Intelligent control and energy storage optimization method and system for distributed energy systems

Abstract

This invention discloses an intelligent regulation and optimization method and system for distributed energy systems. The method includes real-time monitoring of dust distribution and temperature data on the surface of photovoltaic modules; constructing a power generation efficiency correction model to calculate actual power generation degradation and outputting the corrected theoretical power generation; establishing a digital twin model based on energy storage operation data and synchronizing it with the energy storage system status and grid parameters; constructing a multi-objective optimization model based on the digital twin model to collaboratively allocate the output strategies of each energy storage unit in peak shaving and backup power scenarios; and triggering a replanning algorithm to recalculate energy storage capacity allocation and optimize charging and discharging priorities when battery degradation exceeds a first preset threshold or local grid load imbalance is detected, thereby generating the final energy storage configuration scheme. This invention can accurately calculate actual power generation degradation considering the effects of dust, temperature, etc., providing a reliable basis for energy storage planning and enabling collaborative allocation of output strategies for each energy storage unit in different scenarios, thereby improving the operating efficiency and stability of the energy storage system.

Description

Technical Field

[0001] This invention relates to the field of new energy technology, and in particular to an intelligent regulation and energy storage optimization method and system for distributed energy systems. Background Technology

[0002] In distributed energy systems, the effective application of energy storage technology is crucial for improving energy utilization efficiency and ensuring stable grid operation. However, existing technologies have several shortcomings in energy storage regulation within distributed energy systems. On the one hand, for common distributed energy generation equipment such as photovoltaic (PV) modules, there is a lack of precise monitoring and consideration of their operating environment factors. Dust accumulation on the surface of PV modules can block sunlight, reducing photoelectric conversion efficiency, while temperature changes significantly affect their power generation performance. However, existing technologies often overlook these effects, leading to an inability to accurately assess the actual power generation capacity of PV modules. This results in significant deviations in power generation calculations, hindering efficient energy storage planning and regulation.

[0003] On the other hand, in the operation and management of energy storage systems, existing technologies cannot achieve precise synchronization between the energy storage system status and grid parameters. When constructing energy storage optimization models, it is difficult to comprehensively and accurately consider various complex factors, resulting in a lack of coordination and scientific rigor in energy storage output strategies under different scenarios such as peak shaving and backup power, thus failing to fully utilize the efficiency of energy storage devices. Furthermore, when abnormal situations such as battery degradation or local grid load imbalance occur, existing technologies cannot promptly and intelligently re-plan energy storage capacity allocation and charging / discharging priorities, leading to poor ability of energy storage systems to cope with emergencies and affecting the stability and reliability of the entire distributed energy system. Summary of the Invention

[0004] To address at least one of the aforementioned technical problems, this invention provides an intelligent regulation and energy storage optimization method and system for distributed energy systems.

[0005] In a first aspect, the present invention provides an intelligent regulation and energy storage optimization method for distributed energy systems, the method comprising:

[0006] Real-time monitoring of dust distribution and temperature data on the surface of photovoltaic modules;

[0007] A power generation efficiency correction model is constructed based on dust distribution data and temperature data. The actual power generation attenuation is calculated based on the power generation efficiency correction model, and the corrected theoretical power generation is output.

[0008] A digital twin model is established based on the revised theoretical power generation and energy storage operation data, and synchronized with the energy storage system status and grid parameters; a multi-objective optimization model is constructed based on the digital twin model to coordinate the power output strategies of each energy storage system in peak shaving and backup power scenarios.

[0009] When battery degradation exceeds the first preset threshold or local grid load imbalance is detected, the replanning algorithm is triggered to recalculate the energy storage capacity allocation and optimize the charging and discharging priorities to generate the final energy storage configuration scheme.

[0010] Preferably, a power generation efficiency correction model is constructed based on the dust distribution data and temperature data. The actual power generation reduction is calculated according to the power generation efficiency correction model, and the corrected theoretical power generation is output, including:

[0011] Collect dust coverage, particle size distribution, and plate surface temperature gradient;

[0012] Based on dust coverage, particle size distribution and plate surface temperature gradient, a coupled model of dust deposition-temperature field-power generation efficiency is constructed.

[0013] Based on the coupled model, the actual efficiency degradation rate of photovoltaic modules is dynamically calculated through the heat conduction equation and the light attenuation coefficient, and the corrected theoretical power generation is output.

[0014] Preferably, the method for constructing the coupling model includes:

[0015] ;

[0016] in, For the corrected efficiency, For the thickness of dust deposits, For temperature deviation, The dust impact factor has a range of values. ; This is the temperature influence coefficient, with a value range of [value range missing]. .

[0017] Preferably, a digital twin model is established based on the corrected theoretical power generation and energy storage operation data, and synchronized with the energy storage system status and grid parameters; a multi-objective optimization model is constructed based on the digital twin model to collaboratively allocate the output strategies of each energy storage unit in peak shaving and backup power scenarios, including:

[0018] Based on the revised theoretical power generation and energy storage system operation data, a digital twin covering photovoltaic modules, energy storage batteries, and grid topology is established to synchronize battery state of charge, line load, and environmental parameters in real time.

[0019] By utilizing real-time data from digital twins and treating distributed energy storage systems as game participants, a multi-objective optimization model based on Shapley values ​​is designed to dynamically allocate the output strategies of each energy storage system in peak shaving and backup power scenarios, thereby generating an initial energy storage configuration scheme.

