Security operation and maintenance scheduling device and method for wind-solar-storage integrated system

Abstract

The invention relates to the technical field of power system operation and control, in particular to a safety operation and maintenance scheduling device and method for a wind, light and storage integrated system, and the device comprises a field sensing unit which is used for collecting the real-time operation data of wind, light and storage equipment; the edge calculation and autonomous control unit is used for local data processing, short-time prediction and emergency control when communication is abnormal or a safety index is out of limit; the central optimization and safety management platform is used for fusing and standardizing the data, evaluating the safety state of the system based on a double-domain safety redundancy index, evaluating energy storage life consumption through a coupling model, generating a scheduling instruction considering economical efficiency, safety and life by adopting opportunity constraint optimization, and sending the scheduling instruction to the central optimization and safety management platform; security verification and stable execution of the instruction are guaranteed through shadow simulation, strategy progressive switching and a security instruction shielding module; and the man-machine interaction application unit is used for visual monitoring, strategy recommendation and history redisk.

Description

Technical Field

[0001] This invention relates to the field of power system operation and control technology, specifically to a safety operation and maintenance dispatching device and method for integrated wind, solar and energy storage systems. Background Technology

[0002] With the large-scale integration of new energy sources, integrated wind-solar-storage systems, combining wind power, photovoltaics, and energy storage, are gradually becoming an important component of the power system. These systems improve energy efficiency and the absorption of clean energy by leveraging the synergistic effect of renewable energy and energy storage, providing new support for grid operation. At the same time, the complexity of system operation has increased significantly, placing higher demands on dispatching and maintenance.

[0003] In existing technologies, the scheduling of integrated wind, solar, and energy storage systems mainly relies on predictive models and conventional optimization methods, but these methods have the following shortcomings: First, traditional safety assessment methods mostly focus on steady-state indicators, making it difficult to balance dynamic stability and safety under sudden disturbances. Second, the lifespan consumption of energy storage batteries is not fully considered in most scheduling models, resulting in a lack of balance between economic efficiency and lifespan management. Furthermore, existing scheduling strategies are mostly implemented through direct replacement, lacking effective virtual verification and gradual switching mechanisms, which can easily lead to operational risks.

[0004] Therefore, a major technical problem that needs to be solved at present is how to achieve synergistic consideration of safety, economy and energy storage life in wind-solar-storage integrated systems, and to establish a scheduling method that can ensure operational safety and reduce the risk of strategy switching under uncertain conditions, thereby improving the overall operational reliability and stability of the system. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a safe operation and maintenance scheduling device and method for integrated wind, solar and energy storage systems, which addresses the shortcomings of the prior art. This method solves the technical problem that the existing scheduling strategies are mostly implemented by direct replacement, lacking effective virtual verification and gradual switching mechanisms.

[0006] The objective of this invention is achieved through the following technical solutions: In a first aspect, the present invention provides a safety operation and maintenance scheduling device for integrated wind-solar-storage systems, comprising: The field layer is used to collect multi-source operating data, which includes voltage, current, frequency, and energy storage unit status data. The edge layer is used to process and predict multi-source operational data, perform local processing and short-term prediction, and execute emergency control commands when communication is abnormal or local security indicators exceed limits. A central optimization and security management platform is communicatively connected to the edge layer. The central optimization and security management platform includes: The data governance module is used to fuse and standardize the received multi-source operational data; The comprehensive safety status assessment module is used to calculate a dual-domain safety margin index that reflects the steady-state, dynamic, and transient fault tolerance of the system based on standardized data. The online energy storage life assessment module is used to predict the life consumption of the energy storage unit based on the energy storage unit status data in the multi-source operation data of the field layer. The opportunity-constrained scheduling optimization module is used to construct a scheduling optimization model based on an optimization objective function, and generate optimized scheduling instructions according to the scheduling optimization model; the optimization objective of the optimization objective function is to minimize the operating economic cost and balance the priority of the dual-domain safety margin index and the lifetime consumption. The shadow simulation verification module is used to simulate the execution of the optimized scheduling instructions in a virtual environment and evaluate the corresponding security and economic indicators. The strategy progressive switching module is used to switch the optimized scheduling instruction to the actual operation and maintenance system for execution in stages when the evaluation result of the shadow simulation verification module meets the preset conditions.

[0007] As a further improvement of the present invention, the comprehensive safety status assessment module includes: The steady-state margin calculation unit is used to calculate the normalized distance between the operating point and the safety boundary based on real-time voltage, current and frequency data; the normalized distance is used to characterize the steady-state margin. The dynamic margin calculation unit is used to evaluate the disturbance recovery capability based on the small-signal stability analysis method and obtain the dynamic margin based on the evaluation results. The transient fault tolerance margin calculation unit is used to monitor the actual recovery time of the system after a sudden disturbance and compare it with the preset maximum allowable recovery time, and obtain the transient fault tolerance margin based on the comparison result. The comprehensive index fusion unit is used to perform weighted fusion of the steady-state margin, dynamic margin and transient fault tolerance margin to generate the dual-domain safety margin index.

