medium for optimizing the configuration of energy stations through multi-energy synergy and complementarity. The specific embodiments of this invention will be further described in detail below with reference to the accompanying drawings.

[0100] Example 1:

[0101] This invention provides a method for optimizing the configuration of energy stations through multi-energy synergy and complementarity, as illustrated in the flowchart below. Figure 1 As shown, it includes:

[0102] Step 1: Obtain operational data of multi-energy infrastructure equipment in each energy station;

[0103] Step 2: Based on the operating data of the multi-energy infrastructure in each energy station, use the genetic algorithm and branch and bound algorithm to solve the pre-constructed bi-level programming model, and output the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station.

[0104] Step 3: Use the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station as the optimal configuration scheme among the energy stations;

[0105] The two-level programming model includes an upper-level programming model and a lower-level programming model. The upper-level programming model is constructed with the goal of minimizing the sum of investment costs and energy operating costs of multi-energy infrastructure in each energy station. The lower-level programming model is constructed with the goal of minimizing the energy operating costs of multi-energy infrastructure in each energy station.

[0106] Currently, few studies fully consider the complementary advantages of interconnecting multiple regions through various power and heat lines, integrating combined heat and power (CHP), photovoltaic, wind power, and energy storage facilities, as well as the deep coupling and synergistic utilization of multiple energy flows (electricity, heat, and cooling). This makes it difficult to achieve integrated planning of multiple energy networks between energy stations. This research deficiency not only limits further reductions in overall system investment costs but also hinders the continuous improvement of comprehensive energy utilization efficiency and renewable energy absorption capacity. Most existing energy system planning focuses only on capacity or scheduling optimization for single-type energy equipment, failing to achieve complementary synergy between multiple energy forms. Even some existing studies involving multi-energy coordination optimization are often limited to the internal workings of a single energy station, lacking system modeling and coordinated control mechanisms for capacity configuration and scheduling strategies across stations. This fragmented optimization approach easily leads to uneven resource allocation, low operating efficiency, and fragmented investment decisions, making it difficult to support the global coordination and efficient operation of integrated energy systems in complex operating environments.

[0107] To address the aforementioned problems, this invention proposes a multi-energy station optimization configuration method based on a two-layer programming model. The upper layer focuses on the capacity configuration of energy equipment and network structure design, while the lower layer focuses on the output scheduling of various energy equipment during typical time periods. Through the collaborative application of genetic algorithms and branch-and-bound algorithms, unified optimization of multiple energy types, multiple energy stations, and multiple energy flows is achieved. This method effectively overcomes the limitations of traditional optimization methods, improving the economy, scheduling efficiency, and overall coordination capability of the energy system.

[0108] For example, the multi-energy infrastructure in step 1 above may include one or more of the following: energy production equipment, energy conversion equipment, and energy storage equipment;

[0109] The aforementioned energy production equipment may include one or more of the following: combined heat and power units, gas-fired boiler models, coal-fired boiler models, photovoltaic module models, and wind turbine output models;

[0110] The aforementioned energy storage devices may include one or more of the following: electrical storage devices, thermal storage devices, and cold storage devices;

[0111] The aforementioned operational data may include one or more of the following: equipment performance parameters, load data, and meteorological data;

[0112] In the above example, by combining various types of energy production equipment, such as combined heat and power units, gas / coal-fired boilers, photovoltaic modules, and wind turbines, with energy storage devices such as electricity storage, thermal storage, and cold storage, and supplementing them with energy conversion equipment to construct a systematic multi-energy collaborative network, the comprehensive utilization efficiency of energy can be significantly improved, achieving coordinated supply of various forms of energy such as electricity, heat, and cooling. Utilizing the operational data of these devices, including equipment performance parameters, load data, and meteorological information, not only can the operational boundaries and states of the equipment be accurately described, but the realism and dynamic response capability of the modeling can also be improved. This provides precise support for subsequent capacity configuration and output scheduling optimization. Compared to traditional optimization methods that only target a single energy source or a single energy station, by encompassing collaborative planning among multiple types of equipment and multiple energy stations, it is not only beneficial to improve the overall economic efficiency and stability of the energy system's operation, but also to enhance the flexibility and dispatchability of energy supply, effectively supporting the high-proportion integration and fluctuation balance of new energy sources, ultimately achieving the goal of a low-carbon, efficient, and intelligent regional integrated energy system.

[0113] Furthermore, in order to accurately model the operational characteristics of multi-energy infrastructure and support the joint solution of capacity allocation and output scheduling in the bi-level programming model, it is necessary to construct corresponding mathematical models based on the physical characteristics and operational data of various energy infrastructures. The typical modeling methods for multi-energy infrastructure are as follows:

[0114] A. Combined heat and power unit

[0115] A combined heat and power (CHP) unit uses fossil fuels as input and generates electricity by utilizing the expansion of high-temperature gases produced during combustion. The high-temperature waste heat from the exhaust gas is recovered through a heat exchanger, effectively improving energy utilization efficiency. The relationship between coal consumption, waste heat recovery, and output power of a CHP unit can be expressed as follows:

[0116]

[0117] In the formula: This represents the electrical power of the i-th combined heat and power unit in the energy station at time t; This represents the fuel consumption of the i-th combined heat and power unit in energy station j at time t; This represents the amount of waste heat recovered by the i-th cogeneration unit in the energy station at time t. Let be the power generation efficiency at time t; K is the heat dissipation loss coefficient of the gas turbine at time t; he This indicates the efficiency of the waste heat recovery system.

[0118] B. Gas / Coal Boiler Model

[0119] Gas-fired / coal-fired boilers utilize natural gas for heat generation and have advantages such as low construction costs, simple operation, and convenient maintenance. They are frequently chosen heating equipment in traditional heating models (district boiler rooms), and their output characteristics can be expressed as follows:

[0120]

[0121] In the formula: This represents the heat output of the boiler in energy station j at time t; η represents the fuel consumption of the boiler in energy station j at time t; B Indicates heating efficiency.

[0122] C. Photovoltaic module model

[0123] Photovoltaic modules convert abundant natural light energy into electrical energy, possessing advantages such as being renewable and clean. In recent years, the photovoltaic industry has experienced rapid development with policy support, and its output characteristics can be expressed as follows:

[0124]

[0125] In the formula: G represents the photovoltaic output of the energy supply area under the jurisdiction of energy station j at time t; t,j This represents the solar irradiance of the photovoltaic system in the energy supply area under the jurisdiction of energy station j at time t; G represents the maximum photovoltaic output of energy station j under standard conditions; stc T represents the light intensity of a photovoltaic system under standard conditions. t,j T represents the temperature of the photovoltaic system in the energy supply area under the jurisdiction of energy station j at time t; r k represents the reference temperature of the photovoltaic module at time t; T This represents the power temperature coefficient.

