Micro-grid scheduling strategy generation method, device, equipment, medium and product

Abstract

The invention discloses a micro-grid scheduling strategy generation method and device, equipment, a medium and a product, and belongs to the technical field of micro-grid scheduling. The method comprises the following steps: constructing a micro-grid optimization scheduling physical model, wherein the micro-grid optimization scheduling physical model at least comprises a flexible load response model; based on the flexible load response model, establishing a multi-objective optimization function including a power supply reliability objective and an operation cost objective; system operation constraint conditions of the multi-objective optimization function are set, and the system operation constraint conditions at least comprise distributed power supply output constraints; and carrying out optimization solution on the multi-objective optimization function by adopting an optimization algorithm to obtain a micro-grid scheduling strategy, and carrying out cooperative control on various resources in the micro-grid based on the micro-grid scheduling strategy. According to the micro-grid scheduling strategy generated by the embodiment of the invention, the efficiency and robustness of micro-grid scheduling can be effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of micro-grid scheduling, and in particular to a micro-grid scheduling strategy generation method, device, equipment, medium and product. BACKGROUND

[0002] A micro-grid is a small source-grid-load-storage system that combines distributed energy, load and energy storage devices. With the transformation of energy structure to green, the strong randomness of wind power and photovoltaic and the grid connection of diversified flexible load make the power balance change from simple supply-demand matching to a complex system problem that needs to integrate source-grid-load-storage vehicles and multi-energy coupling and other multi-dimensional elements. Under this background, the optimal operation of the micro-grid is crucial, but the existing methods often have limited scheduling efficiency and insufficient robustness when dealing with high proportion of new energy access. SUMMARY

[0003] The purpose of the embodiments of the present application is to provide a micro-grid scheduling strategy generation method, device, equipment, medium and product, which can effectively improve the efficiency and robustness of micro-grid scheduling.

[0004] To achieve the above-mentioned purpose, the first aspect of the embodiments of the present application provides a micro-grid scheduling strategy generation method, comprising: constructing a micro-grid optimal scheduling physical model, the micro-grid optimal scheduling physical model at least including a flexible load response model; based on the flexible load response model, establishing a multi-objective optimization function including power supply reliability target and operation cost target; setting system operation constraint conditions of the multi-objective optimization function, wherein the system operation constraint conditions at least include distributed power output constraints; using an optimization algorithm to optimize and solve the multi-objective optimization function, obtaining a micro-grid scheduling strategy, and performing coordinated control on multiple resources in the micro-grid based on the micro-grid scheduling strategy.

[0005] Compared with the prior art, the micro-grid scheduling strategy generation method provided by the embodiment of the application has the beneficial effects that: by constructing a micro-grid optimization scheduling physical model integrated with a flexible load response model, unified modeling and collaborative characterization of source-load-storage multi-element resources are realized; on this basis, a multi-objective optimization function including power supply reliability and operation cost targets is established, and by setting system operation constraint conditions including distributed power output constraints, the safety boundary and uncertainty influence of system operation are accurately described; finally, an optimization algorithm is used for parallel solving, the calculation efficiency and convergence speed in a complex scenario are significantly improved by comparing the performance of multiple optimization algorithms, and the micro-grid scheduling strategy is obtained, which effectively enhances the adaptability of the system to new energy fluctuations and load changes while ensuring the economy of the scheduling scheme, and simultaneously improves the efficiency and robustness of the micro-grid scheduling.

[0006] In some embodiments, the process of constructing the flexible load response model comprises: Based on the response state and response power of the user, the total response output of the load aggregator in a unit time is calculated; According to the unit incentive price, the expenditure cost of the load aggregator generated by scheduling is calculated.

[0007] In some embodiments, the optimization algorithm is at least one of a particle swarm optimization algorithm, a genetic algorithm, an ant colony algorithm, and a deep reinforcement learning algorithm.

[0008] In some embodiments, based on the flexible load response model, the multi-objective optimization function including the power supply reliability target and the operation cost target is established, comprising: Based on the flexible load response model, a power supply reliability target of minimizing the load fluctuation rate of the distribution network is constructed; Based on the flexible load response model and the operation cost of the energy storage system, a system operation cost target of minimizing the system scheduling cost and power loss cost is constructed.