[0008] As a further improvement of the present invention, the online energy storage lifetime assessment module includes: The coupling effect analysis unit is used to quantify the coupled effects of temperature, charge / discharge rate and state of charge on the battery aging rate. The lifetime consumption prediction unit is used to calculate the current lifetime consumption and cumulative lifetime consumption based on the output of the coupling effect analysis unit and real-time operating data, using a preset lifetime consumption rate function.

[0009] As a further improvement of the present invention, the objective function in the opportunity-constrained scheduling optimization module is:

[0010] In the formula, In order to manage economic costs, It is a dual-domain safety margin indicator; This is the energy storage lifetime consumption function, which is used to obtain the lifetime consumption of the energy storage unit. The weighting coefficients for the dual-domain safety margin index. These are the weighting coefficients of the energy storage lifetime consumption function, used to balance the priorities of safety and lifetime in scheduling.

[0011] As a further improvement of the present invention, the probabilistic safety constraint is: the probability of an event occurring when the safety index reaches or exceeds a preset threshold, and is greater than or equal to a preset risk control threshold.

[0012] As a further improvement of the present invention, the strategy progressive switching module performs phased switching including: During the monitoring and comparison phase, the simulation operation indicators generated by the shadow simulation verification module are compared with the actual system operation indicators in real time. During the partial trial operation phase, select a portion of controllable equipment to test the optimized scheduling instructions and monitor the corresponding operating indicators; During the full rollout phase, once the results of the partial trial operation phase are stable and meet safety requirements, the application scope of the optimized scheduling instructions will be gradually expanded to the entire station.

[0013] As a further improvement of the present invention, the shadow simulation verification module also switches the optimized scheduling instructions based on a rollback mechanism. The rollback mechanism is configured to automatically stop the switching and resume the execution of the original scheduling instructions when the dual-domain safety margin index is detected to be lower than the safety threshold or the lifetime consumption rate exceeds the upper limit during the switching process.

[0014] As a further improvement of the present invention, the central optimization and security management platform also includes a security instruction shielding module, which is configured as follows: A predefined set of safety constraints including voltage, current, frequency, safety margin, and lifetime attrition rate limits; The optimized scheduling instructions are compared with the set of security constraints; If the optimized scheduling instruction exceeds the set of security constraints, the optimized scheduling instruction will be corrected to the nearest feasible solution within the set, and violation information will be recorded.

[0015] As a further improvement of the present invention, the edge layer and the central optimization and security management platform interact according to a predefined collaborative security protocol. The protocol defines a normal state, an alert state, and an emergency state. In the emergency state, the edge computing and autonomous control unit takes over control and executes local emergency strategies.

[0016] As a further improvement of the present invention, the central optimization and security management platform also includes a human-computer interaction application unit, which is connected to the central optimization and security management platform and is used to provide visualized monitoring of system operation status, scheduling strategy recommendation and historical operation review functions.

[0017] Secondly, this invention provides a method for safe operation and maintenance scheduling of integrated wind-solar-storage systems, including: Collect multi-source operating data, including voltage, current, frequency, temperature, and state of charge; The multi-source operational data is preprocessed and short-term predicted through the edge layer, and emergency control is performed based on the local security status. The processed multi-source operational data is uploaded to the central optimization and security management platform; the data governance module integrates and standardizes the multi-source operational data, and based on the standardized multi-source operational data, the following steps are executed in parallel: The dual-domain security redundancy index of the current system is calculated through the security status comprehensive assessment module. The energy storage unit's lifespan is predicted using the online energy storage lifespan assessment module. Through the opportunity-constrained scheduling optimization module, an optimization objective function is constructed with the goal of minimizing the economic cost of operation and balancing the dual-domain safety margin index and the priority of lifetime consumption. The optimization objective function is solved to generate an optimized scheduling instruction. The performance of the optimized scheduling instruction is verified in a virtual environment using the shadow simulation verification module. If the verification is successful, the optimized scheduling instructions will be switched to the actual operation and maintenance system for execution in stages through the policy gradual switching module; if the verification fails or a rollback condition is triggered during the switching process, the original operation and maintenance instructions will be maintained or restored.

[0018] The beneficial effects of this invention are as follows: This invention provides a safety operation and maintenance scheduling device for integrated wind, solar and energy storage systems. It acquires basic data by collecting multi-source operation data at the field layer, performs local processing and short-term prediction on the aforementioned data at the edge layer, and executes emergency control when communication is abnormal or safety indicators exceed limits. The data governance module in the central optimization and safety management platform completes the fusion and standardization of real-time operation data. The comprehensive safety status assessment module calculates a dual-domain safety margin index reflecting the steady-state / dynamic / transient safety level of the system based on standardized data. The online energy storage life assessment module predicts life consumption by combining real-time temperature, charge / discharge rate and state of charge. The opportunity-constrained scheduling optimization module constructs an optimization objective that includes economic cost, dual-domain safety margin index and life consumption, and generates scheduling instructions by including probabilistic safety constraints. The shadow simulation verification module simulates the execution of scheduling instructions in a virtual environment and evaluates safety and economic indicators. The strategy progressive switching module switches instructions to the actual system in stages when the evaluation results meet preset conditions. Each technical feature corresponds to an independent technical effect in achieving comprehensive data acquisition, reliable local autonomous control, efficient data standardization and processing, multidimensional security assessment, accurate lifetime prediction, global scheduling optimization, effective command verification, security of policy switching, and compliance of commands. When they work together, they form a closed-loop control architecture that spans the entire chain of "data acquisition - edge autonomy - central optimization - command verification - secure execution". This architecture ensures the safe and stable operation of the system while achieving synergistic optimization of operational economy and energy storage lifetime. Compared with traditional single-dimensional control schemes, it has a stronger comprehensive performance improvement effect. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of the overall architecture of a safety operation and maintenance scheduling platform for an integrated wind, solar and energy storage system according to an embodiment of the present invention. Figure 2 This is a schematic diagram of the calculation process for a Dual Domain Safety Redundancy Index (DSRI) according to an embodiment of the present invention; Figure 3 This is a schematic diagram of an evaluation process for a coupled aging model of energy storage temperature-C rate-SOC according to an embodiment of the present invention.

