Multi-energy collaborative micro-grid system planning operation method and system
By constructing a two-layer iterative solution model and combining genetic algorithms and deep reinforcement learning, the problem of weak coordination between upper and lower layers in microgrid system planning is solved. It achieves coverage of dynamic time-series changes throughout the year and effective handling of complex variables, thereby improving the solution efficiency and the theoretical optimality and practical adaptability of the optimization results.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ZHEJIANG HAOPU INTELLIGENT TECH CO LTD
- Filing Date
- 2026-02-09
- Publication Date
- 2026-05-19
AI Technical Summary
In existing microgrid system planning, the traditional hierarchical optimization framework has weak coordination between upper and lower layers, fails to effectively cover dynamic temporal changes throughout the year, is difficult to cope with the complex variables and constraints of multi-energy coupled microgrids, has low solution efficiency, and is difficult to balance the theoretical optimality and practical adaptability of the results.
A two-layer iterative solution model is constructed, including an upper-layer equipment capacity configuration planning module and a lower-layer energy allocation simulation optimization module. By combining genetic algorithms and deep reinforcement learning, the optimal solution for capacity configuration and operation strategy is generated, covering dynamic time-series changes throughout the year. Strict constraints are used to ensure the scientific nature and adaptability of the optimization results.
It significantly improves the solution efficiency of microgrid system planning and the theoretical optimality and practical adaptability of optimization results, ensuring the scientific nature and practical engineering applicability of capacity configuration schemes, while also being economical and environmentally friendly.
Smart Images
Figure CN122068569A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of microgrid planning technology, and in particular to a method and system for planning and operating a multi-energy coordinated microgrid system. Background Technology
[0002] Driven by the "dual carbon" goals, the global energy structure is accelerating its transformation towards cleaner and lower-carbon energy, with large-scale grid connection of distributed renewable energy sources (such as photovoltaics and wind power) becoming an important development trend. Microgrids, as a key carrier integrating distributed power sources, energy storage systems, and loads, can achieve localized consumption and efficient utilization of renewable energy, and are one of the core units for building new power systems.
[0003] In existing technologies, methods for microgrid capacity configuration and operation optimization are mainly divided into two categories: one category uses a single intelligent optimization algorithm (such as genetic algorithm or particle swarm optimization) to directly solve the joint optimization problem. This involves constructing an objective function that includes equipment investment and operating costs, and then performing a global search in conjunction with constraints such as power balance and equipment output. The other category uses a hierarchical optimization framework, which decomposes the problem into two sub-problems: upper-level capacity configuration and lower-level operation optimization. The upper level determines the equipment capacity through linear programming or intelligent algorithms, while the lower level uses mixed-integer linear programming (MILP) or simulation software to optimize the short-term operation strategy of the given capacity scheme.
[0004] However, the traditional hierarchical optimization framework suffers from weak coordination between upper and lower layers, and the operation assessment does not cover dynamic time-series changes throughout the year, affecting the scientific nature of capacity configuration schemes. The optimization methods are unable to cope with the complex variables and constraints of multi-energy coupled microgrids, and they do not effectively integrate operations research and reinforcement learning, resulting in low solution efficiency and difficulty in balancing the theoretical optimality and practical adaptability of the results. Summary of the Invention
[0005] In view of the shortcomings of the prior art, the purpose of this invention is to provide a multi-energy coordinated microgrid system planning and operation method, which can solve the technical problems of weak upper and lower layer coordination in the traditional hierarchical optimization framework, failure of operation evaluation to cover dynamic time-series changes throughout the year, affecting the scientificity of capacity configuration scheme; optimization methods are difficult to cope with the complex variables and constraints of multi-energy coupled microgrids, fail to effectively integrate operations research and reinforcement learning, and have low solution efficiency and difficulty in balancing the theoretical optimality and practical adaptability of the results.
[0006] A first aspect of this invention proposes a method for planning and operating a multi-energy coordinated microgrid system, comprising: S1: Obtain the equivalent annual comprehensive cost of a multi-energy coordinated microgrid system; S2: Construct an objective function with the goal of minimizing the comprehensive cost of equal annual value; S3: Construct a two-layer iterative solution model, which includes an upper-layer equipment capacity configuration planning module and a lower-layer energy distribution simulation and optimization module; S4: Constraints for constructing the two-level iterative solution model; S5: Under the constraints of the constraints, based on the objective function, multiple capacity configuration schemes are generated through the upper-level device capacity configuration planning module; S6: Through the lower-level energy allocation simulation and optimization module, simulate and optimize various strategy variables, and calculate the annual comprehensive cost of the capacity configuration scheme based on the simulation results; S7: Repeat S2 to S6 until the overall cost converges, and output the microgrid planning scheme with optimal capacity configuration and operation strategy. S8: Plan and operate the microgrid system according to the microgrid planning scheme.