[0009] In some embodiments, the system operation constraint condition of the multi-objective optimization function comprises: The upper and lower limit constraints for the actual output power of the distributed power source are set, and the upper and lower limits are determined based on the day-ahead predicted output value and combined with the preset prediction error tolerance.

[0010] In some embodiments, the optimization algorithm is used to optimize and solve the multi-objective optimization function to obtain a micro-grid scheduling strategy, comprising: An active distribution network simulation model integrated with a distributed power source and an energy storage system is constructed based on a standard distribution node system; A plurality of scheduling scenarios are set, including at least a fixed load scheduling scenario without energy storage participation, a real-time scheduling only scenario, and a scenario combining day-ahead optimization and real-time optimization; In the active power distribution network simulation model and different scheduling scenarios, the optimization algorithm is applied to solve the multi-objective optimization function, and a micro-grid scheduling strategy is obtained.

[0011] To achieve the above-mentioned purpose, a second aspect of the embodiment of the present application provides a micro-grid scheduling strategy generation device, the device comprises: The construction module is configured to construct a micro-grid optimization scheduling physical model, the micro-grid optimization scheduling physical model at least includes a flexible load response model; The establishment module is configured to establish a multi-objective optimization function containing power supply reliability target and operation cost target based on the flexible load response model; The constraint module is configured to set the system operation constraint condition of the multi-objective optimization function, wherein the system operation constraint condition at least includes a distributed power output constraint; The solving module is configured to adopt an optimization algorithm to optimize and solve the multi-objective optimization function, and obtain a micro-grid scheduling strategy, so as to cooperatively control a plurality of resources in the micro-grid based on the micro-grid scheduling strategy.

[0012] To achieve the above-mentioned purpose, a third aspect of the embodiment of the present application provides an electronic device, the electronic device comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, and the processor executes the computer program to realize the method of the first aspect.

[0013] To achieve the above-mentioned purpose, a fourth aspect of the embodiment of the present application provides a computer readable storage medium, the computer readable storage medium comprises a stored computer program, wherein when the computer program runs, the computer readable storage medium controls the device where the computer readable storage medium is located to execute the method of the first aspect.

[0014] To achieve the above-mentioned purpose, a fifth aspect of the embodiment of the present application provides a computer program product, the computer program product comprises a computer program or computer instructions, and the computer program or the computer instructions are executed by the processor to realize the method of the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 is a flow chart of the micro-grid scheduling strategy generation method provided by the embodiment of the present application; Figure 2 is a structural schematic diagram of the active power distribution network simulation model provided by the embodiment of the present application; Figure 3 is a schematic diagram of actual output power of a photovoltaic system and load predicted output power; Figure 4 is a schematic diagram of actual output power of a wind turbine and load predicted output power; Figure 5 is a schematic diagram of intraday charging and discharging power and SoC of an energy storage system at different time periods; Figure 6 is a structural schematic diagram of a micro-grid scheduling strategy generation device provided by an embodiment of the present application; Figure 7 is a hardware structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0017] In the description of the present application, it should be understood that the terms "center", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship shown in the drawings, and are only for the purpose of facilitating the description of the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application.

[0018] The terms "first", "second" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0019] In the description of the present application, it should be noted that unless otherwise specified and limited, the terms "mounting", "connection", "connection" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium; it can be the communication inside two elements. For those of ordinary skill in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0020] Against the backdrop of global energy transition and green, low-carbon development, the large-scale integration of new energy sources such as wind power and solar power is profoundly changing the operational foundation of traditional power systems. Their inherent randomness, intermittency, and uncertainty, coupled with the widespread adoption of new flexible loads such as electric vehicles and combined cooling, heating, and power (CCHP) systems, have transformed power balance from a simple "source follows load" model to a complex systems engineering project requiring the coordinated management of "source-grid-load-storage-vehicle" and multi-energy coupling. To address this challenge, three main technical approaches have emerged: hierarchical control, multi-resource collaborative scheduling, and predictive-driven optimization.