[0021] Figure 4 This is an internal structural diagram of a computer device according to an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives and technical solutions of this invention clearer and easier to understand, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. The specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention.

[0023] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings and specific embodiments. The described embodiments are only some embodiments of the present invention, and not all embodiments.

[0024] This embodiment provides a safety operation and maintenance scheduling device for integrated wind, solar, and energy storage systems. The device includes a field layer, an edge layer, and a central optimization and safety management platform. The field layer collects multi-source operational data, including voltage, current, frequency, and energy storage unit status data, such as temperature, charge / discharge rate, and state of charge. The edge layer processes and predicts the multi-source operational data, performing local processing and short-term prediction, and executing emergency control commands in case of communication anomalies or exceeding local safety limits. The central optimization and safety management platform communicates with the edge layer and includes: a data governance module for fusing and standardizing the received multi-source operational data in real time; a comprehensive safety status assessment module for calculating a dual-domain safety margin index reflecting the system's steady-state, dynamic, and transient fault tolerance based on the standardized data; and an online energy storage life assessment module for evaluating the lifespan of the energy storage system based on the multi-source operational data from the field layer. Based on the real-time temperature, charge / discharge rate, and state of charge of the energy storage unit, the lifespan consumption of the energy storage unit is predicted; the opportunity-constrained scheduling optimization module is used to construct a scheduling optimization model based on the optimization objective function, and generate optimized scheduling instructions according to the scheduling optimization model; wherein, the optimization objective function aims to minimize the operating economic cost, balance the priority of the dual-domain safety margin index and the lifespan consumption; the shadow simulation verification module is used to simulate the execution of optimized scheduling instructions in a virtual environment and evaluate the corresponding safety and economic indicators; the strategy progressive switching module is used to switch the optimized scheduling instructions to the actual system for execution in stages when the evaluation results of the shadow simulation verification module meet the preset conditions, and has a rollback mechanism; the security instruction shielding module is used to perform security compliance checks and corrections on the optimized scheduling instructions before they are issued.

[0025] Basic data acquisition is achieved by collecting multi-source operational data (voltage, current, frequency, temperature, and state of charge) at the field layer. The edge layer performs local processing and short-term prediction on the aforementioned data and executes emergency control in case of communication anomalies or exceeding safety limits. The data governance module in the central optimization and safety management platform completes the fusion and standardization of real-time operational data. The comprehensive safety status assessment module calculates a dual-domain safety margin index reflecting the system's steady-state / dynamic / transient fault tolerance based on standardized data. The online energy storage life assessment module predicts lifespan consumption by combining real-time temperature, charge / discharge rate, and state of charge. The opportunity-constrained scheduling optimization module constructs an optimization objective that includes economic cost, dual-domain safety margin index, and lifespan consumption, and generates scheduling instructions using a model that includes probabilistic safety constraints. Shadow simulation verification is then performed. The verification module simulates the execution of scheduling commands in a virtual environment and evaluates safety and economic indicators. The policy gradual switching module switches commands to the actual system in stages and sets up a rollback mechanism when the evaluation results meet preset conditions. The safety command shielding module completes safety compliance checks and corrections before issuing commands. Each technical feature corresponds to the independent technical effects of comprehensive data acquisition, reliable local autonomous control, efficient data standardization processing, multidimensional safety assessment, accurate lifetime prediction, global scheduling optimization, effective command verification, policy switching security, and command compliance assurance. After working together, it achieves synergistic optimization of operating economy and energy storage lifetime while ensuring the safe and stable operation of the system. Compared with traditional single-dimensional control schemes, it has a stronger comprehensive performance improvement effect.

[0026] Example 1 This invention provides a safe operation and maintenance scheduling platform for integrated wind, solar and energy storage systems. It adopts a multi-layer architecture design and closed-loop operation process, aiming to solve the problems of insufficient steady-state and dynamic safety measurement, insufficient consideration of energy storage life consumption, lack of security verification for strategy deployment, and lack of autonomous capability under communication interruption in existing scheduling methods.

[0027] like Figure 1 As shown, the platform consists of a field layer, an edge layer, and a central optimization and security management platform. The central optimization and security management platform includes a platform layer and an application layer.