[0126] D. Wind turbine output model

[0127] The output of a wind turbine varies with wind speed. Due to the random nature of wind speed in terms of output, it is difficult for wind turbines to maintain a stable output. Furthermore, the relationship between wind turbine output and wind speed is not a simple linear one, but can be represented by the following piecewise function:

[0128]

[0129] In the formula: P t V represents the output of the wind turbine at time t; t V represents the wind speed at time t; ci Indicates the cut-in wind speed of the fan; V r Indicates the rated wind speed of the fan; V co The cutoff wind speed represents the wind turbine's cutoff velocity; k represents the actual output of the wind turbine; μ represents the average wind speed; σ represents the standard deviation of wind speed; P r A represents the rated power of the wind turbine; B represents the reference power coefficient; C represents the linear wind speed influence coefficient; and D represents the wind speed square term coefficient.

[0130]

[0131] Energy conversion equipment typically follows a process of converting high-grade energy to low-grade energy, with the energy quality decreasing sequentially from electricity to heat to cold. Therefore, the input of this unit is generally electricity and heat, and the output is generally heat and cold. Because the operating characteristics of these energy units are very similar, they can be uniformly represented by the following formula.

[0132]

[0133] In the formula: This represents the input quantity of the s0th energy conversion device in energy station j at time t; This represents the output of the s0th energy conversion device in energy station j at time t; This represents the efficiency or coefficient of performance (COP) of the s0th energy conversion device.

[0134] Operating characteristics of energy storage devices:

[0135] Energy storage devices are used to realize the transfer of energy across time periods and coordinate the imbalance between "source and load" within the grid. On a short time scale, they smooth out the fluctuations of renewable energy, and on a long time scale, they achieve peak shaving and valley filling, ultimately promoting the economical and efficient operation of the energy supply system. Specifically, the operating characteristics of energy storage devices can be expressed as follows:

[0136]

[0137] In the formula: E t,j H represents the current storage capacity of the energy storage equipment in energy station j at time t; t,jE represents the current storage capacity of the thermal (cold) storage equipment in energy station j at time t; t-1,j H represents the current storage capacity of the energy storage equipment in energy station j at time t-1; t-1,j τ represents the existing storage capacity of the thermal (cold) storage equipment in energy station j at time t-1; τ represents the self-discharge rate of the energy storage equipment; μ0 represents the heat loss rate of the thermal / cold storage equipment. This represents the charging power of the energy storage equipment in energy station j at time t; η represents the discharge power of the energy storage device in energy station j at time t; ech Indicates the charging efficiency of energy storage devices; η edis Indicates the discharge efficiency of the energy storage device; This represents the charging power of the thermal / cold storage equipment in energy station j at time t; η represents the heat release power of the thermal / cold storage equipment in energy station j at time t; hch Indicates the heat charging efficiency of thermal storage / cooling equipment; η hdis Δt represents the heat release efficiency of the thermal storage / cooling equipment; Δt represents the time interval.

[0138] Inter-regional heating circuit modeling:

[0139] This section focuses on energy transmission units that interconnect various energy supply areas (i.e., energy stations), mainly divided into two categories: power lines and heat lines. A "channel" model is adopted, and the energy transmission characteristics of the lines are shown in the following formula:

[0140]

[0141] In the formula: This represents the amount of electricity that energy station j transmits to energy station k at time t; This represents the heat transferred from energy station j to energy station k at time t; This represents the amount of electricity that energy station j actually delivers to energy station k at time t; L represents the amount of heat actually delivered by energy station j to energy station k at time t; j,k δ1 represents the distance between energy station j and energy station k; δ2 represents the loss rate per meter of the power line; δ1 represents the loss rate per meter of the heating network pipeline.

[0142] Furthermore, bidirectional transmission is not allowed on the same line simultaneously; therefore, the following conditions must be met:

[0143] x t,r,j,k +x t,r,k,j ≤1;

[0144] In the formula: x t,r,j,k Indicates whether energy station j transmits electricity to energy station k at time t; x t,r,k,j Indicates whether energy station k transmits electricity to energy station j at time t; xt,r,j,k x t,r,k,j ∈{0,1};

[0145] After constructing typical modeling methods for multi-energy infrastructure, to achieve optimal system configuration and efficient operation, it is necessary to combine these models to perform overall optimization of the multi-energy system. Considering the characteristics of multi-energy systems, such as complex energy coupling relationships between equipment, uncertain renewable energy output, and dynamic changes in energy load, traditional single optimization methods are insufficient to efficiently handle such high-dimensional, nonlinear, and multi-objective integrated energy scheduling problems. Therefore, this invention proposes a data-driven, two-layer programming solution strategy. Through the synergistic integration of genetic algorithms and branch-and-bound algorithms, and based on fully considering the modeling characteristics and operational boundaries of various equipment, a unified optimization framework is constructed for capacity configuration and output scheduling problems. Specifically:

[0146] In one implementation, step 2 above, which involves solving a pre-constructed bi-level programming model using genetic algorithms and branch-and-bound algorithms based on the operational data of the multi-energy infrastructure in each energy station, and outputting the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station, may include:

[0147] Based on each energy station, the operating boundaries of the multi-energy infrastructure are set according to the operating data of the multi-energy infrastructure in the energy station;

[0148] A chromosome population is randomly generated, and each chromosome in the population is used as a set of capacity allocation schemes;

[0149] Based on the operational boundaries of multi-energy infrastructure, the chromosome population is binary-coded.

[0150] The lower-level programming model in the pre-constructed bi-level programming model is converted into a mixed-integer linear programming model, and each chromosome after binary encoding is input into the mixed-integer linear programming model.

[0151] Based on each chromosome, the branch and bound algorithm is used to solve the mixed integer linear programming model to obtain the optimal capacity configuration and optimal output scheduling of multi-energy infrastructure in each energy station.

[0152] For example, the optimal capacity configuration described above may include one or more of the following: optimal installation capacity of the equipment, transmission capacity of the lines between different equipment, and transmission path;

[0153] The optimal power output scheduling mentioned above may include one or more of the following: optimal power generation, optimal heating power, optimal cooling power, optimal energy storage status, and equipment switching status.

[0154] In this implementation, combining genetic algorithms with branch-and-bound algorithms for solving bi-level programming models not only achieves a good balance between computational performance and solution quality but also provides a more practical optimization path for the complex operational characteristics of multi-energy infrastructure in energy stations. The genetic algorithm is used for the initial global search of the capacity configuration space, efficiently exploring potential optimal solution regions in a large-scale, complex variable space; while the branch-and-bound algorithm performs a refined solution to the mixed-integer linear programming model under deterministic constraints, significantly improving the accuracy and feasibility of the solution. Technically, by inputting chromosome binary encoding into the solution process of the lower-level model, the search space and optimization model are decoupled, making the bi-level model structurally clearer and more efficient in solution. Furthermore, considering both capacity configuration and output scheduling in the optimization objective simultaneously enables integrated coordinated control from planning to operation, and improves the system's adaptability to fluctuating loads and multi-source coupling characteristics at different time scales. This effectively reduces energy redundancy configuration and operating costs, improving the system's economic efficiency and energy utilization. Furthermore, introducing a data-driven module based on dynamic demand forecasting as prior knowledge input for the genetic algorithm population initialization can further enhance the real-time responsiveness of the solution and the target adaptability of the optimization results. For example, a short-term load forecasting model can be built based on historical operating data and meteorological forecast information, thereby pre-setting a more probable configuration structure during the chromosome generation stage and reducing the cost of blind searching. Simultaneously, energy efficiency constraint response strategies can be integrated into the branch-and-bound process, enabling the model to consider the dynamic behavior of demand-side adjustable resources, such as interruptible loads and user-side energy storage responses, when executing scheduling.