[0021] However, these existing technologies all exhibit significant limitations when dealing with high-dimensional complexity. While hierarchical control technology adapts to response requirements at different time scales through its hierarchical architecture, its cross-layer information coordination faces bottlenecks and insufficient adaptation to specific equipment characteristics such as energy storage lifetime and load latency, making it difficult to dynamically connect real-time control with long-term strategies. Multi-resource collaborative scheduling technology, when constructing economic optimization models, often oversimplifies key characteristics such as the spatiotemporal differences in wind and solar power output and the full lifecycle constraints of energy storage systems, resulting in significant deviations between the model and actual operation and insufficient robustness. Prediction-driven optimization technology faces the dilemma of a sharp drop in prediction accuracy under extreme scenarios, and existing error correction methods are unable to effectively suppress the cumulative effect of prediction deviations on scheduling timing, ultimately leading to the failure of optimization strategies.

[0022] In summary, existing methodologies face severe challenges in terms of collaborative efficiency, model accuracy, and operational robustness when dealing with complex systems composed of a high proportion of new energy sources and diversified loads because they fail to systematically integrate resource characteristics, cross-layer collaboration, and uncertainty management.

[0023] Based on this, embodiments of this application provide a microgrid scheduling strategy generation method, apparatus, equipment, medium, and product, the generated microgrid scheduling strategy can effectively improve the efficiency and robustness of microgrid scheduling.

[0024] Please see Figure 1 , Figure 1 This is an optional flowchart of the microgrid scheduling strategy generation method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S104.

[0025] Step S101: Construct a physical model for microgrid optimization scheduling. The physical model for microgrid optimization scheduling shall include at least a flexible load response model. Step S102: Based on the flexible load response model, establish a multi-objective optimization function that includes power supply reliability and operating cost objectives; Step S103: Set system operation constraints for the multi-objective optimization function, wherein the system operation constraints include at least distributed power source output constraints; Step S104: The multi-objective optimization function is optimized and solved using an optimization algorithm to obtain the microgrid scheduling strategy, so as to coordinate the control of multiple resources in the microgrid based on the microgrid scheduling strategy.

[0026] Steps S101 to S104 of this application embodiment demonstrate that a unified modeling and collaborative representation of multiple resources—source, load, and storage—is achieved by constructing a microgrid optimized scheduling physical model that integrates a flexible load response model. Based on this, a multi-objective optimization function including power supply reliability and operating cost objectives is established. Furthermore, by setting system operation constraints, including distributed power source output constraints, the safety boundary and uncertainty impact of system operation are accurately characterized. Finally, parallel solutions are obtained using optimization algorithms. By comparing the performance of multiple optimization algorithms, the computational efficiency and convergence speed under complex scenarios are significantly improved, resulting in a microgrid scheduling strategy. This strategy ensures the economy of the scheduling scheme while effectively enhancing the system's adaptability to new energy fluctuations and load changes, simultaneously improving the efficiency and robustness of microgrid scheduling.

[0027] In step S101 of some embodiments, the microgrid optimal scheduling physical model can be a basic model that characterizes the characteristics and interactions of distributed power sources such as wind power and photovoltaics, energy storage systems, and various loads within the microgrid, supporting the calculation of scheduling strategies. In a preferred embodiment, the microgrid optimal scheduling physical model can establish a unified modeling framework based on the randomness of wind power and photovoltaics, the charging and discharging dynamics of energy storage devices, the flexible response potential of electric vehicle groups, and the multi-energy complementarity characteristics of combined cooling, heating, and power systems. The flexible load response model can be a model that describes the response patterns of flexible loads such as electric vehicles and adjustable industrial loads as electricity prices or scheduling commands change, reflecting their adjustable characteristics.

[0028] In some embodiments, the process of constructing a flexible load response model includes: Based on the user's response status and response power, calculate the total response output of the load aggregator per unit time. Calculate the expenditure costs incurred by the load aggregator due to scheduling, based on the unit incentive price.

[0029] Specifically, the inputs to the flexible load response model include: user response state, a discrete variable used to characterize the user's load adjustment direction at a specific moment (increase is 1, decrease is -1, no participation is 0); user response power, which refers to the actual change in electrical power by the user in this state; and unit incentive price, representing the unit compensation cost paid by the load aggregator to the user according to the contract.