[0028] The field layer is deployed at wind farms, photovoltaic power stations and energy storage units, and collects multi-source data including electrical quantities, environmental quantities and equipment health status through sensors; The edge layer is responsible for data preprocessing, short-term forecasting, and rapid emergency response, enabling local autonomous control over emergencies; The platform layer is the core of the system, integrating modules such as data governance, prediction engine, safety margin assessment, energy storage aging model, opportunity constraint optimization, shadow scheduling simulation, gray-scale switching, and safety shielding reinforcement learning, which are used to perform integrated optimization scheduling that considers safety, economy, and lifespan on a global scale. The application layer presents safety margin curves, scheduling strategy recommendations, anomaly alarms, and historical replay information through a visual interface, providing auxiliary decision support for operation and maintenance personnel.

[0029] This platform operates according to a closed-loop logic of "perception—evaluation—optimization—execution—verification": First, the operational status is comprehensively perceived through the field layer and edge layer. Then, the platform layer assesses system safety and lifespan based on the Dual Domain Safety Redundancy Index (DSRI) and energy storage aging model. Subsequently, scheduling strategies are formulated under the opportunity-constrained optimization framework and verified in a digital twin environment through a shadow scheduling mechanism. Finally, the real strategy is gradually replaced through a gray-scale switch to ensure the safety and stability of the deployment process. Simultaneously, all scheduling strategies are constrained by a security-shielded reinforcement learning module to ensure that output actions always remain within the safety set. In the event of communication interruption or platform unavailability, the edge layer executes emergency measures according to preset security protocols, thereby achieving a comprehensive effect of coordinated steady-state and dynamic safety, balancing lifespan and economic objectives, and controllable strategy switching.

[0030] In summary, the safe operation and maintenance scheduling platform of this invention realizes the full life cycle safety measurement and optimized operation of the wind-solar-storage integrated system, which improves the level of new energy consumption while ensuring the stability and reliability of power system operation.

[0031] To more clearly illustrate the safety operation and maintenance scheduling platform of the integrated wind-solar-storage system described in this invention, its key functional modules will be described in detail below with reference to the accompanying drawings. Each module collaborates within the overall architecture, maintaining logical independence while forming a complete closed-loop operation system through data flow and control flow. For ease of understanding, this embodiment will proceed in the technical order of safety assessment, energy storage lifespan management, scheduling optimization, and operational assurance, providing a detailed description of the structure and working principle of each functional module.

[0032] like Figure 2 As shown in this embodiment, the safety margin assessment module set up at the platform layer is used to measure the operating status of the integrated wind-solar-storage system in real time. Its core is the Dual Domain Safety Margin Index (DSRI). This index quantifies the safety at different time scales, comprehensively reflecting the steady-state, dynamic, and transient safety levels of the system.

[0033] 1. Steady-state margin (SSM) Steady-state margin describes the relative distance between the current operating point and the safety boundary. Specifically, it evaluates operating parameters such as voltage, current, and frequency; as the operating point approaches its limit, the margin decreases. When the operating point enters the unsafe zone, the steady-state margin becomes negative. Its calculation can be simply expressed as the normalized difference between the operating point and the safety threshold.

[0034] 2. Dynamic Margin (DSM) Dynamic margin, based on small-signal stability analysis, primarily reflects the system's recovery capability after being subjected to disturbances. By constructing the system state matrix and calculating the real parts of its eigenvalues ​​and damping ratios, if the real parts of all eigenvalues ​​are less than zero and the minimum damping ratio is greater than a set threshold, it indicates that the system possesses good dynamic margin.

[0035] 3. Transient Fault Tolerance Margin (TFRM) Transient fault tolerance margin primarily measures the system's recovery speed after encountering sudden disturbances (such as inverter tripping, rapid cloud cover, or communication failure). When the system recovery time is less than the maximum allowable time, the transient fault tolerance margin is considered sufficient; otherwise, it is considered insufficient.

[0036] In this embodiment, steady-state margin, dynamic margin, and transient fault tolerance margin are combined in a weighted manner to form the final dual-domain safety margin index:

[0037] in, As an adjustable weighting coefficient, it can be flexibly set according to the operating scenario and scheduling objectives. For example, it can increase the weight of transient fault tolerance margin in a weak power grid with frequent disturbances.

[0038] Through the aforementioned DSRI index, this invention can characterize the safety level of the wind-solar-storage integrated system in real time and quantitatively, providing a reliable basis for subsequent opportunity-constrained optimization and shadow scheduling verification.

[0039] like Figure 3 As shown, in this embodiment, the platform layer introduces an energy storage battery aging model to predict and constrain the lifespan of the energy storage unit. This model comprehensively considers the battery's operating temperature, charge / discharge rate (C-rate), and state of charge (SOC) to achieve dynamic assessment of lifespan consumption.

[0040] Temperature factors: Increased temperature accelerates the rate of side reactions, leading to accelerated capacity decay; low temperature environments reduce battery activity and increase internal resistance.

[0041] C-rate factor: High-rate charging and discharging increases battery polarization and heat accumulation, shortening cycle life.