[0020] Preferably, the design is based on a multi-objective optimization model using Shapley values, comprising:

[0021] Based on the real-time line load data provided by the digital twin, the output range of each energy storage system is constrained to ensure that the voltage deviation of the grid nodes does not exceed ±5% and the line load rate is less than 90%.

[0022] The peak-shaving revenue of each energy storage system is allocated by Shapley value to ensure that the individual revenue is not less than the revenue when it operates independently, and the total revenue satisfies superadditivity.

[0023] Preferably, the replanning algorithm is as follows:

[0024] Based on the battery health state prediction model, the capacity decay rate is calculated:

[0025] ;

[0026] in, For battery health status, This refers to the number of charge-discharge cycles. The attenuation coefficient has a range of values ​​of 100. ;

[0027] when When the load falls below the second preset threshold, a capacity redistribution strategy is triggered, proportionally transferring the load of the high-degradation battery to the low-degradation battery.

[0028] Preferably, the data synchronization frequency of the digital twin is not less than 10Hz, and localized data processing is achieved through edge computing nodes to reduce cloud transmission latency.

[0029] Secondly, the present invention also provides an intelligent regulation and energy storage optimization system for distributed energy systems, the system comprising:

[0030] The data acquisition unit is used to monitor the dust distribution and temperature data on the surface of the photovoltaic module in real time.

[0031] The power generation correction unit is used to build a power generation efficiency correction model based on dust distribution data and temperature data, calculate the actual power generation attenuation according to the power generation efficiency correction model, and output the corrected theoretical power generation.

[0032] The multi-objective optimization unit is used to establish a digital twin model based on the corrected theoretical power generation and energy storage operation data, and synchronize it with the energy storage system status and grid parameters; based on the digital twin model, a multi-objective optimization model is constructed to coordinate the power output strategies of each energy storage system in peak shaving and backup power scenarios.

[0033] The energy storage configuration update unit is used to trigger a replanning algorithm to recalculate the energy storage capacity allocation and optimize the charging and discharging priorities when the battery degradation exceeds the first preset threshold or the local grid load is unbalanced, thereby generating the final energy storage configuration scheme.

[0034] Thirdly, the present invention also provides an electronic device including a processor and a memory, the memory being used to store computer program code, the computer program code including computer instructions, wherein when the processor executes the computer instructions, the electronic device performs the method as described in the first aspect above and any possible implementation thereof.

[0035] Fourthly, the present invention also provides a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor of an electronic device, cause the processor to perform a method as described in the first aspect above and any possible implementation thereof.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The intelligent regulation and energy storage optimization method for distributed energy systems provided by this invention effectively solves these technical challenges. By monitoring dust distribution and temperature data on the surface of photovoltaic modules in real time and constructing a power generation efficiency correction model, the actual power generation degradation can be accurately calculated, outputting a more realistic corrected theoretical power generation, providing a reliable basis for energy storage planning. Based on this, a digital twin model is established to synchronize the energy storage system status with grid parameters, and a multi-objective optimization model is constructed. This model can collaboratively allocate the output strategies of each energy storage unit in different scenarios, greatly improving the operating efficiency of the energy storage system. When battery degradation exceeds a first preset threshold or local grid load imbalance is detected, a replanning algorithm is triggered to recalculate the energy storage capacity allocation and optimize charging and discharging priorities, generating the final energy storage configuration scheme. This ensures that the energy storage system can still operate stably and efficiently under complex operating conditions, enhancing the distributed energy system's ability to cope with various changes and improving the overall system's stability, reliability, and energy utilization efficiency.

[0038] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention or the background art, the accompanying drawings used in the embodiments of the present invention or the background art will be described below.

[0040] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the specification, serve to illustrate the technical solutions of this disclosure.

[0041] Figure 1 A flowchart illustrating an intelligent regulation and energy storage optimization method for distributed energy systems provided in an embodiment of the present invention;

[0042] Figure 2 for Figure 1 A flowchart illustrating the sub-steps of step S20;

[0043] Figure 3 for Figure 1 A flowchart illustrating the sub-steps of step S30;

[0044] Figure 4 This is a schematic diagram of the structure of an intelligent regulation and energy storage optimization system for distributed energy systems, provided as an embodiment of the present invention. Detailed Implementation

[0045] To enable those skilled in the art to better understand the present invention, the technical solutions of the embodiments 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, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0047] Please see Figure 1 , Figure 1 This is a flowchart illustrating an intelligent regulation and energy storage optimization method for distributed energy systems, provided as an embodiment of the present invention. Figure 1 As shown, the method includes:

[0048] S10. Real-time monitoring of dust distribution and temperature data on the surface of photovoltaic modules;

[0049] Dust on the surface of photovoltaic (PV) modules can block sunlight, reducing their photoelectric conversion efficiency. The degree of impact on power generation efficiency varies depending on the dust distribution. Temperature also significantly affects the power generation performance of PV modules; excessively high or low temperatures can lead to a decrease in efficiency. Only by acquiring real-time data on dust distribution and temperature can we provide the necessary foundational data for accurately assessing the power generation efficiency of PV modules.

[0050] Therefore, in this embodiment, a high-resolution image sensor and a high-precision temperature sensor are installed on the surface of the photovoltaic module. The high-resolution image sensor periodically acquires images of the photovoltaic module surface and analyzes the distribution data such as the coverage area and thickness of dust in the images using image recognition algorithms. The high-precision temperature sensor monitors the surface temperature of the photovoltaic module in real time and transmits the collected temperature data to the data processing center via a wireless communication module. This enables real-time and accurate monitoring of key environmental factors affecting the power generation efficiency of photovoltaic modules, providing reliable data support for the subsequent construction of a power generation efficiency correction model. This makes the power generation calculation more consistent with the actual situation and avoids deviations in power generation estimation caused by ignoring dust and temperature factors, thereby laying the foundation for the rational planning of energy storage systems.

