A flexible load regulation method and system for microgrids

Abstract

The present invention belongs to the field of flexible load regulation and discloses a flexible load regulation method and system applied to a microgrid. According to the real-time operating status data of the microgrid, a data fusion algorithm is adopted to comprehensively analyze the multi-source heterogeneous data of load power and power output to obtain a comprehensive operating status evaluation result of the microgrid; based on the comprehensive operating status evaluation result, the various types of loads in the microgrid are identified and classified through a load characteristic recognition algorithm, and the power consumption characteristic parameters of different types of loads are obtained, including the priority, power consumption habits, and regulation characteristics of the load; the load allocation strategy rapid response mechanism is based on preset response rules, and according to the power output fluctuation amplitude and load priority, the load power adjustment amount is quickly calculated, and the adjustment instructions are issued in real time through the energy management system to ensure the power balance and stable operation of the microgrid.

Description

Technical Field

[0001] The present invention relates to the technical field of flexible load regulation, and in particular to a flexible load regulation method and system applied to a microgrid. Background Art

[0002] Microgrids contain a variety of load types, such as critical loads, controllable loads, and interruptible loads. Each type of load has distinct requirements for power quality and reliability. During real-time microgrid operation, both load power and power output dynamically change. To ensure stable and economical microgrid operation, loads must be optimally allocated based on these characteristics. However, the regulation characteristics of different load types vary significantly. For example, critical loads require continuous power supply, while interruptible loads can be interrupted within specific time periods. Furthermore, load allocation must consider multiple factors, including load priority, electricity usage habits, and electricity pricing policies. Therefore, developing a reasonable load allocation strategy based on the real-time operational state of the microgrid and comprehensive consideration of various constraints is a pressing technical challenge. This strategy coordinates the operation of different load types, achieves a dynamic balance between load and power output, improves the energy efficiency and economical operation of the microgrid, and simultaneously addresses the power quality and reliability requirements of the loads. Summary of the Invention

[0003] In order to solve the above technical problems, the present invention provides a flexible load regulation method and system applied to microgrids, which realizes intelligent and precise regulation of microgrid loads and improves system operation efficiency and reliability.

[0004] The present invention provides a flexible load regulation method applied to a microgrid, the method comprising:

[0005] Based on the real-time operating status data of the microgrid, a data fusion algorithm is used to comprehensively analyze the multi-source heterogeneous data of load power and power output to obtain the comprehensive operating status evaluation results of the microgrid;

[0006] Based on the comprehensive operation status assessment results, the load characteristics identification algorithm is used to identify and classify various loads in the microgrid and obtain the power consumption characteristic parameters of different types of loads;

[0007] Combined with the load's power consumption characteristic parameters, the power quality analysis algorithm is used to conduct real-time evaluation of the microgrid's power quality indicators;

[0008] Based on the power quality assessment results, combined with load priority and electricity price policy factors, a load dispatch strategy optimization model is constructed to optimize the power allocation of controllable loads and interruptible loads while ensuring continuous power supply to critical loads;

[0009] Based on the load allocation strategy optimization results, power dispatch instructions for various loads are generated, and load power is regulated in real time. During the regulation process, changes in power output are continuously monitored. When power output fluctuates, the load allocation strategy rapid response mechanism is activated;

[0010] The load dispatch strategy quick response mechanism is based on preset response rules. It calculates the load power adjustment amount according to the power output fluctuation amplitude and load priority to ensure the power balance and stable operation of the microgrid.

[0011] Preferably, based on the real-time operating status data of the microgrid, a data fusion algorithm is used to comprehensively analyze the multi-source heterogeneous data of load power and power output to obtain the comprehensive operating status evaluation results of the microgrid including:

[0012] Obtain real-time operating status data of each component of the microgrid;

[0013] Preprocess the acquired multi-source heterogeneous data and convert the data into a unified format;

[0014] The Kalman filter algorithm is used to fuse the pre-processed data to obtain an estimate of the overall operating status of the microgrid;

[0015] According to the fused estimated values ​​of the microgrid operation status, key indicators reflecting the microgrid operation characteristics are extracted;

[0016] Compare the extracted key indicators with preset thresholds to evaluate the operating status of the microgrid;

[0017] If key indicators exceed the normal range, the early warning mechanism will be triggered, the warning level will be determined according to the degree of deviation, and an operation status assessment report will be generated;

[0018] The operation status assessment report details the specific values, normal ranges, and deviations of each key indicator of the microgrid, providing a basis for decision-making for dispatchers.