[0042] SOC factor: Maintaining a high SOC for a long time or frequent deep discharge will cause the battery's active materials to be depleted, thereby accelerating aging.

[0043] Based on long-term operation and experimental data, an energy storage lifetime consumption function is established:

[0044] in: Indicates the battery at time Temperature; Indicates the state of charge; Indicates the charge / discharge rate; This is a lifespan attrition rate function, determined by fitting experimental data. This represents the cumulative lifespan consumption.

[0045] In opportunity-constrained optimization, lifetime consumption is both part of the objective function and one of the constraints: In the objective function, the lifetime consumption term is optimized together with economic cost and safety indicators through weighting coefficients to avoid a sharp decline in battery life due to one-sided pursuit of cost optimization; In the constraints, the lifetime consumption per unit time is limited to not exceeding a threshold, thereby ensuring the long-term reliability of energy storage operation.

[0046] The introduction of this model allows the platform to dynamically balance the intensity of energy storage usage with lifespan degradation during scheduling. For example, it can allow higher discharge rates during peak electricity price periods and restrict overcharging and discharging during off-peak periods, thereby ensuring economic benefits while slowing down battery aging.

[0047] In this embodiment, the opportunity constraint optimization module set in the platform layer is used to formulate scheduling strategies under the condition that there are uncertainties in the wind-solar-storage integrated system. Its core objective is to achieve a dynamic balance between economy, safety and energy storage life.

[0048] This module establishes a joint optimization objective function:

[0049] in: Dispatch economic costs, including electricity purchase, wind and solar curtailment, and energy storage operation costs; Dual-domain safety margin index; Energy storage lifetime consumption function; Weighting coefficients are used to balance the priority of safety and lifetime in scheduling.

[0050] Through the above functions, the platform not only pursues the lowest cost when optimizing scheduling, but also takes into account system security and energy storage life.

[0051] 2. Opportunity Constraints To address the uncertainties in wind and solar power output and load forecasting, the optimization model introduces probabilistic constraints:

[0052] in: Safety threshold; The permissible risk level is usually set to 0.05 to 0.1.

[0053] This constraint ensures that, in most scenarios, the system's safety margin remains above the threshold, thereby improving the robustness of scheduling.

[0054] 3. Uncertainty Modeling To accurately characterize the correlation between wind power, photovoltaic power, and load, this embodiment uses a Copula function to construct a joint distribution, capturing the correlation between different random variables. In high-dimensional scenarios, VineCopula can be used to decompose and model the correlation, thereby obtaining a scenario set that more closely matches actual statistical laws.

[0055] In some scenarios, where the predicted distribution has a large deviation, this embodiment further introduces the Distributed Bar Optimization (DRO) method. By constructing an uncertainty set around the probability distribution, the scheduling strategy can still meet safety and lifetime constraints even in the worst case.

[0056] Through the above-mentioned opportunity-constrained optimization mechanism, the present invention can achieve synergistic optimization among economy, safety and life management, and has robustness and adaptability in uncertain environments.

[0057] In this embodiment, the platform layer includes a shadow scheduling module and a gray-scale switching module, which are used to reduce the risk of directly launching new scheduling strategies and ensure a smooth and safe scheduling process.

[0058] The shadow scheduling module runs in parallel within a digital twin sandbox, and its input data is completely consistent with the actual scheduling, including wind and solar power forecasts, equipment operating status, and energy storage SOC. The shadow scheduling generates independent scheduling schemes, but does not directly apply them to the actual equipment; it is only used for comparison and verification.

[0059] During operation, the platform compares the shadow scheduling results with the current execution strategy to calculate key indicators such as economic cost, DSRI safety margin, and energy storage lifetime consumption.

[0060] If shadow scheduling exhibits higher safety margins, lower economic costs, or a more reasonable lifespan consumption rate over a continuous period of time, and does not trigger safety threshold violations, it is determined to have the potential to go live. At this point, the gray-scale switching module will initiate the strategy replacement process.

[0061] The gray-scale switching is divided into three stages: monitoring stage: the shadow scheduling scheme is only used for comparative analysis and does not affect the actual execution; local application stage: the new scheme is tested on a small scale in some wind turbines, photovoltaic arrays or energy storage units, and the indicators are monitored in real time; full-scale switching stage: after the local operation results are stable, the application scope is gradually expanded, and finally the scheduling replacement is realized throughout the entire site.

[0062] If, during the gray-scale switching process, the DSRI index is detected to drop beyond the preset threshold, or the energy storage lifespan is consumed too quickly, the system will immediately trigger a rollback mechanism to restore the stable strategy of the previous version, thus avoiding large-scale operational risks.

[0063] By using shadow scheduling and gray-scale switching, this invention can fully verify and gradually deploy new scheduling strategies without affecting the safe operation of the system, greatly reducing the uncertainty risks caused by direct replacement.

[0064] In this embodiment, the platform layer and the edge layer communicate and control each other through the Adaptive Edge–Center Security Protocol (AESP) to ensure that the system can still operate securely in the event of communication failures, network latency, or platform failure.