[0051] S20. Construct a power generation efficiency correction model based on dust distribution data and temperature data, calculate the actual power generation attenuation according to the power generation efficiency correction model, and output the corrected theoretical power generation.

[0052] Because the effects of dust and temperature on the power generation efficiency of photovoltaic modules are complex, it is difficult to obtain accurate results through simple formulas. In this embodiment, historical operating data can be used, combined with the relationship between dust distribution data, temperature data, and actual power generation, to train a power generation efficiency correction model using machine learning algorithms (such as neural network algorithms). Real-time monitored dust distribution data and temperature data are input into the model, which calculates the power generation efficiency of the photovoltaic module under the current operating conditions based on the learned relationships. This efficiency is compared with the power generation efficiency under standard operating conditions to determine the actual power generation attenuation ratio, and then the corrected theoretical power generation is calculated and output.

[0053] The data-driven power generation efficiency correction model can accurately quantify the impact of dust and temperature on the power generation efficiency of photovoltaic modules, effectively improving the accuracy of theoretical power generation calculations. Compared to traditional power generation calculation methods that do not consider these factors, the corrected theoretical power generation more accurately reflects the actual power generation capacity of photovoltaic modules, helping energy storage systems to more rationally plan charging and discharging strategies and improve energy utilization efficiency.

[0054] S30. Establish a digital twin model based on the corrected theoretical power generation and energy storage operation data, and synchronize it with the energy storage system status and grid parameters; construct a multi-objective optimization model based on the digital twin model to coordinate the power output strategies of each energy storage system in peak shaving and backup power scenarios.

[0055] Digital twin models can simulate the operating status of energy storage systems and power grids in real time and accurately, providing intuitive and visual decision-making basis for energy storage optimization and control. Constructing multi-objective optimization models can comprehensively consider multiple important objectives and solve them through intelligent optimization algorithms. This can find the optimal output strategy for each energy storage system in different scenarios under complex operating environments, achieving efficient utilization of energy storage resources and stable operation of the power grid.

[0056] In this embodiment, the corrected theoretical power generation, the charging and discharging status of the energy storage devices, remaining capacity, charging and discharging power, and other energy storage operation data, as well as grid parameters such as voltage, frequency, and load, are transmitted in real time to the digital twin platform via a data interface. Using 3D modeling technology and simulation algorithms, a digital twin model highly similar to the actual energy storage system and grid is constructed on the digital twin platform, achieving real-time synchronization between the energy storage system status and grid parameters. Based on the digital twin model, a multi-objective optimization model is constructed with the goals of improving energy utilization, reducing operating costs, and ensuring grid stability. Intelligent optimization algorithms (such as genetic algorithms and particle swarm optimization) are used to solve the model, deriving the optimal output strategy for each energy storage system under different scenarios such as peak shaving and backup power.

[0057] The establishment of a digital twin model enables real-time and accurate simulation of the operating status of the energy storage system and the power grid, allowing operators to have a comprehensive understanding of the system's operation. Based on this, a multi-objective optimization model, through intelligent algorithms, can collaboratively allocate the workload of each energy storage unit in different scenarios, avoiding disordered operation of energy storage devices. In peak-shaving scenarios, it can effectively smooth fluctuations in photovoltaic power output and improve the grid's ability to accommodate distributed energy resources; in backup power scenarios, it can rationally allocate energy storage capacity, ensure power supply to critical loads, and significantly improve the overall operating efficiency of the energy storage system and the stability of the power grid.

[0058] S40. When the battery degradation exceeds the first preset threshold or the local grid load is unbalanced, the replanning algorithm is triggered to recalculate the energy storage capacity allocation and optimize the charging and discharging priority to generate the final energy storage configuration scheme.

[0059] Battery degradation leads to a decline in the performance of energy storage devices, affecting the overall efficiency of the energy storage system. Local grid load imbalances may cause voltage fluctuations, frequency anomalies, and other problems, threatening the safe and stable operation of the grid. When these situations occur, the original energy storage configuration scheme may no longer be applicable, and it is necessary to promptly re-plan the allocation of energy storage capacity and charging / discharging priorities to ensure that the energy storage system can continue to operate stably and efficiently, thus protecting grid security.

[0060] During the operation of the energy storage system, parameters such as the number of charge-discharge cycles and capacity retention rate of the batteries are monitored in real time, and the degree of battery degradation is determined through data analysis. Simultaneously, the load status of each node in the power grid is monitored, and the load balance is calculated. When battery degradation exceeds a first preset threshold or the local grid load imbalance exceeds a set standard, a replanning algorithm is triggered. The replanning algorithm takes the revised theoretical power generation, the current state of the energy storage system, and the grid load status as inputs, and uses dynamic programming or heuristic algorithms to recalculate the capacity allocation of each energy storage device, optimize charge-discharge priorities, and ultimately generate a final energy storage configuration scheme adapted to the new operating conditions. This scheme is then sent to the energy storage control system for execution.

[0061] By monitoring in real time and triggering replanning algorithms promptly, the system can quickly respond to anomalies such as battery degradation and local grid load imbalances. The recalculated energy storage capacity allocation and optimized charging / discharging priorities enable the energy storage system to maintain high efficiency under new operating conditions, effectively reducing the adverse effects of battery degradation on the system, improving its ability to cope with grid load changes, enhancing the stability and reliability of the distributed energy system, and ensuring the continuity and quality of power supply.