[0030] Based on the above parameters, firstly, the total response output is calculated, which involves algebraically summing the response power of all participating users according to their response states. This quantifies the total load adjustment that the load aggregator can provide during the scheduling period. Calculating the response output per unit time in a load aggregation group managed by the load aggregator is a complex process. It involves quantifying, coordinating, and optimizing the response potential of all participating users. The total response output of the load aggregator per unit time... It can be expressed by the following formula (1):

[0031] in, Indicates user At any moment The response status is 1 when the load increases, -1 when the load decreases, and 0 when not participating in scheduling; This represents the total number of users who can participate in demand response. Indicates user At any moment The response power.

[0032] Secondly, the scheduling expenditure cost is calculated by multiplying the total response output by the corresponding unit incentive price to determine the total economic expenditure incurred by the load aggregator in calling up these flexible resources. Since different load types have different activation costs, the load aggregator needs to calculate the scheduling cost based on the scheduling contract. The load aggregator's expenditure cost during this period can be expressed by the following formula (2):

[0033] in, For load aggregator scheduling costs; Indicates user At any moment The response status is 1 when the load increases, -1 when the load decreases, and 0 when not participating in scheduling; Indicates user At any moment The response power; This represents the incentive price (RMB / MW) for user I to participate in scheduling per unit of time.

[0034] This model refines user behavior by defining response states and response power, then uses aggregated calculations to obtain system-level controllable potential, and finally transforms physical adjustment capabilities into economic signals through cost correlation. This modeling process transforms dispersed, heterogeneous user-side flexible loads into a standardized "virtual resource" that can be directly invoked by the scheduling system and has a clearly defined cost, thus providing a precise demand-side control basis for subsequent multi-objective optimization and laying the foundation for collaborative optimization.

[0035] In step S102 of some embodiments, the multi-objective optimization function can be a mathematical expression that integrates multiple scheduling objectives and quantifies the relationship between objective priorities and constraints. The power supply reliability objective can be the objective of ensuring continuous power supply to the microgrid and avoiding power shortages, such as reducing outage duration and lowering the power shortage rate. The operating cost objective can be the objective of reducing costs related to power generation, energy storage charging and discharging, and load regulation during microgrid operation.

[0036] In some embodiments, based on a flexible load response model, a multi-objective optimization function is established that includes power supply reliability and operating cost objectives, including: Based on the flexible load response model, a power supply reliability target that minimizes the load fluctuation rate of the distribution network is constructed. Based on the flexible load response model and the operating cost of energy storage systems, a system operation cost target that minimizes system scheduling costs and power loss costs is constructed.

[0037] Specifically, based on the established flexible load response model, this application establishes a multi-objective optimization function that balances power supply reliability and economy. The construction process is as follows: First, a power supply reliability objective is constructed. Power supply reliability is not only related to the ability to continuously supply power, but also involves flexible response to load changes. At the distribution network level, this objective focuses on the stability of the comprehensive load curve, aiming to minimize the load fluctuation rate of the distribution network, and to comprehensively evaluate it by analyzing the degree and frequency of load fluctuation. Its quantification is based on three key operating parameters: daily maximum load power, daily minimum load power, and daily average load. The power supply reliability objective can be expressed by the following formula (3):

[0038] in, and These represent the daily maximum load power and daily minimum load power of the distribution network, respectively. This represents the average daily charge of the distribution network; This represents the time value of the load in the distribution network at time t. This represents the time value of the load in the distribution network at time t+1. and It is the weighting coefficient of the two evaluation indicators. Since load fluctuation has a greater impact on distribution network reliability, in a preferred embodiment, this application sets... , .

[0039] This application comprehensively assesses the stability of the load curve by calculating the ratio of peak-to-valley difference to average load and introducing the time value of load as a correction factor in the time dimension. Two weighting coefficients are used to adjust the weight of fluctuation amplitude and time distribution on reliability. Integrating the above parameters, a mathematical function is constructed with minimizing load fluctuation rate as its core. This function quantifies the flatness of the load curve, transforming the qualitative objective of "improving power supply reliability" into a specific mathematical indicator that can be directly processed by optimization algorithms.