[0019] Preferably, based on the comprehensive operating status evaluation results, various types of loads in the microgrid are identified and classified through a load characteristic identification algorithm, and the power consumption characteristic parameters of different types of loads are obtained, including:

[0020] Obtain real-time operation data of the microgrid by comprehensively evaluating its operation status;

[0021] Based on the acquired microgrid operating status data, a load characteristic recognition algorithm based on machine learning is used to identify and classify various loads in the microgrid and obtain labels for different types of loads.

[0022] For the different types of loads identified, the power consumption characteristic parameters of each type of load are obtained by analyzing the historical power consumption data.

[0023] Preferably, combining the power consumption characteristic parameters of the load and using the power quality analysis algorithm to perform real-time evaluation of the power quality indicators of the microgrid includes:

[0024] Obtain real-time operating data of the microgrid and the power demand and characteristic parameters of different types of loads;

[0025] The acquired data is fed into a pre-built power quality assessment model, which uses a support vector machine algorithm and is obtained by training historical data;

[0026] The model outputs real-time evaluation values ​​of various power quality indicators;

[0027] The evaluation value of the power quality index is compared with the preset quality threshold to determine whether the current power quality meets the power supply requirements of different loads.

[0028] Preferably, based on the power quality assessment results, combined with load priority and electricity price policy factors, a load dispatch strategy optimization model is constructed to optimize the power distribution of controllable loads and interruptible loads while ensuring continuous power supply to critical loads. The optimization includes:

[0029] Obtain power quality assessment results, load priority data, and electricity price policy information, and determine critical loads, controllable loads, and interruptible loads based on the power quality assessment results;

[0030] Based on the load priority data, a clustering algorithm is used to classify the loads and obtain a set of loads with different priorities;

[0031] Based on electricity price policy information, a load dispatch optimization model considering electricity price factors is constructed, with load priority and electricity price factors as model constraints;

[0032] With the optimization goals of maximizing energy utilization efficiency and minimizing operating costs, a multi-objective optimization model is established, and power balance and voltage limit constraints are set;

[0033] The particle swarm optimization algorithm is used to solve the multi-objective optimization model and the Pareto optimal solution set is obtained through iterative search;

[0034] Select the optimal allocation plan that balances energy utilization efficiency and operating costs from the Pareto optimal solution set and determine the power allocation for each load;

[0035] Generate load dispatch control instructions, perform power control on controllable loads and interruptible loads according to the optimization results, and monitor load responses to ensure continuous power supply to critical loads.

[0036] Preferably, based on the load allocation strategy optimization results, power dispatch instructions for various loads are generated, and load power is regulated in real time. During the regulation process, changes in power output are continuously monitored. When power output fluctuates, a rapid response mechanism for the load allocation strategy is initiated, including:

[0037] After receiving the power dispatch instruction, each load control unit uses the PID control algorithm to adjust the actual operating power of each load according to the power value in the instruction, thus realizing real-time control of the load power;

[0038] During the load power control process, the power output data is continuously collected and the data analysis algorithm is used to determine whether the power output fluctuates.

[0039] If the power output fluctuation exceeds the preset threshold, the load allocation strategy rapid response mechanism is triggered;

[0040] After the rapid response mechanism is activated, a heuristic optimization algorithm is used to quickly calculate the load power adjustment plan based on the power output fluctuation and load priority, and generate a new load power dispatch instruction;

[0041] The newly generated load power dispatching instructions are sent to the corresponding load control units through the microgrid energy management system. The load control units quickly adjust the operating power of each load according to the new instructions to achieve dynamic balance of load power.

[0042] During the dynamic balancing of load power, the power output and load power data are continuously monitored, and an adaptive control algorithm is used to dynamically optimize the load power control parameters.

[0043] According to the evaluation results of load regulation effect, the reinforcement learning algorithm is used to perform self-learning optimization on the load dispatching strategy to realize adaptive optimization control of microgrid energy management.

[0044] Preferably, the load dispatching strategy rapid response mechanism calculates the load power adjustment amount based on the preset response rules according to the power output fluctuation amplitude and load priority to ensure the power balance and stable operation of the microgrid, including:

[0045] Obtain real-time data on power output and calculate and judge the fluctuation range of power output;

[0046] Determine the priority adjustment order of each load according to the preset load priority rules;

[0047] Through a fast response mechanism, the power adjustment amount of each load is calculated according to the power output fluctuation amplitude and load priority;

[0048] The calculated load power adjustment amount is sent to each load control unit in real time through the energy management system;

[0049] After receiving the adjustment instruction, each load control unit quickly performs power adjustment to achieve dynamic allocation of load power.