[0007] A second aspect of this invention proposes a multi-energy coordinated microgrid system planning and operation system, comprising: a processor and a memory; The memory stores programs or instructions that can run on the processor, which, when executed by the processor, implement the steps of the multi-energy coordinated microgrid system planning and operation method as described in the first aspect.
[0008] A third aspect of the present invention provides a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the multi-energy coordinated microgrid system planning and operation method as described in the first aspect.
[0009] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: In this embodiment of the invention, by constructing a two-layer iterative solution model that integrates an upper-layer equipment capacity configuration planning module and a lower-layer energy allocation simulation optimization module, the closed-loop synergy between the upper and lower layers can be strengthened. Relying on the lower-layer energy allocation simulation optimization module, full-cycle simulation operation can be carried out on various strategy variables, which can comprehensively cover the dynamic time-series changes throughout the year. At the same time, by constructing the constraints of the two-layer iterative solution model, the complex variables and constraints of multi-energy coupled microgrids can be effectively adapted, promoting the organic integration of operations research and reinforcement learning. This not only significantly improves the solution efficiency of complex planning problems, but also ensures that the optimization results have both theoretical optimality and engineering practical adaptability. Attached Figure Description
[0010] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts. Obviously, the drawings described below are merely some embodiments of the present invention, and those skilled in the art can obtain other drawings based on these drawings without any creative effort.
[0011] Figure 1 This is a flowchart illustrating a multi-energy coordinated microgrid system planning and operation method provided in an embodiment of the present invention.
[0012] Figure 2 This is a schematic diagram of the structure of a multi-energy coordinated microgrid system planning and operation system provided in an embodiment of the present invention. Detailed Implementation
[0013] To enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. It should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0014] The following description, in conjunction with the accompanying drawings, details the multi-energy coordinated microgrid system planning and operation method provided by the present invention through specific embodiments and application scenarios.
[0015] Reference manual attached Figure 1 The diagram shows a flowchart of a multi-energy coordinated microgrid system planning and operation method provided by an embodiment of the present invention.
[0016] This invention provides a method for planning and operating a multi-energy coordinated microgrid system, which may include the following steps: S1: Obtain the equivalent annual comprehensive cost of a multi-energy coordinated microgrid system.
[0017] Specifically, the equivalent annual comprehensive cost is as follows: in, TAC Represents the annual value of comprehensive cost. C inv This represents the annualized cost of investment. C om Indicates annual maintenance cost. C op Indicates annual operating costs. C carbonThis indicates the annual environmental cost of carbon emissions.
[0018] Optionally, the multi-energy coordinated microgrid system specifically includes: a renewable energy power generation module, a biomass processing and flexible conversion module, an electrolysis hydrogen production module, a hydrogen-carbon coordinated conversion and hierarchical storage module, a flexible power generation and power supply module, and an integrated intelligent control module.
[0019] The renewable energy generation module specifically includes wind turbine generators and photovoltaic arrays, which serve as the system's zero-carbon primary energy input, with their power output directly fed into the microgrid's AC bus. The output characteristics (fluctuations and intermittency) of this module are the core input that this architecture needs to coordinate and balance.
[0020] The biomass processing and flexible conversion module specifically includes: a biomass feedstock storage unit, pretreatment equipment, a biomass gasifier, and a syngas purification system. Here, the biomass feedstock is converted into clean syngas. The syngas outlet of the gasifier is connected to the purification system, and the purified outlet is divided into two paths: one path serves as a carbon source for subsequent synthesis units; the other path leads to a backup power generation unit.
[0021] The electrolysis hydrogen production module specifically includes a water electrolyzer, a rectifier / power management device, and a purification unit. Its power input draws from the AC bus and receives commands from the intelligent control module. It activates when wind and solar power are abundant, electrolyzing water into high-purity hydrogen and oxygen. Its hydrogen outlet serves as the starting point for the system's hydrogen energy network.
[0022] The hydrogen-carbon co-conversion and staged storage module specifically includes: a gas mixing and pressurization unit, a catalytic synthesis reactor, a product separation and distillation unit, a first fuel storage tank, and a second fuel storage tank. This is the mixing point for syngas and hydrogen, and it can be stored in stages.