[0062] See Figure 2 In one embodiment, a power generation efficiency correction model is constructed based on the dust distribution data and temperature data. The actual power generation reduction is calculated according to the power generation efficiency correction model, and the corrected theoretical power generation is output, including:

[0063] S201. Collect dust coverage, particle size distribution, and plate surface temperature gradient;

[0064] Dust coverage directly affects the area of ​​a photovoltaic module that receives sunlight; the higher the coverage, the less usable light energy. Particle size distribution determines the scattering and absorption characteristics of light by dust particles; different particle sizes attenuate light to varying degrees. The surface temperature gradient reflects the non-uniformity of the module's surface temperature; temperature changes alter the carrier concentration and mobility of the photovoltaic material, affecting power generation efficiency. These three parameters comprehensively reflect the impact of environmental factors on power generation performance from both optical and thermodynamic perspectives.

[0065] Traditional single sensors cannot acquire multi-dimensional information about dust and temperature, making it difficult to accurately assess environmental impacts. Employing sensor arrays and advanced data processing technologies enables refined, real-time monitoring of dust and temperature, obtaining high spatiotemporal resolution data. If data is missing or insufficiently accurate, the subsequently constructed model will fail to accurately reflect the actual power generation process, leading to deviations in power generation calculations and affecting the control effectiveness of the energy storage system.

[0066] Therefore, in this implementation, a miniature optical sensor array and a thin-film temperature sensor are uniformly deployed on the surface of the photovoltaic module. The optical sensor uses the principle of laser scattering, emitting a laser beam and analyzing the scattering angle and intensity of the laser by dust particles to calculate the dust coverage and particle size distribution. The thin-film temperature sensor is closely attached to the module surface, forming a grid layout with a 5-centimeter spacing, to collect temperature data at each point in real time. The discrete temperature data is processed using an interpolation algorithm to construct a temperature gradient distribution map of the photovoltaic module surface. After preliminary processing by edge computing devices, the collected data is transmitted to a central data processing server via 5G or industrial Ethernet.

[0067] Through high-precision sensors and data processing technology, the measurement error of dust coverage can be controlled within 3%, the measurement error of particle size distribution is less than 5%, and the measurement accuracy of temperature gradient reaches ±0.5℃. This high-quality data provides a solid foundation for subsequent model building, making the calculation of power generation efficiency correction more accurate, significantly reducing the error of power generation prediction, and helping energy storage systems to plan charging and discharging strategies more rationally, thereby improving energy utilization.

[0068] S202. Based on dust coverage, particle size distribution and plate surface temperature gradient, a coupled model of dust deposition-temperature field-power generation efficiency is constructed.

[0069] Dust deposition causes light attenuation, reducing the effective light intensity received by photovoltaic modules. Temperature field changes alter power generation efficiency by affecting the bandgap and carrier mobility of semiconductor materials. These two factors are interrelated: dust deposition affects the heat dissipation characteristics of the module surface, thus changing the temperature field distribution, while temperature changes also affect the physicochemical properties and deposition state of dust. Coupled models, by integrating these interactions, can more realistically describe the changing patterns of power generation efficiency. Considering the effects of dust or temperature alone on power generation efficiency fails to reflect their synergistic effect, leading to significant discrepancies between model calculations and actual results. Constructing coupled models and employing data-driven parameter optimization methods can comprehensively consider the interactive effects of multiple factors, improving the model's accuracy and versatility. Traditional empirical formulas are difficult to adapt to complex and changing real-world environments, while coupled models, through parameter adjustments, can meet the power generation efficiency calculation needs of different scenarios.

[0070] Therefore, in this embodiment, based on heat transfer, optics, and semiconductor physics theories, and combined with a large amount of historical experimental data, a physical coupling model between dust deposition, temperature field, and power generation efficiency is established using the finite element method. The model parameters are determined by performing multivariate nonlinear regression on photovoltaic module power generation experimental data under different dust conditions and temperature environments.

[0071] Preferably, the method for constructing the coupling model includes:

[0072] ;

[0073] in, For the corrected efficiency, For the thickness of dust deposits, For temperature deviation, The dust impact factor has a range of values. ; This is the temperature influence coefficient, with a value range of [value range missing]. .

[0074] Dust Influence Coefficient This indicates the percentage of photovoltaic efficiency loss caused by each millimeter of dust deposition thickness. For example, if... This indicates that the efficiency loss is 30% when 1 mm of dust is deposited; temperature influence coefficient This indicates the percentage of photovoltaic efficiency loss caused by each degree Celsius temperature deviation. For example, if... The temperature will rise. ( The efficiency loss is 5%, and it needs to be ensured during calculation. For the actual temperature and the standard test temperature ( The difference between the two values. Preferably, a genetic algorithm can be used to calculate the difference. and Global optimization is performed, and parameter values ​​are dynamically adjusted according to different regions, seasons, and component types to enable the model to adapt to complex and ever-changing actual working conditions.

[0075] The average error between the power generation efficiency calculated by the coupled model and the actual measured value is within 2.5%, which is significantly lower than that of the single-factor model. An accurate power generation efficiency model provides reliable power generation predictions for energy storage systems, enabling more scientific formulation of energy storage charging and discharging strategies, reducing waste or inadequacy of energy storage resources due to inaccurate predictions, and improving the overall economic efficiency and stability of distributed energy systems.