[0155] Specifically, the process described above, which uses a branch-and-bound algorithm to solve a mixed-integer linear programming model based on each chromosome to obtain the optimal capacity configuration and optimal output scheduling of multi-energy infrastructure in each energy station, may include:

[0156] Based on each chromosome, the branch and bound algorithm is used to solve the mixed integer linear programming model to obtain the output scheduling scheme of the multi-energy infrastructure corresponding to the chromosome.

[0157] Calculate the energy operating costs of the multi-energy infrastructure corresponding to the chromosome based on the power output scheduling scheme of the multi-energy infrastructure corresponding to the chromosome.

[0158] The total operating cost of the multi-energy infrastructure corresponding to the chromosome is obtained by summing the energy operating cost and investment cost.

[0159] Based on the total operating cost of the multi-energy infrastructure corresponding to each chromosome, a genetic algorithm is used to obtain the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station.

[0160] In this specific implementation, capacity configuration schemes represented by chromosomes are input into a mixed-integer linear programming model. A branch-and-bound algorithm is used to accurately solve for the corresponding power dispatching strategy. The total operating cost of the chromosome-corresponding configuration is comprehensively evaluated by combining energy operating costs and investment costs. Then, a genetic algorithm is used to iteratively optimize the entire population, thereby obtaining the cost-optimal multi-energy system configuration and operating strategy. This optimization process, with its closed-loop structure of "capacity configuration—operational dispatching—cost evaluation—genetic optimization," constructs a clear feedback mechanism. This ensures that each candidate configuration scheme not only possesses engineering feasibility but also quantifies its lifecycle cost performance, thus guiding the evolution direction. By using economic efficiency as the core indicator for evaluating the fitness of the genetic algorithm, the optimization results closely align with the cost constraints of actual energy systems. Furthermore, the use of a mixed-integer linear programming model allows for precise characterization of discrete variables such as equipment start-up and shutdown, piecewise cost curves, and changes in energy storage status. This makes the dispatching results not only theoretically feasible but also directly convertible into engineering operating instructions, greatly enhancing the feasibility and practicality of the scheme. While genetic algorithms and branch-and-bound algorithms are common in their respective application domains, this invention integrates cross-level decision-making and algorithmic joint solution by introducing a closed-loop feedback mechanism based on a cost function. This breaks the traditional limitations of separating capacity optimization and operational optimization, and addressing the single optimization objective. In multi-energy coupled systems like energy stations, capacity configuration directly affects the feasibility and cost of subsequent scheduling. Optimizing these separately can easily lead to deviations from the optimal overall result. This invention, through multiple interactions between chromosomes and the scheduling model, forms a dynamic optimization structure where scheduling constraints inversely constrain capacity configuration. Furthermore, the scheduling strategy output during the branch-and-bound solution process is not a static input but is used for subsequent operational cost evaluation and fed back into the population evolution mechanism, thus constructing an evolutionary path with cost-awareness capabilities.

[0161] Specifically, the process of obtaining the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station based on the total operating cost of the multi-energy infrastructure corresponding to each chromosome, using a genetic algorithm, may include:

[0162] The reciprocal of the total operating cost of the multi-energy infrastructure corresponding to each chromosome is used as the fitness function value of the corresponding chromosome.

[0163] Based on the fitness function value of each chromosome, select the chromosomes with the highest fitness function value from the chromosome population, which constitute the top preset proportion, as elite chromosomes.

[0164] Select, crossover, and mutation operations are performed on the chromosome population to generate a new chromosome population, and the elite chromosomes and the new chromosome population are used as the next generation of chromosome population.

[0165] Get the current iteration number. If the current iteration number is greater than the preset maximum iteration number, the chromosome with the largest fitness function value in the new generation chromosome population represents the optimal capacity configuration of the multi-energy infrastructure in the energy station.

[0166] Based on the optimal capacity configuration and the lower-level planning model, the optimal output scheduling of multi-energy infrastructure is obtained;

[0167] In the above implementation, an improved genetic algorithm (with an elite retention strategy, adaptive crossover rate, and mutation rate) is introduced to solve the upper-level programming model, forming a more robust and globally convergent optimization path. The detailed solution process for the bi-level programming model based on the optimal configuration of energy stations is as follows:

[0168] 1) Solving the upper-level programming model using a genetic algorithm based on an elite retention strategy:

[0169] An improved genetic algorithm with an elite retention strategy, adaptive crossover rate, and mutation rate is used to solve the upper-level planning problem. Binary encoding is applied to encode the capacity of each device in the energy station; the encoding strategy for each chromosome is shown in the appendix. Figure 2 As shown.

[0170] In the appendix Figure 2 In this diagram, the chromosome structure of the energy station configuration (GT represents gas turbine, GS represents gas boiler, PV represents photovoltaic power generation system, AC represents absorption chiller, HP represents heat pump, EC represents electric chiller, ES represents energy storage equipment, and HS represents thermal storage equipment) is divided into 7 sub-parts, each representing the capacity of the corresponding equipment. The "2" and "3" indicate the use of 2-bit and 3-bit binary encoding, respectively. For example, for a combined heat and power turbine using 2-bit binary encoding, "00" indicates no installation, "01" indicates 1 million kW installation, "10" indicates 2 million kW installation, and "11" indicates 3 million kW installation. For example, for energy infrastructure equipment using 3-bit binary encoding, given the minimum candidate capacity R of the s-th energy infrastructure equipment in the energy station... s (e.g., 1,000,000 kilowatts), "000 to 111" increase sequentially, corresponding to installed capacities of 0 to 7R respectively. s As shown in Table 1, the numbers increase sequentially.

[0171] Table 1. Encoding of the capacity of the s-th device in the energy station.