[0023] The flexible power generation and supply module specifically includes: a fuel cell power generation system, a dual-fuel internal combustion generator set, and a heat recovery system. The outlet of the second fuel storage tank is connected to the fuel cell for rapid and efficient conversion of hydrogen energy into electrical energy. The outlet of the first fuel storage tank is connected to the dual-fuel generator set for converting the chemical energy of synthetic fuels into electrical and thermal energy when high-power, long-term power supply is required. The power output from both is fed back to the AC bus.
[0024] The integrated intelligent control module specifically includes: a data acquisition and monitoring system, a local controller network for each subsystem, and a central controller. It connects to the sensors and actuators of all modules via a data bus, collects data in real time (such as power, flow, pressure, and inventory), and sends scheduling instructions to each module based on pre-set optimization goals and algorithms to coordinate the operation of the entire system.
[0025] It should be noted that the power output of the renewable energy power generation module is connected to the microgrid AC bus, providing zero-carbon primary energy input to the system; the syngas output of the biomass treatment and flexible conversion module is divided into two paths: one path serves as a carbon source connected to the hydrogen-carbon co-conversion and staged storage module, and the other path connects to the backup power generation unit, used to convert biomass raw materials into clean syngas; the power input of the electrolysis hydrogen production module is connected to the AC bus, and the hydrogen output is connected to the hydrogen-carbon co-conversion and staged storage module, used to electrolyze water to generate high-purity hydrogen when wind and solar power are abundant; the hydrogen-carbon co-conversion and staged storage module is used to receive syngas and hydrogen, and achieve staged storage after mixing, catalytic synthesis, separation and distillation; the fuel input of the flexible power generation and energy supply module is connected to the hydrogen-carbon co-conversion and staged storage module, and the power output is connected to the AC bus, used to convert stored hydrogen energy and synthetic fuel into electrical energy, and simultaneously recover heat energy; the integrated intelligent control module communicates with the sensors and actuators of all modules through a data bus, used to collect data in real time and send scheduling commands to coordinate the operation of the entire system.
[0026] Optionally, the equivalent annual comprehensive cost is the sum of the equivalent annual investment cost, annual maintenance cost, annual operating cost, and annual carbon emission environmental cost.
[0027] The equivalent annual investment cost is the total one-time investment amount for the initial purchase, installation and commissioning of various core equipment of the microgrid, which is allocated to the equivalent investment cost in each year according to the principle of the time value of money and the project's entire life cycle.
[0028] Among them, the annual maintenance cost is the continuous cost of maintenance, replacement of spare parts, and manual operation and maintenance incurred by the microgrid system during the annual operating cycle to ensure the stable and reliable operation of each device.
[0029] Among them, the annual operating cost is the various dynamic expenditures incurred during the 8760 hours of operation of the microgrid throughout the year, such as electricity purchase from the grid, fuel replenishment, and energy consumption of auxiliary systems, which are directly related to the operation and scheduling strategy.
[0030] The annual carbon emission environmental cost is calculated based on the microgrid's annual net carbon emissions, combined with regional carbon emission trading pricing standards or environmental regulations, reflecting the low-carbon development attributes of the plan.
[0031] S2: Construct an objective function with the goal of minimizing the annual comprehensive cost.
[0032] In this embodiment of the invention, an objective function is constructed with the goal of minimizing the equivalent annual comprehensive cost. This provides a clear and unified optimization guide for the two-layer iterative solution model. The objective function comprehensively integrates four core elements: equivalent annual investment cost, annual maintenance cost, annual operating cost, and annual carbon emission environmental cost. It covers the economic indicators of the entire life cycle of the microgrid and incorporates the requirements of low-carbon and environmentally friendly green development, avoiding the bias of unilaterally pursuing single-dimensional benefits in the optimization process. At the same time, the quantified objective function provides a precise basis for the fitness evaluation of the upper-layer genetic algorithm, enabling the cost data output by the lower-layer operation evaluation to be directly transformed into core indicators driving the iterative optimization of the scheme. This significantly improves the pertinence and efficiency of the two-layer model iterative optimization, ensuring that the final output capacity configuration scheme is both economically feasible and environmentally friendly.
[0033] S3: Construct a two-layer iterative solution model, which includes an upper-layer equipment capacity configuration planning module and a lower-layer energy distribution simulation optimization module.