[0065] AESP uses a finite state machine approach and defines four operating states: Normal state: When communication is uninterrupted, the edge layer executes the scheduling strategy issued by the platform and transmits operational data back in real time. Alert state: When the DSRI is detected to be approaching the safety threshold, the edge layer immediately sends an early warning signal to the platform and prepares to switch to a local emergency strategy.

[0066] Emergency State: When the DSRI falls below the safety threshold or communication is interrupted, the edge layer independently executes emergency control measures, including rapid power reduction, rapid energy storage support, and controllable load reduction. Recovery State: After the platform restores communication and takes over control, the edge layer gradually exits emergency mode and returns to normal state.

[0067] According to the data interaction mechanism stipulated in the agreement, the system adopts periodic bidirectional communication: on the one hand, the edge layer needs to periodically upload real-time operating data (including voltage, current, frequency, SOC, temperature, etc.), the current value and trend of DSRI, and short-term prediction residuals; on the other hand, the platform layer is responsible for issuing scheduling strategies and power allocation plans, safety threshold settings, and control commands such as grayscale switching.

[0068] In an emergency, the edge layer quickly implements the following measures: Rapid power reduction: Reduces the output of wind turbines and photovoltaic inverters to avoid exceeding limits. Energy storage support: Schedules energy storage units to discharge rapidly to increase frequency or absorbs excess energy to alleviate overvoltage. Load shedding: Temporarily reduces or shifts peak loads of the microgrid to manageable loads.

[0069] When the primary link fails, it automatically switches to the backup communication link.

[0070] If communication delays are too long, the edge layer can use the latest cached scheduling instructions; if communication is completely interrupted, the edge layer will run contingency strategies independently.

[0071] Through the edge-center collaborative security protocol, this invention can still maintain the safe operation of the wind, solar and energy storage system by relying on edge autonomy when the network is unstable or the platform is unavailable, thus realizing the organic combination of centralized optimization and distributed emergency response.

[0072] In this embodiment, the platform layer also includes a Safe-RL-Shield module, which is used to impose safety constraints on the output actions during the process of optimizing the scheduling strategy through deep reinforcement learning, so as to ensure that the scheduling instructions are always within the safe set.

[0073] The scheduling optimization employs deep reinforcement learning algorithms (such as DQN, DDPG, or PPO), taking operational status data and predicted scenarios as input, and outputting action vectors including energy storage power scheduling, wind and solar power output limits, and load response. These actions must be verified by a safety shielding module before execution.

[0074] The system predefines a safety set, including the following constraints: voltage, current, and frequency do not exceed limits; DSRI is not lower than the safety threshold; and energy storage lifetime consumption rate does not exceed the set upper limit.

[0075] If the actions output by the reinforcement learning policy exceed the set, the security shielding module performs projection: that is, maps the actions to the nearest safe solution region to ensure that the issued instructions do not compromise system security.

[0076] Each projection correction generates a marker, recording the type of constraint violation (such as "voltage limit exceeded", "frequency drop", "lifetime consumption exceeded", "DSRI insufficient"), and writes it to the log database. These records facilitate review by operations and maintenance personnel and can also serve as training samples for subsequent improvements to the reinforcement learning model.

[0077] The platform layer periodically invokes formal verification tools to perform logical completeness checks on the security set, ensuring that there are no uncovered potential risk conditions. Simultaneously, a lightweight security shielding module copy is deployed at the edge layer, enabling projection correction of local scheduling actions even during communication interruptions, ensuring action security in emergency situations.

[0078] By using a security-shielded reinforcement learning mechanism, this invention retains the optimization effect of deep reinforcement learning while avoiding the security risks that may be caused by policy uncertainty, ensuring the controllability and interpretability of the scheduling process, and further improving the overall security and robustness of the platform.

[0079] In summary, the integrated wind-solar-storage safety operation and maintenance scheduling method proposed in this embodiment constructs a bottom-up, multi-layered scheduling system based on a closed-loop logic of "perception—assessment—optimization—verification—execution." Through multi-source data acquisition at the field layer, local rapid response at the edge layer, safety assessment and optimization scheduling at the platform layer, and visualization at the application layer, it achieves end-to-end perception and management of operational data.

[0080] In the detailed description, the proposed Dual Domain Safety Redundancy Index (DSRI) provides a quantitative assessment method for system safety, the coupled aging model of energy storage temperature-C rate-SOC ensures the sustainability of energy storage use, the opportunity-constrained optimization mechanism achieves a multi-objective balance of economy, safety and lifetime management, the shadow scheduling and gray-scale switching strategy reduces the risk of new schemes going online, the edge-center collaborative security protocol enhances the system's autonomy under communication anomalies, and the security shielding reinforcement learning further ensures the security and interpretability of scheduling instructions.

[0081] Therefore, through the comprehensive application of the above-mentioned technical means, this invention achieves a coordinated unity of safety, reliability, economy and lifespan management of the integrated wind-solar-storage system. It can not only effectively improve the level of new energy consumption, but also enhance the stable operation capability of the power system under uncertain conditions, and has good prospects for promotion and application.