[0172]

[0173] 2) Solving the lower-level planning model based on the branch and bound algorithm

[0174] The lower-level dynamic economic scheduling problem can be transformed into a 0-1 mixed-integer linear programming model, the standard form of which is shown in the following equation;

[0175]

[0176] In the formula: the optimization variable x may include the optimized scheduling value of each energy infrastructure equipment on a typical day, the scheduling factor, and the interaction power between the system and the distribution network; It can represent continuous variables, such as equipment output and energy transmission power; represents 0-1 variables, such as equipment start / stop status, line transmission direction, etc.; c is the objective function coefficient vector, used to represent the unit cost or benefit of each variable; T represents transpose; A0 represents the coefficient matrix of the equality constraint, used to describe the linear relationship between variables; b represents the right-hand constant vector of the equality constraint; I represents the index set of continuous variables; J represents the index set of 0-1 integer variables; x min Indicates the lower bound of a continuous variable; x max This represents the upper limit of continuous variables; among them, the equality constraints can include the energy balance of the energy system and the operating characteristics of each device, as well as the operating constraints of each device (these constraints are essentially inequality constraints, which can be transformed into the form of equality).

[0177] For the above model, this invention can consider using the branch-and-bound algorithm for solving it. The main idea of ​​this method is to first solve the adjoint program of the integer programming problem. If the optimal solution obtained does not meet the integer condition, a new constraint is added—reducing the feasible region. The original integer programming problem is then branched—divided into two subprograms, and the adjoint programs of the subprograms are solved. By solving the adjoint programs of a series of subprograms and continuously branching, the optimal solution to the original integer programming problem is finally obtained. Commonly used optimization software such as LINGO and CPLEX have built-in branch-and-bound algorithms. Taking CPLEX as an example, the process of solving the established 0-1 mixed integer programming model is as follows:

[0178] The solution steps for the bi-level programming model for optimal energy station configuration are as follows, and the process is attached. Figure 3 As shown.

[0179] 1) Input basic data such as equipment and load (i.e., operating data of energy infrastructure equipment);

[0180] 2) Perform chromosome encoding for upper-level planning and establish a general CPLEX model for lower-level planning optimization scheduling;

[0181] 3) Generate the initial population (capacity of each device) for the upper-level planning, and set the iteration number T0 = 1;

[0182] 4) For each chromosome in the upper population, determine the relevant parameters of the lower planning CPLEX general model, obtain the optimal solution, and return the result to the upper layer;

[0183] 5) Calculate the objective function for each chromosome in the upper-level population;

[0184] 6) Perform selection, crossover, and mutation genetic operations to generate a new population (i.e., a new chromosome population) for the upper-level planning;

[0185] 7) Determine if the termination condition is met. If the generation number T0 is greater than the maximum generation number, stop the calculation and output the result; otherwise, T0 = T0 + 1, go to 4).

[0186] After completing the solution process design based on the collaborative optimization of genetic algorithm and branch and bound algorithm, it is necessary to further clarify the construction details of the upper-level and lower-level planning models, which is crucial for ensuring algorithm convergence, improving computational efficiency, and model applicability. Therefore, the construction process of the upper-level capacity configuration planning model and the lower-level output scheduling optimization model can be systematically characterized from two dimensions: objective function construction and constraint setting. This provides a solid modeling foundation for the entire energy station optimization configuration problem. The overall objective of energy station configuration and inter-station network planning includes annual operating costs, which are calculated from the optimal output of equipment in a typical 24-hour period. The optimal scheduling of multiple energy flows requires the installed capacity of each piece of equipment as a prerequisite; the two are mutually constrained, and the optimal planning scheme is obtained through iterative iteration.

[0187] A two-tiered planning approach is used to integrate the planning of energy stations and inter-regional energy networks. The general model of the two-tiered planning can be represented as follows:

[0188]

[0189] In the formula: F represents the upper-level objective function; f represents the lower-level objective function; G represents the upper-level constraints; g represents the lower-level constraints; the upper-level decision variables include x and w, where x represents investment cost and w represents energy operation cost; the lower-level decision variables include x and y, where y represents the sum of operation and maintenance costs, fuel costs, electricity purchase costs, and carbon tax costs. The upper level is an investment decision problem, aiming to minimize the total annual operating cost, including investment cost and energy operation cost. The optimization variables are the installed capacity of all energy units within each energy station, the transmission capacity of various lines between energy stations, and the path. The lower level is an operation optimization problem, aiming to minimize the annual energy operation cost, including four costs: fuel, operation and maintenance, interaction with the main grid (electricity purchase), and carbon tax. The optimization variables are the optimal scheduling values ​​of all energy infrastructure equipment within the system at each time of a typical day. The results of the upper-level investment decisions affect the lower-level objective function and constraints, and the lower-level operation optimization feeds back the optimal value to the upper level, realizing the interaction between the upper and lower levels. The constraints of the planning model involve local resource endowment, relevant regulations, energy balance, and the specific operating characteristics of energy units.

[0190] Specifically, the aforementioned upper-level planning model may include the following construction process:

[0191] The total operating cost of each energy station is obtained by summing the investment cost and energy operation cost of the multi-energy infrastructure in each energy station.

[0192] To minimize the total running cost, a higher-level objective function is constructed.

[0193] Based on the upper-level objective function, formulate the upper-level constraints corresponding to the upper-level objective function;

[0194] Based on the upper-level objective function and upper-level constraints, construct an upper-level planning model;

[0195] The upper-level constraints include one or more of the following: equipment installation capacity constraints, equipment collaborative operation constraints, and reliability constraints. In this implementation, by constructing an upper-level planning model aimed at minimizing total operating costs, the economic efficiency and coordination of the capacity configuration of multi-energy infrastructure equipment in the energy station are systematically optimized. Its key technical feature lies in using total operating costs as the core indicator. This cost not only integrates the initial investment cost of the equipment but also incorporates the energy consumption costs during long-term operation, forming a unified evaluation dimension and ensuring the financial feasibility of the optimization results. Simultaneously, the equipment installation capacity constraints introduced in the upper-level planning model effectively limit equipment selection and scale, preventing exceedance of site space and resource carrying capacity; the collaborative operation constraints ensure the technical coordination of operation among various devices in the combined cooling, heating, and power system, avoiding redundant loads and resource waste during operation; and the introduction of reliability constraints ensures the operational stability and service continuity of the energy station while pursuing economic efficiency.

[0196] Specifically, the aforementioned lower-level planning model may include the following construction process:

[0197] The energy operating cost of each energy station is calculated by summing the operation and maintenance costs, fuel costs, electricity purchase costs, and carbon tax costs of the multi-energy infrastructure in each energy station.

[0198] To minimize energy operating costs, a lower-level objective function is constructed.

[0199] Based on the lower-level objective function, formulate the corresponding lower-level constraints.

[0200] Based on the lower-level objective function and lower-level constraints, construct the lower-level planning model;

[0201] The lower-level constraints can include one or more of the following: power balance constraints, output constraints, charging constraints, and discharging constraints. In this implementation, by constructing a lower-level planning model with the goal of minimizing energy operating costs, refined control and cost optimization of the operation and scheduling process of multi-energy infrastructure equipment in the energy station are achieved. The resulting technical effects are mainly reflected in two dimensions: improved operating efficiency and enhanced economics. Specifically, the key technical feature of this scheme—incorporating operation and maintenance costs, fuel costs, electricity purchase costs, and carbon tax costs into a unified cost accounting system to form a lower-level objective function—not only comprehensively reflects the economic burden throughout the entire life cycle of the energy station's operation but also specifically considers the financial impact of environmental policy factors (such as carbon taxes). This ensures that the final scheduling scheme is economically feasible while also taking into account carbon emission constraints, demonstrating good policy adaptability.