[0034] It should be noted that the microgrid capacity configuration and operation co-optimization problem is a complex planning problem involving integer / continuous variables and nonlinear relationships. Traditional single optimization algorithms struggle to balance solution efficiency and optimal results. Therefore, an innovative two-layer optimization framework of "planning-operation" nesting is adopted. The core idea is to decompose the tightly coupled complex joint optimization problem into two interactive iterative sub-problems: capacity configuration optimization and operational performance evaluation, which are mutually input-output, to achieve efficient search for the global optimum. The upper layer (planning layer) takes minimizing the microgrid system's total annual cost (TAC) as its core optimization objective. A genetic algorithm is used to randomly generate multiple initial candidate capacity schemes within the feasible region of preset equipment capacity variables, including core equipment specifications such as photovoltaic array installed power and wind turbine installed power. The schemes are iteratively optimized through interactive feedback with the lower layer. The lower layer (operation layer) is responsible for conducting full-cycle operational performance evaluation and energy allocation optimization for each candidate capacity scheme passed from the upper layer. It covers 8760 hours throughout the year with hourly time steps, accurately simulating the fluctuations in wind and solar power output and the temporal changes in load demand. It optimizes the operation strategy by combining differentiated energy allocation rules: "prioritizing the allocation of surplus electricity after meeting the load during the peak season according to the priority of electrolytic hydrogen production and biomass synthetic fuel", "prioritizing the use of synthetic fuel, followed by green hydrogen, and finally biomass direct combustion" during the dry season, and "starting biomass direct combustion and fuel cell combined power supply" in extreme cases. The upper and lower layers are optimized through a closed-loop process of "upper-layer output, lower-layer evaluation, result feedback, and upper-layer iteration". Specifically, the upper-layer candidate capacity scheme serves as the hardware boundary condition for the lower layer. The lower layer uses deep reinforcement learning agent simulation to output the annual operating cost and annual carbon emission environmental cost, which are then fed back to the upper layer. The upper layer combines the equivalent annual investment cost and annual maintenance cost to calculate the TAC and uses this as a fitness index to drive the genetic algorithm to iteratively generate a new generation of schemes. This process is repeated until the TAC change is less than a preset threshold for multiple consecutive generations, reaching iterative convergence. Finally, the microgrid planning scheme with optimal capacity configuration and operation strategy is output, along with the corresponding refined annual operation strategy map.
[0035] Optionally, the upper-layer device capacity configuration planning module is specifically: a device capacity configuration module that generates and iteratively improves the configuration based on a genetic algorithm.
[0036] Among them, the genetic algorithm is an intelligent optimization algorithm that simulates the natural selection and genetic variation evolution mechanism in the biological world. It encodes the solution to the problem to be optimized as a parameter sequence similar to a biological chromosome. An initial population is formed by randomly generating initial candidate schemes. Then, based on the fitness of the preset objective function, selection operations are performed to retain high-quality schemes, crossover operations are used to recombine the advantageous features of different schemes, and mutation operations are used to introduce new parameters to expand the search space. Through multiple rounds of iterative evolution, the optimal solution is gradually selected. The algorithm uses the annual comprehensive cost of the upper-level capacity configuration scheme as the fitness evaluation index. It can efficiently handle the integer / continuous variables and nonlinear constraints involved in the capacity configuration of multi-energy coupled microgrids, avoid getting trapped in local optima, and ultimately converge to the globally optimal capacity configuration-operation strategy collaborative scheme.
[0037] The lower-level energy allocation simulation optimization module is specifically designed to optimize the energy allocation strategy for each time period by using a deep reinforcement learning agent to simulate dynamic operation throughout the year, based on the capacity scheme output from the upper layer.
[0038] Among them, the Deep Reinforcement Learning (DRL) agent is an intelligent computing module that integrates deep learning and reinforcement learning theories and has the ability to make autonomous decisions and optimize strategies. It uses the microgrid digital simulation environment as the interaction object, defines real-time operating conditions such as wind and solar power output, load demand, and energy storage status as observation states, and defines operations such as equipment start-up and shutdown, power regulation, and energy dispatch as execution actions. Through continuous interaction with the simulation environment, it accumulates experience and iteratively optimizes decision-making strategies. It can accurately realize the dynamic simulation of candidate planning operation schemes for 8760 hours throughout the year, and output the annual operating cost and annual carbon emission environmental cost that fit the actual operating conditions, providing a high-quality evaluation basis for the scheme iteration of the upper-level genetic algorithm.