[0040] Secondly, a system operation cost target is constructed, which focuses on the economic efficiency of system operation. Its cost composition mainly includes: energy storage system dispatch cost (based on the unit charge and discharge cost of energy storage equipment), grid power loss cost, and the economic benefits and subsidy income obtained by the energy storage system through the "low charge and high discharge" strategy. The goal is to minimize the operation cost of distribution network dispatch, including minimizing the costs related to optimizing the integration with the energy storage system and flexibly involving loads in distribution regulation, while ensuring that power loss in the grid is minimized. The system operation cost target can be expressed by the following formula (4):

[0041]

[0042]

[0043] in, The dispatch cost of the energy storage system is determined by the unit energy consumption cost. With the absolute value of charging and discharging power Joint decision, The benchmark is based on the energy cost of a typical lithium-ion battery in 2024, which is approximately per kilowatt-hour. ; The economic benefits achieved by the energy storage device using a "low-cost storage, high-cost release" strategy during charging and discharging, as well as any additional subsidy income; The scheduling cost for load aggregators stems from the expenditure on flexible load response models; Cost of power loss in the power grid; For error; This represents the absolute value of active power. , All are constants.

[0044] This objective function deeply integrates the scheduling cost of the flexible load response model, the full-cycle operational economy of the energy storage system, and the inherent losses of the power grid. By accurately calculating the costs and benefits of energy storage charging and discharging, and optimizing them in conjunction with demand-side resource costs, the scheduling strategy can ultimately significantly improve the overall economic efficiency of microgrid operation and minimize net expenditures while meeting system operational constraints.

[0045] Through the above steps, this application deeply integrates the output of the flexible load response model (i.e., adjustable load and its cost) with the inherent operating characteristics of the power grid (load fluctuations, network losses) and the economic characteristics of energy storage, constructing power supply reliability and operating cost objectives. These two objective functions together constitute a multi-objective optimization function, enabling subsequent scheduling strategies to accurately calculate and minimize the total system operating cost while smoothing load fluctuations and improving power supply quality, providing a clear optimization guide for achieving economical and reliable operation of microgrids.

[0046] In step S103 of some embodiments, the system operation constraints can be boundary conditions to ensure the safe and stable operation of the microgrid, limiting the operating range of various resources. Distributed power output constraints can be constraints that limit the output power range of wind power and photovoltaic power.

[0047] In some embodiments, system operation constraints for the multi-objective optimization function are set, including: Upper and lower limits are set for the actual output power of distributed power sources. The upper and lower limits are determined based on their day-ahead predicted output values ​​and in combination with a preset prediction error tolerance.

[0048] Specifically, for distributed power sources, the output constraints are set as follows:

[0049] in, For distributed power source output constraints; This represents the prediction error coefficient for wind and solar power output. , This represents the maximum output value of the distributed power source. The closer the forecast is to 0, the more accurate the wind and solar energy output predictions will be. This represents the day-ahead forecast value of the distributed power source output.

[0050] This constraint aims to limit the actual output range of distributed power sources. Its setting relies on three key parameters: the day-ahead predicted output value, serving as the output benchmark; the prediction error coefficient, used to quantify the uncertainty of wind and solar power output; and the resulting upper limit of output power, serving as the boundary condition for decision variables in the optimization model. By integrating the prediction benchmark and the uncertainty coefficient, and scaling the day-ahead predicted value according to a preset error tolerance, the upper and lower limits of output power for each scheduling period are dynamically determined. This operation transforms the requirement to "handle the stochasticity of wind and solar power" into explicit inequality constraints in the optimization model. The ultimate effect is that it effectively prevents aggressive scheduling strategies based on over-reliance on prediction data during the optimization process, thereby significantly enhancing the robustness and practical feasibility of the scheduling scheme in response to renewable energy fluctuations.

[0051] In a preferred embodiment, in addition to distributed power source output constraints, the multi-objective optimization function can be supplemented with constraints on energy storage charging and discharging power / capacity, flexible load adjustment range, and grid voltage / frequency limits to comprehensively characterize the system's safe operating boundaries. Clearly defining various operating boundaries, such as those for distributed power source output, establishes a safe range for subsequent optimization solutions, preventing system failures caused by scheduling strategies.