[0202] The year is divided into three typical seasons (summer, winter, and spring and autumn are considered as one season). One representative day is selected for each season. In the planning, the operating cost of the system on each typical day can be calculated first, and then multiplied by the corresponding number of days to obtain the annual operating cost.

[0203] 1) Upper-level planning model

[0204] A. Upper-level objective function

[0205] The upper-level planning model aims to minimize the total annual operating cost, which includes equipment investment costs ξ. Cap and the energy operating cost ξ in the lower-level planning model Ope ,

[0206] minF up =ξ Cap +ξ Ope ;

[0207] in,

[0208]

[0209] In the formula: F up Indicates total operating cost; C s This represents the installed capacity of the s-th energy infrastructure device in the energy station; ψ represents the unit capacity cost of the s-th energy infrastructure unit in the energy station; s Let represent the discount rate for the s-th energy infrastructure unit.

[0210] B. Upper-level constraints

[0211] For example, the allowable installation capacity limits for each energy infrastructure device in the constraints of the upper-level planning model can be expressed as follows:

[0212]

[0213] In the formula: This represents the upper limit of the allowed installation capacity of the s-th energy infrastructure device in the energy station; This represents the lower limit of the allowable installation capacity of the s-th energy infrastructure device in the energy station.

[0214] 2) Lower-level planning model

[0215] A. Lower-level objective function

[0216] The lower-level planning model aims to minimize the system's energy operating costs, including fuel costs ξ. Fuel Operation and maintenance costs ξ Om Interaction fees with the distribution network (electricity purchase fees) ξ Grid and environmental costs (carbon tax) ξ Env The expression is as follows:

[0217] minF down =ξ Ope =ξ Fuel +ξ Om +ξ Grid +ξ Env ;

[0218] in

[0219]

[0220] In the formula: F down Indicates energy operating costs; f t,s This represents the fuel consumption of the s-th energy infrastructure in the energy station at time t; σ represents the fuel price; σ0 represents the low calorific value produced by fuel combustion.

[0221]

[0222] In the formula: Let be the electrical / thermal power output of the s-th energy infrastructure in the energy station at time t; The operating and maintenance costs generated for the electrical / thermal power output of the s-th energy infrastructure device.

[0223]

[0224] In the formula: This represents the amount of electricity purchased by the energy station at time t; This represents the amount of electricity sold by the energy station at time t; This represents the time-of-use electricity price at which the energy station purchases electricity at time t. This represents the time-of-use electricity price at which the energy station sells electricity at time t.

[0225]

[0226] In the formula: E f E represents the CO2 emissions per unit of electricity produced by a combined heat and power (CHP) unit. grid η represents the CO2 emissions per unit of electricity produced by a traditional power plant. grid For power grid transmission efficiency; ω Ctax For carbon tax; f t,s This represents the fuel consumption of the s-th energy infrastructure in the energy station at time t; This represents the amount of electricity purchased by the energy station at time t.

[0227] B. Lower-level constraints

[0228] a. System power (electricity, heat, cooling) balance

[0229]

[0230] In the formula: This represents the electrical load of the energy station at time t; This represents the heat load of the energy station at time t; This represents the cooling load of the energy station at time t; This indicates the m-th time in the energy station at time t. p Output power of each power generation unit; This indicates the m-th time in the energy station at time t. h Output power of each heat-generating unit; This indicates the m-th time in the energy station at time t. c Output power of each cooling unit; This indicates the nth time in the energy station at time t. p The heat consumed by each electro-cooling conversion device; This indicates the nth time in the energy station at time t. h The electricity consumed by each heat-to-cool conversion device; P t BuyP represents the net purchased electricity at time t (i.e., the electricity purchased by the energy station at time t), which is the difference between the actual purchased electricity and the sold electricity; t dis H represents the net discharge power of the energy storage unit within the energy station at time t; t dis This represents the net heat release power of the energy storage unit within the energy station at time t; This represents the net cooling power of the energy storage unit within the energy station at time t.

[0231]

[0232] In the formula: This represents the discharge power of the energy storage unit in the energy station at time t; This represents the charging power of the energy storage unit in the energy station at time t; This represents the heat release power of the thermal storage unit in the energy station at time t; This represents the charging power of the thermal storage unit in the energy station at time t; This represents the cooling power of the cold storage unit in the energy station at time t; This represents the charging cooling power of the cold storage unit in the energy station at time t; The scheduling factors represent whether the energy storage devices in the energy station are discharging or charging at time t, respectively. A value of 1 indicates discharge, and a value of 0 indicates no discharge. (On the contrary); These represent whether the thermal storage equipment in the energy station is releasing heat or charging heat at time t, respectively. These represent whether the cold storage equipment in the energy station is releasing or charging at time t, respectively.

[0233] b. Output constraints of energy units

[0234]

[0235] In the formula: This represents the maximum load rate of the s-th energy infrastructure unit in energy station j; C represents the minimum load factor of the s-th energy infrastructure unit in energy station j; s This represents the installed capacity of the s-th energy infrastructure device in the energy station; Let be the electrical / thermal power output of the s-th energy infrastructure device in the energy station at time t.

[0236] For energy storage devices, it is also necessary to ensure the initial time t0 and the end time t of the scheduling cycle. N If the stored energy is the same, and the stored energy (state of charge) at each moment should be within a certain range, then the following conditions are met:

[0237]

[0238] In the formula: This represents the amount of electricity stored by the energy storage device at the initial time t0 of the scheduling cycle; This indicates the time t at the end of the scheduling cycle for the energy storage device. N The amount of electricity; This represents the amount of heat in the thermal storage device at the initial moment t0 of the scheduling cycle; This indicates the time t at the end of the scheduling cycle for the thermal storage equipment. N Calories; This represents the amount of cold storage equipment stored at the beginning of the scheduling cycle, t0. This indicates the time t at the end of the scheduling cycle for the cold storage equipment. N The cold storage capacity; This indicates the upper limit of the state of charge of the energy storage and cold storage equipment during operation; This indicates the lower limit of the state of charge of the energy storage device during operation; This indicates the upper limit of the state of charge of the thermal storage equipment during operation; This indicates the lower limit of the state of charge of the thermal storage equipment during operation; This indicates the upper limit of the state of charge of the cold storage equipment during operation; This indicates the lower limit of the state of charge of the cold storage equipment during operation; C ES Indicates the rated storage capacity of the energy storage device; C HS Indicates the rated heat storage capacity of the thermal storage equipment; C CS Indicates the rated cold storage capacity of the refrigeration equipment; E t H represents the actual stored capacity of the energy storage device at time t; t C represents the actual heat storage capacity of the thermal storage device at time t; t This represents the actual amount of cold storage capacity of the cold storage equipment at time t.