[0039] In this embodiment of the invention, a two-layer iterative solution model is constructed, comprising an upper-layer genetic algorithm-based device capacity configuration planning module and a lower-layer deep reinforcement learning agent-based energy allocation simulation optimization module. This innovatively decomposes the complex joint optimization problem of microgrids, which involves integer / continuous variables and nonlinear relationships, into two interactive iterative sub-problems: capacity configuration optimization and operational performance evaluation. This effectively addresses the technical pain point of traditional single optimization algorithms, which struggle to balance solution efficiency and optimal results. The upper-layer module efficiently generates and iterates candidate capacity schemes using a "selection, crossover, and mutation" mechanism, while the lower-layer module covers 8760 hours of dynamic operating conditions throughout the year with hourly time steps. It also accurately evaluates the operational performance of the schemes by combining differentiated seasonal energy allocation rules. The upper and lower layers are deeply linked through a closed-loop collaborative mechanism of "output, evaluation, feedback, and iteration," ensuring the scientific validity and feasibility of the capacity configuration scheme while significantly improving the solution efficiency of complex planning problems. This avoids the algorithm getting trapped in local optima and ultimately outputs a microgrid planning scheme that combines economic efficiency, reliability, and environmental friendliness with a coordinated optimal capacity configuration and operation strategy.
[0040] S4: Constraints for constructing the two-layer iterative solution model.
[0041] Optionally, the constraints may specifically include: real-time power balance constraints, equipment operation constraints, energy storage dynamic constraints, and resource availability constraints.
[0042] The specific constraints for real-time power balance are as follows: in, t Indicates time, P PV This indicates the power generation capacity of the photovoltaic array. P wt This indicates the power generation capacity of the wind turbine generator set. P bio,gen This indicates the power generation capacity of biomass direct combustion / gasification. P fc This indicates the power generation capacity of the fuel cell. P gen,meoh This indicates the power generation capacity of the methanol generator. P grid,buy Indicates the power purchased. P load Indicates the power of the electrical load. P ele This indicates the power consumption of the electrolytic cell. P aux Indicates the power consumption of the auxiliary system. P grid,sell This indicates the power output.
[0043] The specific constraints on equipment operation include: output vertical constraints, ramping constraints, and minimum start / stop constraints.
[0044] Specifically, the upper and lower constraints on output are as follows: in, Indicates the first i Minimum power of each device P i Indicates the first i Instantaneous power of each device Indicates the first i The maximum power of each device.
[0045] Specifically, the climbing constraint is as follows: in, Indicates the first j The maximum downhill ramp rate of each device P j ( t)express t Time of the first j The power of each device P j ( t -1) indicates t -1 moment j The power of each device Indicates the first j The maximum uphill climbing rate of each device.
[0046] It should be noted that the minimum start-up and shutdown constraints stipulate that once the equipment completes the start-up operation and enters a stable operating state, it must continue to run for the minimum required time, during which no shutdown operation is permitted. After the equipment is shut down, it must undergo the minimum cooling or preparation time, and only after the internal temperature, pressure, and other parameters have returned to the safe start-up threshold, can it be restarted.
[0047] The specific constraints on energy storage dynamics include: hydrogen storage tank status update constraints and hydrogen storage capacity limit constraints.
[0048] Specifically, the constraints for updating the state of the hydrogen storage tank are as follows: in, SOC H2 ( t )express t The inventory level of hydrogen storage tanks at all times. SOC H2 ( t -1) indicates t The hydrogen storage tank inventory at time -1 η ch,H2 This indicates the charging efficiency of hydrogen. m H2,in This indicates the mass flow rate of the stored hydrogen gas. m H2,out This indicates the mass flow rate of hydrogen gas extracted. η dis,H2 This indicates the discharge efficiency of hydrogen gas. m H2,loss ∆ represents the natural wear rate per unit time of the hydrogen storage tank. t This indicates the time step for inventory updates.
[0049] Specifically, the hydrogen storage capacity limitation constraints are as follows: in, This indicates the safe lower limit for the inventory level of hydrogen storage tanks. C H2 This indicates the safe upper limit of the hydrogen storage tank's inventory.
[0050] The resource availability constraints specifically include: biomass upper limit constraints and grid interaction power limit constraints.
[0051] Specifically, the upper limit constraint on biomass is as follows: in, This represents the total amount of biomass raw materials consumed by the microgrid throughout the year. This indicates the maximum annual biomass resource consumption of a microgrid.