[0076] S203. Based on the coupled model, the actual efficiency degradation rate of the photovoltaic module is dynamically calculated through the heat conduction equation and the light attenuation coefficient, and the corrected theoretical power generation is output.

[0077] The heat conduction equation describes the heat transfer within a photovoltaic module. Solving this equation yields the temperature of various parts of the module, allowing for the calculation of the temperature's impact on power generation efficiency. The light attenuation coefficient reflects the degree of light absorption and scattering by dust particles; different dust characteristics correspond to different light attenuation coefficients. Based on a coupled model, the combined calculation of the effects of heat conduction and light attenuation on power generation efficiency accurately reflects the efficiency degradation of photovoltaic modules under actual operating conditions, thereby correcting the theoretical power generation.

[0078] The power generation efficiency of photovoltaic modules changes dynamically with environmental conditions, and traditional static calculation methods cannot adapt to this change. By collecting data in real time and dynamically calculating the efficiency degradation rate using physical equations, the impact of environmental changes on power generation performance can be reflected in a timely manner, making the corrected theoretical power generation closer to reality. The calculation method based on physical equations and coupled models has a solid theoretical foundation, and compared with empirical formulas, the calculation results are more reliable, providing an accurate basis for the regulation of energy storage systems.

[0079] In this embodiment, the real-time dust coverage, particle size distribution, and panel temperature gradient data collected in step S201 are input into the coupled model. Using the heat conduction equation and the thermophysical parameters of the module materials, the internal temperature distribution of the module is calculated to determine the impact of temperature on power generation efficiency. Based on the dust coverage and particle size distribution, the light attenuation coefficient is calculated using Mie scattering theory to assess the light loss caused by dust. The efficiency attenuation caused by temperature and dust is superimposed to obtain the actual efficiency attenuation rate of the photovoltaic module. Finally, the corrected efficiency formula is used... Calculate the corrected power generation efficiency, and combine it with the nominal power of the components and the operating time to output the corrected theoretical power generation.

[0080] Dynamic calculation methods enable real-time correction of photovoltaic module power generation efficiency, with the average error between the corrected theoretical power generation and the actual power generation controlled within 2%. Accurate power generation prediction allows energy storage systems to adjust charging and discharging strategies more promptly and precisely, efficiently storing excess electricity during periods of ample sunlight and rationally releasing electricity during peak demand or insufficient sunlight. This improves the response speed and control precision of energy storage systems, enhances the stability and energy utilization efficiency of distributed energy systems, and reduces system operating costs.

[0081] See Figure 3 In one embodiment, a digital twin model is established based on the corrected theoretical power generation and energy storage operation data, and synchronized with the energy storage system status and grid parameters; a multi-objective optimization model is constructed based on the digital twin model to collaboratively allocate the output strategies of each energy storage unit in peak shaving and backup power scenarios, including:

[0082] S301. Based on the corrected theoretical power generation and energy storage system operation data, establish a digital twin covering photovoltaic modules, energy storage batteries, and grid topology, and synchronize battery state of charge, line load, and environmental parameters in real time.

[0083] Traditional centralized monitoring systems cannot reflect the dynamic characteristics of distributed energy systems and the coupling relationships between devices in real time. Digital twins, by establishing a virtual model that is highly similar to the physical system, use a combination of data-driven and physical modeling methods to achieve real-time mapping and prediction of the physical system's state. There are complex energy flows and interactions between photovoltaic modules, energy storage batteries, and the power grid; only by establishing a unified model encompassing all three can the operating status of the entire system be accurately reflected.

[0084] Specifically, in step S301, a joint simulation model of photovoltaic-energy storage-grid is established based on the electrical characteristic equations of photovoltaic modules, the equivalent circuit model of energy storage batteries, and the power flow equations of the power grid. The finite element method is used to model the thermal distribution of photovoltaic modules and the electrochemical processes inside the batteries, accurately reflecting the physical characteristics of the equipment. Real-time data such as the temperature, light intensity, and output power of photovoltaic modules, the voltage, current, temperature, and SOC (state of charge) of energy storage batteries, and the node voltage and line current of the power grid are collected via an IoT sensor network. Field data is transmitted to the digital twin platform using a common protocol, and the data is denoised and state estimated using a Kalman filter to ensure accuracy and real-time performance. Finally, the actual operating data is compared with the simulation results of the digital twin model. The model parameters are dynamically adjusted using a particle swarm optimization algorithm to keep the model output error within 5% of the actual system. This achieves panoramic monitoring and accurate prediction of the distributed energy system, reducing the system state estimation error to within 3% and correspondingly improving the early warning of faults. The pre-simulation function of the digital twin allows for the early evaluation of the effects of different control strategies, reducing trial-and-error costs and improving system operational stability.

[0085] S302. Using real-time data from the digital twin, the distributed energy storage system is treated as a game participant. A multi-objective optimization model based on Shapley values ​​is designed to dynamically allocate the output strategies of each energy storage system in peak shaving and backup power scenarios, and generate an initial energy storage configuration scheme.

[0086] Traditional centralized optimization methods are ill-suited to the decentralized and uncertain nature of distributed energy systems. Shapley value theory, through a fair allocation mechanism, quantifies each participant's contribution to the consortium, resolving the balance between individual and collective interests in distributed systems. In multi-objective optimization, different output strategies have varying impacts on peak-shaving effectiveness, backup power reliability, and energy storage device lifespan, requiring mathematical methods to find the optimal equilibrium point.