[0239] c. Other constraints

[0240] At any given moment, an energy storage unit is not allowed to both charge and discharge energy, satisfying the following constraint expression:

[0241]

[0242] In the formula: As the scheduling factor, Indicates whether the energy storage device in energy station j is discharging at time t; Indicates whether the energy storage equipment in energy station j is charging at time t; These represent whether the thermal storage equipment in energy station j is releasing heat or charging heat at time t, respectively. These represent whether the cold storage equipment in energy station j is releasing or charging at time t, respectively.

[0243] Considering the interconnection of various energy sources such as electricity / heat through multiple lines, gas turbines / photovoltaics / energy storage, and the joint optimization scheduling of multiple energy flows (electricity, heat, and cooling) on ​​typical days, this paper establishes an operational characteristic model for energy infrastructure and inter-regional electricity-heat networks. The objective is to minimize the total annual operating cost, comprised of five components: investment, operation and maintenance, fuel, electricity purchase, and carbon tax. Further, an integrated planning model for energy stations and inter-regional electricity-heat networks is established, defining the objective function and constraints. Finally, an efficient solution method based on a fusion of an elite-preservation strategy genetic algorithm and a branch-and-bound algorithm is proposed to achieve overall optimization of the construction capacity of various energy facilities at energy stations, the capacity of inter-station electricity-heat lines, and the output scheduling values ​​of various facilities on typical days. In this implementation, the upper-level planning model undertakes system investment and structural planning decisions, while the lower-level planning model dynamically schedules real-time output. The interaction between the two requires good coordination and division of labor between the algorithms. Traditional solutions often use only one optimization algorithm for single-layer modeling and optimization, making it difficult to ensure optimality and feasibility of the results while considering both long-term structure and short-term operational strategies. In this invention, the design of the mapping relationship between chromosome encoding and model parameters, as well as the structural change of converting the lower-level planning model into a mixed-integer linear programming, fully releases the accuracy of the branch and bound algorithm while maintaining the breadth search capability of the genetic algorithm. This results in a combination of optimization strategies that is highly engineering-adaptable, complementary in algorithms, and structurally distinct in engineering applications.

[0244] In summary, this invention addresses the problem in existing multi-energy collaborative technologies that only plan and operate individual energy stations in isolation, failing to fully consider the synergy and complementarity between multiple energy stations, thus reducing the overall energy utilization efficiency. It proposes a multi-energy collaborative and complementary energy station optimization configuration method, aiming to minimize the total operating cost of the energy station throughout its entire lifecycle. The upper-level planning model comprehensively considers the investment and operating costs of multi-energy infrastructure, constructs a capacity configuration optimization mechanism, and introduces equipment collaborative operation constraints and reliability constraints to ensure the feasibility and robustness of the system under various load scenarios. The lower-level planning model refines the operation and scheduling process of each device, constructing an operating cost model around maintenance costs, fuel costs, electricity purchase costs, and carbon tax costs. Through precise constraints on power balance, output range, and energy storage charging and discharging behavior, it achieves dynamic optimal control of the system's operational economy. At the model solution level, this invention introduces a genetic algorithm based on an elite retention strategy and adaptive operator control to efficiently solve the upper-level nonlinear combinatorial optimization problem. Simultaneously, it employs the branch and bound algorithm embedded in CPLEX to solve the lower-level 0-1 mixed integer programming problem, achieving coupled solution of upper-level configuration and lower-level scheduling through multiple rounds of interactive iteration. Furthermore, the technical approach of this invention strengthens the interconnection mechanism between multiple energy stations. Compared to traditional independent or serial optimization methods for single stations, it introduces multiple types of lines, such as electrical and thermal lines, at the physical connection level to achieve flexible exchange of energy flows across stations. At the system configuration level, it achieves unified planning for station-network collaboration, avoiding equipment redundancy and resource waste caused by phased independent design. Especially in areas where multiple energy stations have strong load complementarity and high operational coordination, this method significantly improves energy efficiency, scheduling flexibility, and economy.

[0245] Therefore, this invention effectively improves the overall energy efficiency of the energy system and reduces the overall investment cost by integrating multiple energy types, joint inter-station networks, and operational strategies through a collaborative optimization approach. Compared with traditional wireless connections, interconnecting multiple energy stations helps to leverage the complementary advantages of regional load characteristics, thereby further improving system energy efficiency. Through multiple interconnection methods for electrical and thermal lines, energy flow transmission becomes more flexible and free compared to single-line connections, significantly enhancing the system's economics. Furthermore, synchronous joint planning of energy stations and inter-station networks, compared to sequential independent planning, effectively avoids redundant equipment configuration, thereby reducing the overall annual planning cost of the system.

[0246] Example 2:

[0247] Based on the same inventive concept, this invention also provides a multi-energy synergistic and complementary energy station optimization configuration system, the structural composition of which is shown in the schematic diagram below. Figure 4 As shown, it includes:

[0248] The data acquisition module is used to acquire operational data of multi-energy infrastructure equipment in each energy station;

[0249] The model solving module is used to solve the pre-built bi-level programming model based on the operation data of the multi-energy infrastructure in each energy station, using genetic algorithms and branch and bound algorithms, and output the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station.

[0250] The optimization configuration module is used to use the optimal capacity configuration and optimal output scheduling of multi-energy infrastructure equipment in each energy station as the optimal configuration scheme among the energy stations.

[0251] The two-level programming model includes an upper-level programming model and a lower-level programming model. The upper-level programming model is constructed with the goal of minimizing the sum of investment costs and energy operating costs of multi-energy infrastructure in each energy station. The lower-level programming model is constructed with the goal of minimizing the energy operating costs of multi-energy infrastructure in each energy station.

[0252] For example, the aforementioned multi-energy infrastructure may include one or more of the following: energy production equipment, energy conversion equipment, and energy storage equipment;

[0253] The aforementioned energy production equipment may include one or more of the following: combined heat and power units, gas-fired boiler models, coal-fired boiler models, photovoltaic module models, and wind turbine output models;

[0254] The aforementioned energy storage devices may include one or more of the following: electrical storage devices, thermal storage devices, and cold storage devices;

[0255] The aforementioned operational data may include one or more of the following: equipment performance parameters, load data, and meteorological data;

[0256] In one implementation, the model solving module described above may include:

[0257] The boundary setting submodule is used to set the operating boundaries of multi-energy infrastructure based on the operating data of the multi-energy infrastructure in each energy station.

[0258] The chromosome generation submodule is used to randomly generate a chromosome population, with each chromosome in the population serving as a set of capacity configuration schemes;

[0259] The population coding submodule is used to perform binary coding of the chromosome population based on the operating boundaries of the multi-energy infrastructure.