[0082] Example 3 In another embodiment of the present invention, a computer-readable storage medium is provided as a storage component within a terminal device, the function of which is to store programs and data. It should be noted that the computer-readable storage medium here encompasses not only the built-in storage components of the terminal device but also extended storage components supported by the device. Essentially, it is a tangible medium capable of containing or storing programs that can be invoked by or in conjunction with an instruction execution system, device, or apparatus. This storage medium provides storage areas for the terminal's operating system and stores one or more instructions suitable for processor loading and execution, which can constitute one or more computer programs containing program code.

[0083] Specifically, examples of computer-readable storage media (a non-exclusive list) include: electrical connections with one or more wires, portable disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable optical disc read-only memory, optical storage devices, magnetic storage devices, or any reasonable combination of the above types.

[0084] The storage medium may also include data signals propagated as part of a baseband portion or a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any reasonable combination of both. Furthermore, computer-readable storage medium may also refer to other readable media besides conventional readable storage media, capable of sending, propagating, or transmitting programs for use or operation by an instruction execution system, apparatus, or device. Program code on the storage medium can be transmitted via any suitable medium, including but not limited to wireless, wired, optical fiber, or any reasonable combination thereof.

[0085] The program code used to implement the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C. The execution modes of the program code include: running entirely on the user's computing device, running partially on the user's device as a standalone software package, running partially in a distributed manner on both the user's device and a remote computing device, or running entirely on a remote computing device or server. When a remote computing device is involved, the device can be connected to the user's computing device via any type of network such as a local area network (LAN) or a wide area network (WAN), or connected to an external computing device via the Internet through an Internet service provider.

[0086] The processor is capable of loading and executing one or more instructions stored in a computer-readable storage medium to implement the corresponding steps of the safety operation and maintenance scheduling method for an integrated wind, solar and energy storage system as described in Embodiment 1.

[0087] Example 4 Figure 4 This is a schematic diagram of a computer device provided according to an embodiment of the present invention.

[0088] Please see Figure 4 The terminal device is a computer device. In this embodiment, the computer device 60 includes a processor 61, a memory 62, and a computer program 63 stored in the memory 62 and executable on the processor 61. When executed by the processor 61, the computer program 63 implements the safety operation and maintenance scheduling method for the integrated wind-solar-storage system described in this embodiment. To avoid repetition, these details are not elaborated here. Alternatively, when executed by the processor 61, the computer program 63 implements the functions of each model / unit in the computing system that constitutes the safety operation and maintenance scheduling method for the integrated wind-solar-storage system described in this embodiment. To avoid repetition, these details are not elaborated here.

[0089] Computer device 60 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. Computer device 60 may include, but is not limited to, a processor 61 and a memory 62. Those skilled in the art will understand that... Figure 4This is merely an example of computer device 60 and does not constitute a limitation on computer device 60. It may include more or fewer components than shown, or combine certain components, or different components. For example, computer device may also include input / output devices, network access devices, buses, etc.

[0090] The processor 61 may be a central processing unit (CPU), or other general-purpose processors, CPUs, graphics processing units (GPUs), 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, quantum computing-based data processing logic units, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0091] The memory 62 can be an internal storage unit of the computer device 60, such as a hard disk or RAM of the computer device 60. The memory 62 can also be an external storage device of the computer device 60, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc., equipped on the computer device 60.

[0092] Furthermore, the memory 62 may include both internal storage units of the computer device 60 and external storage devices. The memory 62 is used to store computer programs and other programs and data required by the computer device. The memory 62 can also be used to temporarily store data that has been output or will be output.

[0093] Any references to memory, databases, or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (Read-Only Memory). Memory includes ROM, magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0094] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

Claims

1. A safety operation and maintenance scheduling device for integrated wind-solar-storage systems, characterized in that, include: The field layer is used to collect multi-source operating data, which includes voltage, current, frequency, and energy storage unit status data. The edge layer is used to process and predict multi-source operational data, perform local processing and short-term prediction, and execute emergency control commands when communication is abnormal or local security indicators exceed limits. A central optimization and security management platform is communicatively connected to the edge layer. The central optimization and security management platform includes: The data governance module is used to fuse and standardize the received multi-source operational data; The comprehensive safety status assessment module is used to calculate a dual-domain safety margin index that reflects the steady-state, dynamic, and transient fault tolerance of the system based on standardized data. The online energy storage life assessment module is used to predict the life consumption of the energy storage unit based on the energy storage unit status data in the multi-source operation data of the field layer. The opportunity-constrained scheduling optimization module is used to construct a scheduling optimization model based on an optimization objective function, and generate optimized scheduling instructions according to the scheduling optimization model; the optimization objective of the optimization objective function is to minimize the operating economic cost and balance the priority of the dual-domain safety margin index and the lifetime consumption. The shadow simulation verification module is used to simulate the execution of the optimized scheduling instructions in a virtual environment and evaluate the corresponding security and economic indicators. The strategy progressive switching module is used to switch the optimized scheduling instruction to the actual operation and maintenance system for execution in stages when the evaluation result of the shadow simulation verification module meets the preset conditions.