[0052] Specifically, the power grid interaction constraint is as follows: in, P grid,buy Indicates the power purchased. Indicates the maximum power purchase capacity. P grid,sell Indicates the power sold. This indicates the maximum power output.
[0053] In this embodiment of the invention, by constructing multi-dimensional constraints covering real-time power balance, equipment operation, energy storage dynamics, and resource availability, a rigorous physical boundary and engineering feasible region are established for the two-layer iterative solution model. Among them, the real-time power balance constraint ensures the power supply and demand balance of the microgrid at all times, the equipment operation constraint limits the equipment output, ramp rate, and start-stop rules to avoid fault risks, the energy storage dynamic constraint ensures the safe and efficient operation of the hydrogen storage tank, and the resource availability constraint conforms to the actual endowment of biomass feedstock and grid interaction. These quantitative and precise constraints can effectively filter invalid candidate solutions that violate engineering reality, avoid the two-layer model from getting stuck in the infeasible region search during the iteration process, greatly improve the solution efficiency and stability, and at the same time ensure that the final output microgrid capacity configuration scheme has technical compliance, operational safety, and practical feasibility.
[0054] S5: Under the constraints of the constraints, based on the objective function, multiple capacity configuration schemes are generated through the upper-level device capacity configuration planning module.
[0055] Optionally, the capacity configuration scheme may specifically include: annual investment cost, annual maintenance cost, equipment capacity variables, and strategy variables.
[0056] The specific equipment capacity variables include: photovoltaic installed capacity, wind turbine installed capacity, electrolyzer rated power, hydrogen storage tank capacity, synthesis reactor capacity, synthetic fuel storage tank volume, fuel cell, and generator rated power.
[0057] The specific strategy variables include: the output sequence of each device throughout the year and the start-stop status sequence of each device throughout the year.
[0058] In this embodiment of the invention, under the rigid constraints of multi-dimensional conditions and guided by the objective function of minimizing the equivalent annual comprehensive cost, a capacity configuration scheme is generated based on the upper-level equipment capacity configuration planning module. The scheme not only covers economic indicators such as equivalent annual investment cost and annual maintenance cost, but also clarifies core equipment capacity variables such as photovoltaic installed capacity and hydrogen storage tank capacity, as well as strategy variables such as annual equipment output sequence and start-stop state sequence. This ensures that all candidate schemes meet the physical boundaries and engineering requirements of microgrid operation, effectively filters out invalid schemes, and provides diverse candidate samples. This provides a sufficient and high-quality foundation for the full-cycle performance evaluation and subsequent iterative optimization of the lower-level energy distribution simulation optimization module, significantly improving the optimization efficiency of the two-layer iterative solution model and the scientific nature of the final scheme.
[0059] In one possible implementation, after S5 and before S6, the following is also included: Construct a digital simulation environment for microgrids.
[0060] Among them, the microgrid digital simulation environment is a digital virtual operation carrier built based on the actual physical characteristics and operation rules of multi-energy coupled microgrids. It integrates parameter models of core equipment such as photovoltaics, wind turbines, hydrogen storage tanks, and fuel cells, replicates dynamic operating conditions such as wind and solar power output fluctuations and load demand changes throughout the year for 8760 hours, and embeds constraints such as real-time power balance, equipment operation, and energy storage dynamics. As an interaction platform for the lower-level deep reinforcement learning agent, it provides the agent with a closed-loop scenario of observation state input and execution action feedback. It supports the agent to continuously interact with the environment to iteratively optimize the scheduling strategy, and can also combine mixed integer linear programming algorithms to complete the initial strategy optimization of the agent, thereby realizing the upper-level candidate planning.
[0061] Define the initial observation state and initial execution actions of the lower-level energy distribution simulation optimization module in the microgrid digital simulation environment.
[0062] Based on the initial observation state and initial execution actions, the lower-level energy allocation simulation optimization module is optimized using a mixed-integer linear programming algorithm.
[0063] Among them, the Mixed Integer Linear Programming (MILP) algorithm is a mathematical optimization method that integrates continuous and integer variable solutions. It can handle linear programming problems that simultaneously include continuous decision parameters (such as equipment output) and discrete decision variables (such as equipment start-up and shutdown states, and unit combination schemes). Under the premise of satisfying linear constraints, it optimizes a preset linear objective function and quickly outputs the global optimal solution or a near-optimal solution. The algorithm is used to optimize the initial observation state and execution actions of the lower-level deep reinforcement learning agent in a microgrid digital simulation environment. It helps the agent quickly establish an initial decision strategy that conforms to engineering practice, effectively solving the problems of low efficiency and slow convergence when learning from scratch, and improving the accuracy and stability of the simulation evaluation of upper-level candidate planning operation schemes.