[0260] The model transformation submodule is used to convert the lower-level programming model in the pre-built bi-level programming model into a mixed-integer linear programming model, and input each chromosome after binary encoding as an input item into the mixed-integer linear programming model;

[0261] The model output submodule is used to solve the mixed integer linear programming model based on each chromosome using the branch and bound algorithm, so as to obtain the optimal capacity configuration and optimal output scheduling of multi-energy infrastructure in each energy station.

[0262] For example, the optimal capacity configuration described above may include one or more of the following: optimal installation capacity of the equipment, transmission capacity of the lines between different equipment, and transmission path;

[0263] The aforementioned optimal power output scheduling may include one or more of the following: optimal power generation, optimal heating power, optimal cooling power, optimal energy storage status, and equipment switching status.

[0264] In this implementation, the aforementioned model output submodule may include:

[0265] The output scheduling unit is used to solve the mixed integer linear programming model based on each chromosome using the branch and bound algorithm, and obtain the output scheduling scheme of the multi-energy infrastructure corresponding to the chromosome.

[0266] The cost calculation unit is used to calculate the energy operation cost of the multi-energy infrastructure corresponding to the chromosome based on the output scheduling scheme of the multi-energy infrastructure corresponding to the chromosome.

[0267] The total cost calculation unit is used to obtain the total operating cost of the multi-energy infrastructure corresponding to the chromosome based on the sum of the energy operating cost and investment cost of the multi-energy infrastructure corresponding to the chromosome.

[0268] The scheme output unit is used to obtain the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station based on the total operating cost of the multi-energy infrastructure corresponding to each chromosome and using a genetic algorithm.

[0269] In this implementation, the above-mentioned solution output unit may include:

[0270] The fitness setting subunit is used to take the reciprocal of the total operating cost of the multi-energy infrastructure corresponding to each chromosome as the fitness function value of the corresponding chromosome.

[0271] The elite retention subunit is used to select the chromosomes with the highest fitness function values ​​from the chromosome population as elite chromosomes based on the fitness function values ​​of each chromosome.

[0272] The population generation subunit is used to perform selection, crossover, and mutation operations on the chromosome population to generate a new chromosome population, and to use the elite chromosomes and the new chromosome population as the next generation of chromosome population.

[0273] The capacity configuration subunit is used to obtain the current iteration number. If the current iteration number is greater than the preset maximum iteration number, the chromosome with the largest fitness function value in the new generation chromosome population is represented as the optimal capacity configuration of the multi-energy infrastructure in the energy station.

[0274] The output scheduling subunit is used to obtain the optimal output scheduling of multi-energy infrastructure based on the optimal capacity configuration and the lower-level planning model.

[0275] In one implementation, the aforementioned optimization configuration module may further include: an upper-level model construction module, specifically including:

[0276] The upper-level target calculation submodule is used to obtain the total operating cost of each energy station based on the sum of the investment cost and energy operation cost of the multi-energy infrastructure in each energy station;

[0277] The upper-level objective construction submodule is used to construct the upper-level objective function with the goal of minimizing the total running cost;

[0278] The upper-level constraint formulation submodule is used to formulate the upper-level constraint conditions corresponding to the upper-level objective function based on the upper-level objective function.

[0279] The upper-level model construction submodule is used to construct the upper-level planning model based on the upper-level objective function and upper-level constraints.

[0280] The upper-level constraints may include one or more of the following: equipment installation capacity constraints, equipment cooperative operation constraints, and reliability constraints.

[0281] Optionally, the optimized configuration system further includes: a lower-level model construction module, comprising:

[0282] The lower-level target calculation submodule is used to obtain the energy operation cost of each energy station based on the sum of the operation and maintenance costs, fuel costs, electricity purchase costs and carbon tax costs of the multi-energy infrastructure in each energy station;

[0283] The lower-level objective construction submodule is used to construct the lower-level objective function with the goal of minimizing energy operating costs;

[0284] The lower-level constraint formulation submodule is used to formulate the lower-level constraint conditions corresponding to the lower-level objective function based on the lower-level objective function.

[0285] The lower-level model construction submodule is used to construct the lower-level planning model based on the lower-level objective function and lower-level constraints.

[0286] The lower-level constraints may include one or more of the following: power balance constraints, output constraints, charging constraints, and discharging constraints.

[0287] Example 3:

[0288] like Figure 5 As shown, the present invention also provides an electronic device, which may be a computer device, a microcontroller device, a smart mobile device, etc. The electronic device in this embodiment may include a processor, a memory, a transceiver component, etc. The memory, processor, and transceiver component are connected via a bus; the memory can be used to store executable programs, and an exemplary executable program may include instructions; the processor is used to execute the instructions stored in the memory. The memory can also be used to store data, which can be accessed and / or modified when instructions are executed.

[0289] The processor may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and it is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in the storage medium to realize the corresponding method flow or corresponding function, so as to realize the steps of the multi-energy collaborative and complementary energy station optimization configuration method in the above embodiments.

[0290] Example 4:

[0291] Based on the same inventive concept, this invention also provides a readable storage medium, specifically an electronic device readable storage medium (Memory). This readable storage medium is a memory device within an electronic device used to store programs and data. It is understood that the storage medium here can include both the built-in storage medium within the electronic device and extended storage media supported by the electronic device. The storage medium provides storage space, which stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more executable programs (including program code). It should be noted that the storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. Loading and executing one or more instructions stored in the storage medium by the processor can implement the steps of the multi-energy collaborative and complementary energy station optimization configuration method described in the above embodiments.

[0292] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied 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.

[0293] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0294] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0295] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0296] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit its scope of protection. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that after reading the present invention, they can still make various changes, modifications or equivalent substitutions to the specific implementation methods of the application, but these changes, modifications or equivalent substitutions are all within the scope of protection of the claims pending approval.

Claims

1. A method for optimizing the configuration of energy stations through multi-energy synergy and complementarity, characterized in that, include: Acquire operational data of multi-energy infrastructure equipment in each energy station; Based on the operating data of the multi-energy infrastructure in each energy station, the pre-constructed bi-level programming model is solved using genetic algorithm and branch and bound algorithm, and the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station are output. The optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station are used as the optimal configuration scheme among the energy stations. The two-level planning model includes an upper-level planning model and a lower-level planning model. The upper-level planning model is constructed with the goal of minimizing the sum of investment costs and energy operating costs of the multi-energy infrastructure in each energy station. The lower-level planning model is constructed with the goal of minimizing the energy operating costs of the multi-energy infrastructure in each energy station.