2. The safety operation and maintenance scheduling device for integrated wind, solar, and energy storage systems according to claim 1, characterized in that, The comprehensive security status assessment module includes: The steady-state margin calculation unit is used to calculate the normalized distance between the operating point and the safety boundary based on real-time voltage, current and frequency data; the normalized distance is used to characterize the steady-state margin. The dynamic margin calculation unit is used to evaluate the disturbance recovery capability based on the small-signal stability analysis method and obtain the dynamic margin based on the evaluation results. The transient fault tolerance margin calculation unit is used to monitor the actual recovery time of the system after a sudden disturbance and compare it with the preset maximum allowable recovery time, and obtain the transient fault tolerance margin based on the comparison result. The comprehensive index fusion unit is used to perform weighted fusion of the steady-state margin, dynamic margin and transient fault tolerance margin to generate the dual-domain safety margin index.

3. The safety operation and maintenance scheduling device for integrated wind, solar, and energy storage systems according to claim 1, characterized in that, The online energy storage lifetime assessment module includes: The coupling effect analysis unit is used to quantify the coupled effects of temperature, charge / discharge rate and state of charge on the battery aging rate. The lifetime consumption prediction unit is used to calculate the current lifetime consumption and cumulative lifetime consumption based on the output of the coupling effect analysis unit and real-time operating data, using a preset lifetime consumption rate function.

4. The safety operation and maintenance scheduling device for integrated wind, solar, and energy storage systems according to claim 1, characterized in that, In the opportunity-constrained scheduling optimization module, the objective function is: In the formula, In order to manage economic costs, It is a dual-domain safety margin indicator; This is the energy storage lifetime consumption function, which is used to obtain the lifetime consumption of the energy storage unit. The weighting coefficients for the dual-domain safety margin index. These are the weighting coefficients of the energy storage lifetime consumption function, used to balance the priorities of safety and lifetime in scheduling.

5. The safety operation and maintenance scheduling device for integrated wind, solar, and energy storage systems according to claim 1, characterized in that, The phased switching of the strategy transition module includes: During the monitoring and comparison phase, the simulation operation indicators generated by the shadow simulation verification module are compared with the actual system operation indicators in real time. During the partial trial operation phase, select a portion of controllable equipment to test the optimized scheduling instructions and monitor the corresponding operating indicators; During the full rollout phase, once the results of the partial trial operation phase are stable and meet safety requirements, the application scope of the optimized scheduling instructions will be gradually expanded to the entire station.

6. The safety operation and maintenance scheduling device for integrated wind, solar, and energy storage systems according to claim 1, characterized in that, The shadow simulation verification module also switches and optimizes the scheduling instructions based on a rollback mechanism. The rollback mechanism is configured to automatically stop the switching and resume the execution of the original scheduling instructions when the dual-domain safety margin index is detected to be lower than the safety threshold or the lifetime consumption rate exceeds the upper limit during the switching process.

7. The safety operation and maintenance scheduling device for integrated wind-solar-storage systems according to any one of claims 1 to 6, characterized in that, The central optimization and security management platform also includes a security command blocking module, which is configured as follows: A predefined set of safety constraints including voltage, current, frequency, dual-domain safety margin indicators, and lifetime attrition rate limits; The optimized scheduling instructions are compared with the set of security constraints; If the optimized scheduling instruction exceeds the set of security constraints, the optimized scheduling instruction will be corrected to the nearest feasible solution within the set, and violation information will be recorded.

8. The safety operation and maintenance scheduling device for integrated wind, solar, and energy storage systems according to claim 1, characterized in that, The edge layer interacts with the central optimization and security management platform according to a predefined collaborative security protocol. The protocol defines a normal state, an alert state, and an emergency state. In the emergency state, the edge computing and autonomous control unit takes over control and executes local emergency strategies.

9. The safety operation and maintenance scheduling device for integrated wind-solar-storage systems according to claim 1, characterized in that, The central optimization and security management platform also includes a human-computer interaction application unit, which is connected to the central optimization and security management platform to provide visualized monitoring of system operation status, scheduling strategy recommendation, and historical operation review functions.

10. A method for safe operation and maintenance scheduling of integrated wind-solar-storage systems, characterized in that, include: Collect multi-source operating data, including voltage, current, frequency, temperature, and state of charge; The multi-source operational data is preprocessed and short-term predicted through the edge layer, and emergency control is performed based on the local security status. The processed multi-source operational data is uploaded to the central optimization and security management platform. The data governance module integrates and standardizes multi-source operational data, and based on the standardized multi-source operational data, the following steps are executed in parallel: The dual-domain security redundancy index of the current system is calculated through the security status comprehensive assessment module. The energy storage unit's lifespan is predicted using the online energy storage lifespan assessment module. The opportunity-constrained scheduling optimization module constructs an optimization objective function with the goal of minimizing the operating economic cost, balancing the dual-domain safety margin index and the priority of lifetime consumption, and solves the optimization objective function to generate optimized scheduling instructions. The performance of the optimized scheduling instruction is verified in a virtual environment using the shadow simulation verification module. If the verification is successful, the optimized scheduling instruction will be switched to the actual operation and maintenance system for execution in stages through the strategy gradual switching module. If the verification fails or a rollback condition is triggered during the switchover process, the original operation and maintenance instructions will be maintained or restored.

Images