[0087] In step S302, each energy storage unit in the distributed energy storage system is treated as an independent player in a game, with each player aiming to maximize its own interests and optimize the overall system. The objective of the peak-shaving scenario is defined as minimizing the peak-to-valley difference in the power grid, while the objective of the backup power scenario is maximizing the reliability of power supply to critical loads. The marginal contribution of each energy storage unit to the system objective is calculated using Monte Carlo simulation under different alliance combinations. The revenue weights of each energy storage unit are allocated according to the Shapley value formula, establishing a multi-objective function that includes economic benefits, system reliability, and equipment lifespan. The Pareto optimal solution set is solved using the NSGA-II algorithm. The optimal compromise solution is determined using fuzzy decision theory, generating the initial energy storage configuration scheme. Compared to traditional optimization methods, the multi-objective optimization strategy based on Shapley values ​​can reduce the peak-to-valley difference in the power grid by 15%-20%, improve the reliability of power supply to critical loads to over 99.9%, and extend the lifespan of energy storage equipment. This method, while ensuring the overall interests of the system, fairly allocates the revenue of each energy storage unit, increasing the enthusiasm of participants and promoting the healthy development of distributed energy systems. Therefore, this embodiment achieves intelligent collaborative control of the energy storage system through the combination of digital twins and game theory.

[0088] In one embodiment, the design is based on a multi-objective optimization model using Shapley values, including:

[0089] 1) Based on the real-time line load data provided by the digital twin, constrain the output range of each energy storage system to ensure that the voltage deviation of the grid nodes does not exceed ±5% and the line load rate is less than 90%;

[0090] The safe operation of power systems places strict requirements on voltage and line load. Excessive node voltage deviations can affect the lifespan and performance of electrical equipment, while line overloads can lead to equipment damage or even power outages. By using digital twin models to monitor system status in real time and incorporating constraints during the optimization process, it is possible to ensure that energy storage control strategies are implemented while meeting system safety requirements.

[0091] State estimation and power flow calculation: Using the real-time line load, node voltage and equipment parameters provided by the digital twin platform, the power flow equations of the power grid are solved by the Newton-Raphson method to calculate the voltage of each node and the line load rate.

[0092] Constraint Construction:

[0093] Voltage constraint: ;

[0094] Load factor constraints: ;

[0095] Energy storage output constraints: ;

[0096] in, For nodes voltage, For reference voltage, For the line The current, This is the maximum current of the line. For nodes of effort.

[0097] The aforementioned constraints are embedded into a multi-objective optimization model, which is then solved using the interior-point method or sequential quadratic programming algorithm. Through this constraint mechanism, grid node voltage deviations can be controlled within ±3%, and line load rates can be maintained below 80%, significantly improving grid operational safety. Simultaneously, the energy storage system's control strategy can fully consider the actual operating conditions of the grid, avoiding system instability caused by blind control.

[0098] 2) Allocate the peak-shaving revenue of each energy storage system through the Shapley value to ensure that the individual revenue is not less than the revenue when it operates independently, and that the total revenue satisfies superadditivity.

[0099] The Shapley value, as a fair allocation mechanism, quantifies the marginal contribution of each participant to the consortium. In peak-shaving scenarios, different energy storage systems have different locations, capacities, and response characteristics, resulting in varying contributions to the system. Allocating revenue through the Shapley value incentivizes each energy storage system to actively participate in peak shaving while ensuring the fairness and stability of the allocation results. This method can achieve a matching degree of over 90% between the peak-shaving revenue of each energy storage system and its actual contribution, effectively solving the fairness problem caused by traditional revenue allocation based on capacity. By satisfying individual and collective rationality constraints, it enhances the enthusiasm of energy storage systems to participate in peak shaving, significantly improving the overall peak-shaving efficiency of the system.

[0100] Therefore, the above embodiments reduce the risks of voltage exceedances and line overloads caused by energy storage regulation by leveraging grid constraints, thus lowering the system failure rate. The Shapley value allocation mechanism ensures a positive correlation between the benefits and contributions of each energy storage system, increasing their participation. Under the premise of meeting system safety constraints, peak-shaving costs are reduced, achieving a balance between overall system benefits and individual interests.

[0101] Preferably, the replanning algorithm is as follows:

[0102] Based on the battery health state prediction model, the capacity decay rate is calculated:

[0103] ;

[0104] in, For battery health status, This refers to the number of charge-discharge cycles. The attenuation coefficient has a range of values ​​of 100. ;

[0105] when When the load falls below the second preset threshold, a capacity redistribution strategy is triggered, proportionally transferring the load of the high-degradation battery to the low-degradation battery.

[0106] Battery capacity degradation is a gradual process with a non-linear relationship to the number of charge-discharge cycles. The square root model can fit the physical mechanism of battery degradation well and reflect the internal structure of the battery. The process of membrane growth and loss of active substances. This is achieved through real-time monitoring and prediction. This allows for early detection of declining battery performance, providing a basis for capacity reallocation decisions.

[0107] The battery management system collects real-time data on battery charge / discharge current, voltage, and temperature. A sliding window filtering algorithm is used to remove noise and extract the charge / discharge cycle count and depth. For different battery types, such as lithium iron phosphate, accelerated life testing is used to obtain experimental data, and the least squares method is employed to fit the degradation coefficient. A battery health status prediction model was established, and a Kalman filter was used to fuse real-time data with the prediction model to achieve [the desired result]. The dynamic updates keep the estimation error within ±3%.