2. The method as described in claim 1, characterized in that, The step involves solving a pre-constructed bi-level programming model using genetic algorithms and branch-and-bound algorithms based on the operational data of the multi-energy infrastructure in each energy station, and outputting the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station. This includes: Based on each energy station, and according to the operating data of the multi-energy infrastructure in the energy station, the operating boundaries of the multi-energy infrastructure are set; A chromosome population is randomly generated, and each chromosome in the population is used as a set of capacity allocation schemes; The chromosome population is binary-coded according to the operational boundaries of the multi-energy infrastructure. The lower-level programming model in the pre-constructed bi-level programming model is converted into a mixed-integer linear programming model, and each chromosome after binary encoding is input into the mixed-integer linear programming model. Based on each chromosome, the branch and bound algorithm is used to solve the mixed integer linear programming model to obtain the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station.

3. The method as described in claim 2, characterized in that, The method involves solving the mixed-integer linear programming model based on each chromosome using a branch-and-bound algorithm to obtain the optimal capacity configuration and optimal output scheduling of multi-energy infrastructure in each energy station, including: Based on each chromosome, the mixed integer linear programming model is solved using the branch and bound algorithm to obtain the output scheduling scheme of the multi-energy infrastructure corresponding to the chromosome. Calculate the energy operating cost of the multi-energy infrastructure corresponding to the chromosome based on the power output scheduling scheme of the multi-energy infrastructure corresponding to the chromosome. The total operating cost of the multi-energy infrastructure corresponding to the chromosome is obtained by summing the energy operating cost and investment cost. Based on the total operating cost of the multi-energy infrastructure corresponding to each chromosome, a genetic algorithm is used to obtain the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station.

4. The method as described in claim 3, characterized in that, Based on the total operating cost of the multi-energy infrastructure corresponding to each chromosome, a genetic algorithm is used to obtain the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station, including: The reciprocal of the total operating cost of the multi-energy infrastructure corresponding to each chromosome is used as the fitness function value of the corresponding chromosome. Based on the fitness function value of each chromosome, select the chromosomes with the highest fitness function value from the chromosome population, which constitute the top preset proportion, as elite chromosomes. The chromosome population is subjected to selection, crossover, and mutation operations to generate a new chromosome population, and the elite chromosomes and the new chromosome population are used as the next generation chromosome population; Obtain the current iteration number. If the current iteration number is greater than the preset maximum iteration number, select the chromosome with the largest fitness function value in the new generation chromosome population as the optimal capacity configuration of the multi-energy infrastructure in the energy station. Based on the optimal capacity configuration and the lower-level planning model, the optimal output scheduling of the multi-energy infrastructure is obtained.

5. The method according to any one of claims 1-4, characterized in that, The upper-level planning model includes the following construction process: The total operating cost of each energy station is obtained by summing the investment cost and energy operation cost of the multi-energy infrastructure in each energy station. To minimize the total operating cost, a higher-level objective function is constructed. Based on the aforementioned upper-level objective function, formulate the corresponding upper-level constraints for the upper-level objective function; Based on the aforementioned upper-level objective function and upper-level constraints, an upper-level planning model is constructed. The upper-level constraints include one or more of the following: equipment installation capacity constraints, equipment collaborative operation constraints, and reliability constraints.

6. The method according to any one of claims 1-4, characterized in that, The lower-level planning model includes the following construction process: The energy operating cost of each energy station is obtained by summing the operation and maintenance costs, fuel costs, electricity purchase costs, and carbon tax costs of the multi-energy infrastructure in each energy station. To minimize the energy operating costs, a lower-level objective function is constructed. Based on the lower-level objective function, formulate the lower-level constraint conditions corresponding to the lower-level objective function; Based on the lower-level objective function and the lower-level constraints, a lower-level planning model is constructed; The lower-level constraints include one or more of the following: power balance constraints, output constraints, charging constraints, and discharging constraints.

7. The method as described in claim 1, characterized in that, The multi-energy infrastructure includes one or more of the following: energy production equipment, energy conversion equipment, and energy storage equipment; The energy production equipment includes one or more of the following: combined heat and power units, gas boiler models, coal-fired boiler models, photovoltaic module models, and wind turbine output models; The energy storage device includes one or more of the following: electrical storage device, thermal storage device, and cold storage device; The operational data includes one or more of the following: equipment performance parameters, load data, and meteorological data; The energy operating costs include one or more of the following: operation and maintenance costs, fuel costs, electricity purchase costs, and carbon tax costs; The optimal capacity configuration includes one or more of the following: optimal installation capacity of equipment, transmission capacity of lines between different equipment, and transmission path; The optimal power output scheduling includes one or more of the following: optimal power generation, optimal heating power, optimal cooling power, optimal energy storage status, and equipment switching status.

8. A multi-energy synergistic and complementary energy station optimization configuration system, characterized in that, include: The data acquisition module is used to acquire operational data of multi-energy infrastructure equipment in each energy station; The model solving module is used to solve the pre-constructed bi-level programming model based on the operating data of the multi-energy infrastructure in each energy station, using genetic algorithms and branch and bound algorithms, and output the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station. The optimization configuration module is used to use the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure equipment in each energy station as the optimal configuration scheme among the energy stations. The two-level planning model includes an upper-level planning model and a lower-level planning model. The upper-level planning model is constructed with the goal of minimizing the sum of investment costs and energy operating costs of the multi-energy infrastructure in each energy station. The lower-level planning model is constructed with the goal of minimizing the energy operating costs of the multi-energy infrastructure in each energy station.

9. The system as described in claim 8, characterized in that, The model solving module includes: The boundary setting submodule is used to set the operating boundaries of the multi-energy infrastructure based on the operating data of the multi-energy infrastructure in each energy station. The chromosome generation submodule is used to randomly generate a chromosome population, with each chromosome in the population serving as a set of capacity configuration schemes; The population coding submodule is used to perform binary coding on the chromosome population based on the operating boundaries of the multi-energy infrastructure. The model conversion submodule is used to convert the lower-level programming model in the pre-built bi-level programming model into a mixed-integer linear programming model, and input each chromosome after binary encoding as an input item into the mixed-integer linear programming model; The model output submodule is used to solve the mixed integer linear programming model based on each chromosome using the branch and bound algorithm, so as to obtain the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station.

10. The system as described in claim 9, characterized in that, The model output submodule includes: The output scheduling unit is used to solve the mixed integer linear programming model based on each chromosome using a branch and bound algorithm to obtain the output scheduling scheme of the multi-energy infrastructure corresponding to the chromosome. The cost calculation unit is used to calculate the energy operation cost of the multi-energy infrastructure corresponding to the chromosome based on the output scheduling scheme of the multi-energy infrastructure corresponding to the chromosome. The total cost calculation unit is used to obtain the total operating cost of the multi-energy infrastructure corresponding to the chromosome based on the sum of the energy operating cost and investment cost of the multi-energy infrastructure corresponding to the chromosome. The scheme output unit is used to obtain the optimal capacity configuration and optimal output scheduling of the multi-energy infrastructure in each energy station based on the total operating cost of the multi-energy infrastructure corresponding to each chromosome and using a genetic algorithm.