[0052] In step S103 of some embodiments, the optimization algorithm can be a mathematical method for solving multi-objective optimization functions and finding the optimal solution. The optimization algorithm can be at least one of particle swarm optimization (PSO), genetic algorithm (GA), ant colony algorithm (ACO), and deep reinforcement learning (DRL). The microgrid scheduling strategy can be a specific scheme guiding distributed power generation output, energy storage charging and discharging, and flexible load regulation. Cooperative control refers to a control method that coordinates the actions of various resources within the microgrid according to the scheduling strategy to achieve the overall goal.

[0053] In some embodiments, an optimization algorithm is used to optimize and solve a multi-objective optimization function to obtain a microgrid dispatch strategy, including: An active power distribution network simulation model integrating distributed power sources and energy storage systems is constructed based on the standard power distribution node system. Multiple scheduling scenarios are set up, including at least a fixed load scheduling scenario without energy storage, a scenario that only performs real-time scheduling, and a scenario that combines day-ahead optimization and real-time optimization. In active distribution network simulation models and under different scheduling scenarios, optimization algorithms are applied to solve multi-objective optimization functions to obtain microgrid scheduling strategies.

[0054] Specifically, the standard active distribution network simulation model uses the IEEE-33 node system as its topology and integrates specific equipment parameters such as distributed photovoltaic, wind power and distributed energy storage stations; multiple typical scheduling scenarios, including three comparative scenarios: fixed loads without energy storage (Scenario 1), real-time scheduling only (Scenario 2), and day-ahead-real-time collaborative optimization (Scenario 3).

[0055] See Figure 2 First, an active power distribution network simulation model integrating distributed power sources and energy storage systems was constructed based on the IEEE-33-bus system, providing a reliable verification environment for algorithm testing. The standard bus voltage of this model is... The maximum load capacity is (3.917 + j1.986) MVA. Node 5 integrates 1.5 MW of distributed photovoltaic power generation, while nodes 16 and 27 integrate 1 MW and 1.5 MW of distributed wind power generation resources, respectively, accurately reflecting a typical scenario of high-proportion renewable energy integration.

[0056] Figure 3 The actual output power of the photovoltaic system and load forecast curves for different time periods within the distribution network are displayed. Due to the high volatility of the output of the new power system, the maximum forecast error tolerance for distributed energy output is set at 20%, while the maximum allowable deviation for base load forecasting is set at 10%. To address forecast uncertainty, a real-time dispatch strategy is implemented, with hourly forecast error corrections to ensure dispatch accuracy.

[0057] Figure 4 The study presents the actual output power of wind turbines and load forecasting, further demonstrating that the integration of distributed power sources significantly increases the fluctuation range of the load curve and the rate of power change. This trend directly leads to a decrease in the reliability of the distribution network and also greatly increases the complexity and challenge of peak shaving. In particular, distributed wind power output, due to its highly random characteristics, causes particularly significant interference to the distribution network.

[0058] The distributed energy storage station uses lithium-ion battery packs as the energy storage medium, connects to the grid at 17 nodes, and has an installed capacity of [missing information]. Under ideal conditions, the system can achieve... The system charges and discharges at its maximum power. The dispatch cost in the optimization objective is set at 250 yuan / MWh, which is crucial for assessing the economic feasibility of the energy storage system, as it directly impacts operating costs and potential revenue. Furthermore, the benefits of a "low-charge, high-discharge" strategy and additional economic incentives provided by the government or electricity market to encourage the energy storage system to discharge are also considered.

[0059] To fully verify the adaptability of the scheduling strategy, this application designed three progressive comparison scenarios, each with a different resource interaction model, to explore the optimal system scheduling strategy: In Scenario 1, the energy storage system is not included in the optimized scheduling process. The scheduling plan for the user-side controllable load is determined one day in advance and does not involve dynamic adjustments during real-time scheduling.

[0060] In Scenario 2, the scheduling optimization steps taken one day in advance are ignored. Instead, the charging and discharging output of the energy storage system is directly adjusted during real-time scheduling based on the updated overall load situation.