[0108] When any battery is detected When the capacity falls below a second preset threshold, typically 80%, the capacity redistribution algorithm is triggered. This is based on the individual battery... The value is used to calculate the load distribution weight, i.e., the current battery's... With all batteries The ratio of the sums is used to achieve a smooth load transfer using a PID controller, avoiding power surges that could impact the power grid. The transfer rate must be limited to ensure safe battery operation.

[0109] By transferring the load from high-degradation batteries to low-degradation batteries, the depth of charge and discharge of each battery can be balanced, the aging rate of the high-degradation batteries can be slowed down, and the lifespan of the entire energy storage system can be extended. Based on The weight allocation mechanism ensures the fairness and rationality of load transfer, maximizing the overall performance of the system.

[0110] Therefore, this embodiment extends the overall lifespan of the energy storage system, reduces battery replacement frequency, lowers operation and maintenance costs, improves the system's available capacity retention rate, and enhances charging and discharging efficiency through predictive maintenance and capacity reallocation.

[0111] Preferably, the data synchronization frequency of the digital twin is not less than 10Hz, and localized data processing is achieved through edge computing nodes to reduce cloud transmission latency.

[0112] Miniature multi-parameter sensors are deployed on the surface of photovoltaic modules, integrating detection functions for light intensity, temperature, and dust coverage, with a sampling frequency ≥100Hz. Energy storage battery packs are equipped with a BMS (Battery Management System) to collect voltage, current, and temperature data in real time, with a sampling frequency ≥50Hz. PMUs (Phasor Measurement Units) are installed at key grid nodes to synchronously collect voltage phasor and frequency data, with a sampling frequency ≥60Hz. An industrial-grade edge computing gateway equipped with a multi-core processor and FPGA coprocessor is used, deploying a lightweight containerized platform to achieve distributed deployment of algorithm modules. Edge nodes have built-in data processing pipelines, including data cleaning, feature extraction, and state estimation modules. A hybrid time-triggered and event-triggered mechanism is adopted, synchronizing key state data at a frequency of 10Hz under normal operating conditions to achieve bidirectional data synchronization between the edge and the cloud, supporting breakpoint resume and data verification mechanisms. In this way, the end-to-end data synchronization latency is reduced from 200ms in the traditional solution to less than 8ms, the state estimation update cycle is improved from the second level to the 100ms level, significantly improving the system response speed, while the fault detection time is shortened to less than 50ms, realizing rapid perception and response to power grid disturbances. Through the deep integration of hardware acceleration and algorithm optimization, a low-latency and highly reliable digital twin data channel is constructed.

[0113] In summary, the intelligent regulation and energy storage optimization method for distributed energy systems provided by this invention, by real-time monitoring of dust distribution and temperature data on the surface of photovoltaic modules and constructing a power generation efficiency correction model, can accurately calculate the actual power generation degradation and output a more realistic corrected theoretical power generation, providing a reliable basis for energy storage planning. Based on this, a digital twin model is established to synchronize the energy storage system status with grid parameters, and a multi-objective optimization model is constructed. This model can collaboratively allocate the output strategies of each energy storage unit in different scenarios, greatly improving the operating efficiency of the energy storage system. When battery degradation exceeds a first preset threshold or a local grid load imbalance is detected, a replanning algorithm is triggered to recalculate the energy storage capacity allocation and optimize charging and discharging priorities, generating a final energy storage configuration scheme. This ensures that the energy storage system can still operate stably and efficiently under complex operating conditions, enhancing the distributed energy system's ability to cope with various changes and improving the overall system's stability, reliability, and energy utilization efficiency.

[0114] See Figure 4 In one embodiment, the present invention also provides an intelligent regulation and energy storage optimization system for distributed energy systems, the system comprising:

[0115] The data acquisition unit 100 is used to monitor the dust distribution and temperature data on the surface of the photovoltaic module in real time.

[0116] The power generation correction unit 200 is used to build a power generation efficiency correction model based on dust distribution data and temperature data, calculate the actual power generation attenuation according to the power generation efficiency correction model, and output the corrected theoretical power generation.

[0117] The multi-objective optimization unit 300 is used to establish a digital twin model based on the corrected theoretical power generation and energy storage operation data, and synchronize it with the energy storage system status and grid parameters; based on the digital twin model, a multi-objective optimization model is constructed to coordinate the power output strategies of each energy storage system in peak shaving and backup power scenarios;

[0118] The energy storage configuration update unit 400 is used to trigger a replanning algorithm to recalculate the energy storage capacity allocation and optimize the charging and discharging priorities when the battery degradation exceeds the first preset threshold or the local grid load is unbalanced, so as to generate the final energy storage configuration scheme.

[0119] It is understood that the system provided in this embodiment has functions or includes modules that can be used to execute the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0120] The present invention also provides an electronic device including a processor and a memory, the memory being used to store computer program code, the computer program code including computer instructions, wherein when the processor executes the computer instructions, the electronic device performs a method as described in any of the above possible implementations.

[0121] The present invention also provides a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor of an electronic device, cause the processor to perform a method as described in any of the above possible implementations.

[0122] 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.