[0064] In this embodiment of the invention, a high-fidelity operation evaluation scenario is built for the lower-level energy allocation simulation optimization module, clarifying the input boundaries and action range of intelligent decision-making. At the same time, by leveraging the theoretical advantages of mixed-integer linear programming algorithms, the lower-level module can quickly grasp the basic optimization rules of microgrid operation, effectively solving the pain points of low efficiency and slow convergence when learning from scratch. This significantly improves the accuracy and efficiency of subsequent full-cycle evaluation of upper-level capacity configuration schemes, providing high-quality data support for the stable optimization of the two-level iterative solution model.
[0065] S6: Through the lower-level energy allocation simulation and optimization module, simulate and optimize various strategy variables, and calculate the annual comprehensive cost of the capacity configuration scheme based on the simulation results.
[0066] In one possible implementation, S6 specifically includes: S601: Through the lower-level energy allocation simulation and optimization module, various strategy variables are simulated and optimized to obtain the annual operating cost and annual carbon emission environmental cost of the capacity configuration scheme.
[0067] S602: Based on the annual investment cost, annual maintenance cost, annual operating cost, and annual carbon emission environmental cost of each capacity configuration scheme, the equivalent annual comprehensive cost of the capacity configuration scheme is calculated by summing.
[0068] In this embodiment of the invention, the lower-level energy allocation simulation optimization module performs full-cycle simulation of each strategy variable, accurately outputting annual operating costs and annual carbon emission environmental costs that conform to actual operating conditions. This is then combined with the equivalent annual investment cost and annual maintenance cost provided by the scheme to perform a summation calculation, yielding a complete equivalent annual comprehensive cost. This not only achieves a quantitative assessment of the economic and environmental performance of candidate schemes but also provides precise fitness criteria for the selection, crossover, and variation operations of the upper-level equipment capacity configuration planning module. It effectively filters out non-optimal schemes, improves the optimization efficiency of the two-layer iterative solution model, and ensures that the final microgrid planning scheme is both economical and low-carbon.
[0069] S7: Repeat S2 to S6 until the maximum number of iterations is reached and the comprehensive cost converges, and output the optimal capacity configuration-operation strategy co-optimal microgrid planning capacity configuration planning operation scheme.
[0070] In this embodiment of the invention, multiple rounds of closed-loop iteration allow the upper-level device capacity configuration planning module to continuously optimize candidate schemes, while the lower-level simulation module accurately provides feedback on the evaluation results. This process continuously filters out non-optimal schemes and iterates to upgrade high-quality schemes, effectively preventing the algorithm from getting stuck in local optima and fully exploring the global optimal solution. At the same time, using the maximum number of iterations as the termination condition balances the optimization effect and solution efficiency, ensuring that the final output capacity configuration scheme is fully verified and combines economy, low carbon emissions, and engineering feasibility, providing reliable support for the scientific planning of microgrids.
[0071] S8: Based on the optimal planning and operation scheme of the microgrid planning, the microgrid system is planned and operated.
[0072] Reference manual attached Figure 2 The diagram shows a structural schematic of a multi-energy coordinated microgrid system planning and operation system provided by an embodiment of the present invention.
[0073] This invention provides a multi-energy coordinated microgrid system planning and operation system 20, including: a processor 201 and a memory 202; The memory 202 stores programs or instructions that can run on the processor 201. When the program or instructions are executed by the processor 201, they implement the steps of the above-described multi-energy coordinated microgrid system planning and operation method and achieve the same technical effect. To avoid repetition, the present invention will not elaborate further.
[0074] It should be understood that the processor 201 in this embodiment of the invention 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. The general-purpose processor may be a microprocessor or any conventional processor.
[0075] It should also be understood that the memory 202 in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DR RAM).
[0076] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.
[0077] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0078] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.
[0079] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0080] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.
[0081] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0082] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0083] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0084] This invention provides a readable storage medium comprising: storing a program or instructions on the readable storage medium, wherein when the program or instructions are executed by a processor, the program or instructions implement the steps of the above-described multi-energy coordinated microgrid system planning and operation method, and can achieve the same technical effect. To avoid repetition, this invention will not elaborate further.
[0085] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the protection scope of the present invention.