[0061] In Scenario 3, the scheduling strategy combines advance optimization one day in advance with real-time optimization, improving flexibility and efficiency.

[0062] Simulation results show that in Scenario 1, which only uses fixed load scheduling, the system struggles to cope with power shortages caused by fluctuations in renewable energy sources. While Scenario 2, through real-time scheduling of energy storage, can alleviate instantaneous power imbalances, the lack of day-ahead optimization guidance results in a lack of foresight in energy storage actions. Scenario 3, by coordinating day-ahead planning with real-time correction, achieves optimized allocation of energy storage resources, with its intraday charge / discharge power and state of charge (SoC) of the energy storage system at different times as shown in the following figures. Figure 5 As shown. Figure 5 It includes two sub-plots: the left plot shows the intraday active power changes (unit: MW) of ESS1 (blue line) and ESS2 (orange line), with positive values ​​corresponding to discharge (supplying energy to the grid) and negative values ​​corresponding to charging (taking energy from the grid). The power fluctuations of the two can be used to smooth out the fluctuations in the output of new energy sources; the right plot shows the changes in their state of charge (SoC, i.e., the percentage of remaining energy storage capacity), reflecting the dynamic changes in capacity during the charging and discharging process of energy storage.

[0063] Finally, on this simulation platform and in multiple scenarios, various optimization algorithms were applied in parallel for solution calculations, and the generated scheduling strategies were compared and analyzed. By comparing multiple optimization algorithms, the applicability and advantages of optimization methods in dealing with complex nonlinear, multi-objective, and multi-constraint problems were verified, especially the adaptability of deep reinforcement learning in dynamic environments, which provides a new technical path for microgrid scheduling problems.

[0064] At the modeling level, this application breaks through the simplistic assumptions of traditional methods that only consider "source-load" or "source-storage" relationships, making the model closer to the actual operating environment of microgrids. At the methodological level, based on particle swarm optimization, this application introduces genetic algorithms, ant colony optimization, and deep reinforcement learning. By comparing various optimization algorithms, the applicability and advantages of optimization methods in dealing with complex nonlinear, multi-objective, and multi-constraint problems are verified. In particular, the adaptability of deep reinforcement learning in dynamic environments provides a new technical path for microgrid scheduling problems.

[0065] Please see Figure 6 This application also provides a microgrid scheduling strategy generation device, which can implement the above-mentioned microgrid scheduling strategy generation method. The device includes: Module 601 is used to construct a physical model for microgrid optimal scheduling, which includes at least a flexible load response model. Module 602 is established to create a multi-objective optimization function that includes power supply reliability and operating cost objectives based on a flexible load response model. The constraint module 603 is used to set the system operation constraints of the multi-objective optimization function, wherein the system operation constraints include at least the distributed power source output constraints; The solver module 604 is used to optimize the multi-objective optimization function using an optimization algorithm to obtain the microgrid scheduling strategy, so as to coordinate the control of various resources in the microgrid based on the microgrid scheduling strategy.

[0066] The specific implementation of the microgrid scheduling strategy generation device is basically the same as the specific implementation of the microgrid scheduling strategy generation method described above, and will not be repeated here.

[0067] Thirdly, embodiments of this application provide an electronic device, see [link to relevant documentation]. Figure 7 The diagram shown is a structural schematic of an electronic device provided in this application.

[0068] like Figure 7 As shown, the device includes: Memory 31 is used to store computer programs; Processor 32 is used to execute computer programs; When the processor 32 executes the computer program, it implements the microgrid scheduling strategy generation method as described in any of the above embodiments.

[0069] For example, a computer program may be divided into one or more modules / units, one or more of which are stored in memory 31 and executed by processor 32 to complete this application. One or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in an electronic device.

[0070] The processor 32 may be a Central Processing Unit (CPU), or 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. A general-purpose processor may be a microprocessor or any conventional processor.

[0071] The memory 31 can be used to store computer programs and / or modules. The processor 32 implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory 31 and calling the data stored in the memory 31. The memory 31 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 31 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0072] It should be noted that the aforementioned electronic devices include, but are not limited to, processors and memory, as will be understood by those skilled in the art. Figure 7 The structural diagram is merely an example of the electronic device described above and does not constitute a limitation on the electronic device. It may include more components than shown in the diagram, or combine certain components, or use different components.