Claims

1. A smart regulation and energy storage optimization method for distributed energy systems, characterized in that, The method includes: Real-time monitoring of dust distribution and temperature data on the surface of photovoltaic modules; A power generation efficiency correction model is constructed based on dust distribution data and temperature data. The actual power generation attenuation is calculated based on the power generation efficiency correction model, and the corrected theoretical power generation is output. A digital twin model is established based on the revised theoretical power generation and energy storage operation data, and synchronized with the energy storage system status and grid parameters; a multi-objective optimization model is constructed based on the digital twin model to coordinate the power output strategies of each energy storage system in peak shaving and backup power scenarios. When the battery degradation exceeds the first preset threshold or the local grid load is unbalanced, the replanning algorithm is triggered to recalculate the energy storage capacity allocation and optimize the charging and discharging priority to generate the final energy storage configuration scheme. The replanning algorithm is as follows: Based on the battery health state prediction model, the capacity decay rate is calculated: Where SOH represents the battery health status, and N... 循环 The charge-discharge cycle number is given, and k is the attenuation coefficient, with a value range of 0.005 ≤ k ≤ 0.

01. When the SOH is lower than the second preset threshold, the capacity redistribution strategy is triggered, and the load of the high-degradation battery is transferred to the low-degradation battery proportionally.

2. The intelligent regulation and energy storage optimization method for distributed energy systems according to claim 1, characterized in that, Based on the dust distribution data and temperature data, a power generation efficiency correction model is constructed. The actual power generation reduction is calculated according to the power generation efficiency correction model, and the corrected theoretical power generation is output, including: Collect dust coverage, particle size distribution, and plate surface temperature gradient; Based on dust coverage, particle size distribution and plate surface temperature gradient, a coupled model of dust deposition-temperature field-power generation efficiency is constructed. Based on the coupled model, the actual efficiency degradation rate of photovoltaic modules is dynamically calculated through the heat conduction equation and the light attenuation coefficient, and the corrected theoretical power generation is output.

3. The intelligent regulation and energy storage optimization method for distributed energy systems according to claim 2, characterized in that, The method for constructing the coupling model includes or 实际 =the 标称 ×(1-α·d 灰尘 )×(1-βΔT); Where, η 实际 For the corrected efficiency, d 灰尘 ΔT is the dust deposition thickness, ΔT is the temperature deviation, α is the dust influence coefficient with a value range of 0.1≤α≤0.5mm, and β is the temperature influence coefficient with a value range of 0.003℃≤β≤0.005℃.

4. The intelligent regulation and energy storage optimization method for distributed energy systems according to claim 1, characterized in that, A digital twin model is established based on the revised theoretical power generation and energy storage operation data, and synchronized with the energy storage system status and grid parameters; A multi-objective optimization model is constructed based on a digital twin model to collaboratively allocate the output strategies of various energy storage systems in peak shaving and backup power scenarios, including: Based on the revised theoretical power generation and energy storage system operation data, a digital twin covering photovoltaic modules, energy storage batteries, and grid topology is established to synchronize battery state of charge, line load, and environmental parameters in real time. By utilizing real-time data from digital twins and treating distributed energy storage systems as game participants, a multi-objective optimization model based on Shapley values ​​is designed to dynamically allocate the output strategies of each energy storage system in peak shaving and backup power scenarios, thereby generating an initial energy storage configuration scheme.

5. The intelligent regulation and energy storage optimization method for distributed energy systems according to claim 4, characterized in that, The design is based on a multi-objective optimization model using Shapley values, including: Based on the real-time line load data provided by the digital twin, the output range of each energy storage system is constrained to ensure that the voltage deviation of the grid nodes does not exceed ±5% and the line load rate is less than 90%. The peak-shaving revenue of each energy storage system is allocated by Shapley value to ensure that the individual revenue is not less than the revenue when it operates independently, and the total revenue satisfies superadditivity.

6. The intelligent regulation and energy storage optimization method for distributed energy systems according to claim 1, characterized in that, The data synchronization frequency of the digital twin is no less than 10Hz, and localized data processing is achieved through edge computing nodes to reduce cloud transmission latency.

7. A smart regulation and energy storage optimization system for distributed energy systems, characterized in that, The system includes: The data acquisition unit is used to monitor the dust distribution and temperature data on the surface of the photovoltaic module in real time. The power generation correction unit is used to build a power generation efficiency correction model based on dust distribution data and temperature data, calculate the actual power generation attenuation according to the power generation efficiency correction model, and output the corrected theoretical power generation. The multi-objective optimization unit is used to establish a digital twin model based on the corrected theoretical power generation and energy storage operation data, and synchronize it with the energy storage system status and grid parameters; based on the digital twin model, a multi-objective optimization model is constructed to coordinate the power output strategies of each energy storage system in peak shaving and backup power scenarios. The energy storage configuration update unit is used to trigger the replanning algorithm to recalculate the energy storage capacity allocation and optimize the charging and discharging priority when the battery degradation exceeds the first preset threshold or the local grid load is unbalanced, and generate the final energy storage configuration scheme. The replanning algorithm is as follows: Based on the battery health state prediction model, the capacity decay rate is calculated: Where SOH represents the battery health status, and N... 循环 The charge-discharge cycle number is given, and k is the attenuation coefficient, with a value range of 0.005 ≤ k ≤ 0.

01. When the SOH is lower than the second preset threshold, the capacity redistribution strategy is triggered, and the load of the high-degradation battery is transferred to the low-degradation battery proportionally.

8. An electronic device, characterized in that, include: A processor and a memory, the memory being used to store computer program code, the computer program code including computer instructions, wherein when the processor executes the computer instructions, the electronic device performs the intelligent regulation and energy storage optimization method for distributed energy systems as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which includes program instructions that, when executed by a processor of an electronic device, cause the processor to perform the intelligent regulation and energy storage optimization method for distributed energy systems as described in any one of claims 1 to 6.

Images