[0050] The present invention also provides a flexible load regulation system for microgrids, the system being used to implement any one of the methods described above, comprising: a comprehensive operating status assessment module, a load characteristics identification module, a power quality analysis module, a load dispatching strategy optimization module, a load power scheduling module, and a rapid response mechanism module;

[0051] The comprehensive operation status evaluation module is used to comprehensively analyze the load power and power output multi-source heterogeneous data based on the real-time operation status data of the microgrid using a data fusion algorithm to obtain a comprehensive operation status evaluation result of the microgrid;

[0052] The load characteristic identification module is used to identify and classify various types of loads in the microgrid based on the comprehensive operation status evaluation results and obtain power consumption characteristic parameters of different types of loads through the load characteristic identification algorithm;

[0053] The power quality analysis module is used to combine the power consumption characteristic parameters of the load and adopt the power quality analysis algorithm to perform real-time evaluation of the power quality indicators of the microgrid;

[0054] The load dispatch strategy optimization module is used to construct a load dispatch strategy optimization model based on the power quality assessment results, combined with load priority and electricity price policy factors, to optimize the power distribution of controllable loads and interruptible loads while ensuring continuous power supply to key loads;

[0055] The load power scheduling module is used to generate power scheduling instructions for various loads based on the load allocation strategy optimization results, and to regulate the load power in real time. During the regulation process, it continuously monitors the changes in power output. When the power output fluctuates, it activates the load allocation strategy rapid response mechanism;

[0056] The quick response mechanism module is used for the load allocation strategy. The quick response mechanism is based on preset response rules and calculates the load power adjustment amount according to the power output fluctuation amplitude and load priority to ensure the power balance and stable operation of the microgrid.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] The present invention discloses a method for intelligent control of microgrids based on load characteristics. The method comprehensively evaluates the operating status of the microgrid through a data fusion algorithm, and classifies various types of loads using a load characteristic identification algorithm. In combination with load characteristic parameters, the present invention uses a power quality analysis algorithm to evaluate the power supply quality in real time, and triggers load allocation strategy optimization when the requirements are not met. The optimization process takes into account factors such as load priority and electricity price policy, and uses a multi-objective optimization algorithm to generate a load allocation plan, maximizing energy utilization efficiency and minimizing operating costs while ensuring power supply to critical loads. The present invention also includes a fast response mechanism that can adjust the load power in real time according to power output fluctuations to ensure power balance and stable operation of the microgrid. The method realizes intelligent and precise control of microgrid loads and improves system operation efficiency and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0060] Figure 1 A flow chart of a flexible load regulation method applied to a microgrid according to an embodiment of the present invention; DETAILED DESCRIPTION

[0061] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0062] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should have the usual meanings understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in the embodiments of the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative position relationships. When the absolute position of the described object changes, the relative position relationship may also change accordingly.

[0063] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0064] Example 1

[0065] like Figure 1 As shown, an embodiment of the present invention provides a flexible load regulation method applied to a microgrid, the method comprising:

[0066] Based on the real-time operating status data of the microgrid, a data fusion algorithm is used to comprehensively analyze the multi-source heterogeneous data of load power and power output to obtain the comprehensive operating status evaluation results of the microgrid;

[0067] Based on the comprehensive operation status assessment results, the load characteristics identification algorithm is used to identify and classify various loads in the microgrid and obtain the power consumption characteristic parameters of different types of loads;

[0068] Combined with the load's power consumption characteristic parameters, the power quality analysis algorithm is used to conduct real-time evaluation of the microgrid's power quality indicators;

[0069] Based on the power quality assessment results, combined with load priority and electricity price policy factors, a load dispatch strategy optimization model is constructed to optimize the power allocation of controllable loads and interruptible loads while ensuring continuous power supply to critical loads;

[0070] Based on the load allocation strategy optimization results, power dispatch instructions for various loads are generated, and load power is regulated in real time. During the regulation process, changes in power output are continuously monitored. When power output fluctuates, the load allocation strategy rapid response mechanism is activated;

[0071] The load dispatch strategy quick response mechanism is based on preset response rules. It calculates the load power adjustment amount according to the power output fluctuation amplitude and load priority to ensure the power balance and stable operation of the microgrid.