Claims
1. A method for planning and operating a multi-energy coordinated microgrid system, characterized in that, include: S1: Obtain the equivalent annual comprehensive cost of a multi-energy coordinated microgrid system; S2: Construct an objective function with the goal of minimizing the comprehensive cost of the equivalent annual value; S3: Construct a two-layer iterative solution model, which includes an upper-layer equipment capacity configuration planning module and a lower-layer energy allocation simulation optimization module; S4: Construct the constraints for the two-layer iterative solution model; S5: Under the constraints of the above constraints, based on the objective function, multiple capacity configuration schemes are generated through the upper-layer device capacity configuration planning module; S6: Through the lower-level energy allocation simulation and optimization module, simulate and optimize each strategy variable, and calculate the equivalent annual comprehensive cost of the capacity configuration scheme based on the simulation results; S7: Repeat S2 to S6 until the overall cost converges, and output the microgrid planning scheme with optimal capacity configuration and operation strategy. S8: Plan and operate the microgrid system according to the microgrid planning scheme.
2. The multi-energy coordinated microgrid system planning and operation method according to claim 1, characterized in that, The multi-energy coordinated microgrid system specifically includes: a renewable energy power generation module, a biomass processing and flexible conversion module, an electrolysis hydrogen production module, a hydrogen-carbon coordinated conversion and hierarchical storage module, a flexible power generation and power supply module, and an integrated intelligent control module.
3. The multi-energy coordinated microgrid system planning and operation method according to claim 1, characterized in that, The equivalent annual comprehensive cost is specifically the sum of the equivalent annual investment cost, annual maintenance cost, annual operating cost, and annual carbon emission environmental cost.
4. The multi-energy coordinated microgrid system planning and operation method according to claim 1, characterized in that, The upper-layer device capacity configuration planning module is specifically a device capacity configuration module that generates and iteratively improves the device capacity configuration based on a genetic algorithm. The lower-level energy allocation simulation and optimization module specifically works by using a deep reinforcement learning agent to simulate dynamic operation throughout the year, based on the capacity scheme output from the upper layer, and optimizing the energy allocation strategy for each time period.
5. The method for planning and operating a multi-energy coordinated microgrid system according to claim 1, characterized in that, The constraints specifically include: real-time power balance constraints, equipment operation constraints, energy storage dynamic constraints, and resource availability constraints. The specific constraints on equipment operation include: output vertical constraints, ramping constraints, and minimum start / stop constraints. The specific dynamic constraints on energy storage include: hydrogen storage tank status update constraints and hydrogen storage capacity limit constraints. The resource availability constraints specifically include: biomass upper limit constraints and grid interaction power limit constraints.
6. The multi-energy coordinated microgrid system planning and operation method according to claim 1, characterized in that, The capacity configuration scheme specifically includes: annual investment cost, annual maintenance cost, equipment capacity variables, and strategy variables; The specific equipment capacity variables include: photovoltaic installed power, wind turbine installed power, electrolyzer rated power, hydrogen storage tank capacity, synthesis reactor capacity, synthetic fuel storage tank volume, fuel cell, and generator rated power. The specific strategy variables include: the output sequence of each device throughout the year and the start / stop status sequence of each device throughout the year.
7. The multi-energy coordinated microgrid system planning and operation method according to claim 1, characterized in that, After S5 and before S6, it also includes: Constructing a digital simulation environment for microgrids; Define the initial observation state and initial execution action of the lower-level energy distribution simulation optimization module in the microgrid digital simulation environment; Based on the initial observation state and the initial execution action, the lower-level energy allocation simulation optimization module is optimized using a mixed-integer linear programming algorithm.
8. The multi-energy coordinated microgrid system planning and operation method according to claim 6, characterized in that, S6 specifically includes: S601: Through the lower-level energy allocation simulation and optimization module, simulate and optimize each of the strategy variables to obtain the annual operating cost and annual carbon emission environmental cost of the capacity configuration scheme; S602: Based on the annual investment cost, annual maintenance cost, annual operating cost, and annual carbon emission environmental cost of each capacity configuration scheme, the equivalent annual comprehensive cost of the capacity configuration scheme is calculated by summing.
9. A multi-energy coordinated microgrid system planning and operation system, characterized in that, include: Processor and memory; The memory stores programs or instructions that can be executed on the processor, which, when executed by the processor, implement the steps of the multi-energy coordinated microgrid system planning and operation method as described in any one of claims 1 to 8.
10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the multi-energy coordinated microgrid system planning and operation method as described in any one of claims 1 to 8.