[0073] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed, implements the microgrid scheduling strategy generation method of any of the above embodiments.

[0074] It should be understood that the implementation of all or part of the processes in the microgrid dispatch strategy generation method described above can also be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the microgrid dispatch strategy generation method described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content contained in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the relevant jurisdiction. For example, in some relevant jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0075] Fifthly, embodiments of this application also provide a computer program product, which is stored in a storage medium and executed by at least one processor to implement the microgrid scheduling strategy generation method of any of the above embodiments.

[0076] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0077] The above description is the preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications are also considered to be within the scope of protection of this application.

Claims

1. A method for generating microgrid dispatch strategies, characterized in that, include: Construct a physical model for optimal scheduling of a microgrid, wherein the physical model for optimal scheduling of a microgrid includes at least a flexible load response model; Based on the aforementioned flexible load response model, a multi-objective optimization function is established that includes power supply reliability and operating cost objectives. The system operation constraints of the multi-objective optimization function are set, wherein the system operation constraints include at least distributed power source output constraints; An optimization algorithm is used to optimize and solve the multi-objective optimization function to obtain a microgrid scheduling strategy, which is then used to coordinate the control of various resources within the microgrid.

2. The microgrid scheduling strategy generation method as described in claim 1, characterized in that, The process of constructing the flexible load response model includes: Based on the user's response status and response power, calculate the total response output of the load aggregator per unit time. Calculate the expenditure costs incurred by the load aggregator due to scheduling, based on the unit incentive price.

3. The microgrid scheduling strategy generation method as described in claim 1, characterized in that, The optimization algorithm is at least one of particle swarm optimization, genetic algorithm, ant colony optimization, and deep reinforcement learning algorithm.

4. The microgrid scheduling strategy generation method as described in claim 1, characterized in that, The establishment of a multi-objective optimization function based on the flexible load response model, which includes power supply reliability and operating cost objectives, includes: Based on the aforementioned flexible load response model, a power supply reliability target that minimizes the load fluctuation rate of the distribution network is constructed. Based on the aforementioned flexible load response model and energy storage system operating costs, a system operation cost objective that minimizes system scheduling costs and power loss costs is constructed.

5. The microgrid scheduling strategy generation method as described in claim 1, characterized in that, The system operation constraints for setting the multi-objective optimization function include: Upper and lower limits are set for the actual output power of the distributed power source. The upper and lower limits are determined based on its day-ahead predicted output value and in combination with a preset prediction error tolerance.

6. The microgrid scheduling strategy generation method as described in claim 1, characterized in that, The step of using an optimization algorithm to optimize the multi-objective optimization function to obtain a microgrid scheduling strategy includes: An active power distribution network simulation model integrating distributed power sources and energy storage systems is constructed based on the standard power distribution node system. Multiple scheduling scenarios are defined, including at least a fixed load scheduling scenario without energy storage, a scenario that only performs real-time scheduling, and a scenario that combines day-ahead optimization and real-time optimization. In the active power distribution network simulation model and under different scheduling scenarios, the optimization algorithm is applied to solve the multi-objective optimization function to obtain the microgrid scheduling strategy.

7. A microgrid dispatch strategy generation device, characterized in that, include: The construction module is used to construct a physical model for microgrid optimal scheduling, wherein the physical model for microgrid optimal scheduling includes at least a flexible load response model; A module is established to create a multi-objective optimization function that includes power supply reliability and operating cost objectives based on the flexible load response model. The constraint module is used to set the system operation constraints of the multi-objective optimization function, wherein the system operation constraints include at least distributed power source output constraints; The solution module is used to optimize the multi-objective optimization function using an optimization algorithm to obtain a microgrid scheduling strategy, so as to coordinate the control of various resources within the microgrid based on the microgrid scheduling strategy.

8. An electronic device, characterized in that, The system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the microgrid scheduling strategy generation method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform the microgrid scheduling strategy generation method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program or computer instructions, which, when executed by a processor, implement the microgrid scheduling strategy generation method as described in any one of claims 1 to 6.

Images