[0072] In this embodiment, based on the real-time operating status data of the microgrid, a data fusion algorithm is used to comprehensively analyze the multi-source heterogeneous data of load power and power output to obtain the comprehensive operating status evaluation results of the microgrid, including:

[0073] Obtain real-time operating status data of each component of the microgrid;

[0074] Preprocess the acquired multi-source heterogeneous data and convert the data into a unified format;

[0075] The Kalman filter algorithm is used to fuse the pre-processed data to obtain an estimate of the overall operating status of the microgrid;

[0076] According to the fused estimated values ​​of the microgrid operation status, key indicators reflecting the microgrid operation characteristics are extracted;

[0077] Compare the extracted key indicators with preset thresholds to evaluate the operating status of the microgrid;

[0078] If key indicators exceed the normal range, the early warning mechanism will be triggered, the warning level will be determined according to the degree of deviation, and an operation status assessment report will be generated;

[0079] The operation status assessment report details the specific values, normal ranges, and deviations of each key indicator of the microgrid, providing a basis for decision-making for dispatchers.

[0080] In this embodiment, based on the comprehensive operating status evaluation results, various types of loads in the microgrid are identified and classified through a load characteristics identification algorithm. The power consumption characteristic parameters of different types of loads are obtained, including:

[0081] Obtain real-time operation data of the microgrid by comprehensively evaluating its operation status;

[0082] Based on the acquired microgrid operating status data, a load characteristic recognition algorithm based on machine learning is used to identify and classify various loads in the microgrid and obtain labels for different types of loads.

[0083] For the different types of loads identified, the power consumption characteristic parameters of each type of load are obtained by analyzing the historical power consumption data.

[0084] In this embodiment, the power quality analysis algorithm is used in combination with the power consumption characteristic parameters of the load to perform real-time evaluation of the power quality indicators of the microgrid, including:

[0085] Obtain real-time operating data of the microgrid and the power demand and characteristic parameters of different types of loads;

[0086] The acquired data is input into a pre-built power quality assessment model, which is obtained by training historical data using a support vector machine algorithm; wherein the power quality assessment model is constructed using a support vector machine algorithm;

[0087] The model outputs real-time evaluation values ​​of various power quality indicators;

[0088] The evaluation value of the power quality index is compared with the preset quality threshold to determine whether the current power quality meets the power supply requirements of different loads.

[0089] In this embodiment, based on the power quality assessment results, combined with load priority and electricity price policy factors, a load dispatch strategy optimization model is constructed. While ensuring continuous power supply to critical loads, the power allocation of controllable loads and interruptible loads is optimized, including:

[0090] Obtain power quality assessment results, load priority data, and electricity price policy information, and determine critical loads, controllable loads, and interruptible loads based on the power quality assessment results;

[0091] Based on the load priority data, a clustering algorithm is used to classify the loads and obtain a set of loads with different priorities;

[0092] Based on electricity price policy information, a load dispatch optimization model considering electricity price factors is constructed, with load priority and electricity price factors as model constraints;

[0093] With the optimization goals of maximizing energy utilization efficiency and minimizing operating costs, a multi-objective optimization model is established, and power balance and voltage limit constraints are set;

[0094] The particle swarm optimization algorithm is used to solve the multi-objective optimization model and the Pareto optimal solution set is obtained through iterative search;

[0095] Select the optimal allocation plan that balances energy utilization efficiency and operating costs from the Pareto optimal solution set and determine the power allocation for each load;

[0096] Generate load dispatch control instructions, perform power control on controllable loads and interruptible loads according to the optimization results, and monitor load responses to ensure continuous power supply to critical loads.

[0097] Specifically, the optimal allocation scheme that balances energy efficiency and operating costs is selected from the Pareto optimal solution set to determine the power allocation of each load, including:

[0098] Obtain all optimal solutions in the Pareto optimal solution set, for example, Solution 1: 90% energy efficiency, operating cost 100 yuan; Solution 2: 85% energy efficiency, operating cost 80 yuan; Solution 3: 95% energy efficiency, operating cost 120 yuan. For each optimal solution, calculate its energy efficiency and operating cost. Based on the energy efficiency and operating cost, construct a two-dimensional efficiency-cost evaluation matrix. For example, plot the three solutions in a two-dimensional coordinate system with energy efficiency on the horizontal axis and operating cost on the vertical axis to form a matrix. Using the weighted summation method, assign weights to efficiency and cost respectively, converting the two-dimensional matrix into a one-dimensional scoring vector. For example, set the weight of energy efficiency to 0.6 and the weight of operating cost to 0.4. Solution 1's score is 0.6*90% + 0.4*(1-100 / 220) = 0.718 (cost normalization: 100 / (100+120+80)); Solution 2's score is 0.6*85% + 0.4*(1-80 / 220) = 0.772; and Solution 3's score is 0.6*95% + 0.4*(1-120 / 220) = 0.75. The weighted summation method is used because energy efficiency and operating cost are often conflicting objectives, requiring a trade-off based on actual circumstances. The weighted summation method can transform multiple objectives into a single one, facilitating comparison and selection. The Pareto optimal solution set is sorted based on the score vector to obtain the optimal solution that balances energy efficiency and operating cost. For example, based on the above scores, Solution 2 > Solution 3 > Solution 1, making Solution 2 the optimal solution. The purpose of sorting is to select the solution that best meets practical needs from among numerous alternatives. The power allocation plan for each load is extracted from the optimal solution. For example, the power allocation plan corresponding to Solution 2 is: 100 kW for critical loads, 50 kW for controllable loads, and 30 kW for interruptible loads. This power allocation plan is extracted for subsequent control and scheduling. Power allocation is optimized by solving a linear programming model. For example, with the goal of minimizing operating costs, a linear programming model is constructed based on power balance, voltage limits, and load priorities to further optimize the power allocation plan from Solution 2. This can further improve the solution's cost-effectiveness and reliability. Monte Carlo simulation is used to validate the optimal power allocation plan across multiple scenarios to ensure its robustness. For example, scenarios with varying load fluctuations and electricity price fluctuations are simulated to verify the effectiveness and stability of the optimal power allocation plan under various conditions. Monte Carlo simulation can evaluate the solution's performance under uncertainty, improving its reliability. The finalized optimal power allocation plan is distributed to each load control unit to achieve optimal energy scheduling. For example, the optimized power allocation plan from Solution 2 is distributed to each load control unit, which adjusts the load's power accordingly, ultimately achieving optimal energy scheduling. Doing so can apply the optimization results to the actual system and achieve the goal of energy saving and consumption reduction.

[0099] In this embodiment, based on the load dispatch strategy optimization results, power dispatch instructions are generated for various loads, and load power is regulated in real time. During the regulation process, changes in power output are continuously monitored. When power output fluctuates, a rapid response mechanism for the load dispatch strategy is initiated, including:

[0100] After receiving the power dispatch instruction, each load control unit uses the PID control algorithm to adjust the actual operating power of each load according to the power value in the instruction, thus realizing real-time control of the load power;

[0101] During the load power control process, the power output data is continuously collected and the data analysis algorithm is used to determine whether the power output fluctuates.

[0102] If the power output fluctuation exceeds the preset threshold, the load allocation strategy rapid response mechanism is triggered;

[0103] After the rapid response mechanism is activated, a heuristic optimization algorithm is used to quickly calculate the load power adjustment plan based on the power output fluctuation and load priority, and generate a new load power dispatch instruction;

[0104] The newly generated load power dispatching instructions are sent to the corresponding load control units through the microgrid energy management system. The load control units quickly adjust the operating power of each load according to the new instructions to achieve dynamic balance of load power.

[0105] During the dynamic balancing of load power, the power output and load power data are continuously monitored, and an adaptive control algorithm is used to dynamically optimize the load power control parameters.

[0106] According to the evaluation results of load regulation effect, the reinforcement learning algorithm is used to perform self-learning optimization on the load dispatching strategy to realize adaptive optimization control of microgrid energy management.

[0107] In this embodiment, the load dispatch strategy rapid response mechanism calculates the load power adjustment amount based on the preset response rules and the power output fluctuation amplitude and load priority to ensure the power balance and stable operation of the microgrid. The following steps are included:

[0108] Obtain real-time data on power output and calculate and judge the fluctuation range of power output;

[0109] Determine the priority adjustment order of each load according to the preset load priority rules;

[0110] Through a fast response mechanism, the power adjustment amount of each load is calculated according to the power output fluctuation amplitude and load priority;

[0111] The calculated load power adjustment amount is sent to each load control unit in real time through the energy management system;

[0112] After receiving the adjustment instruction, each load control unit quickly performs power adjustment to achieve dynamic allocation of load power.

[0113] It should be noted that the method of the embodiments of the present disclosure can be performed by a single device, such as a computer or server. The method of the embodiments of the present disclosure can also be applied in a distributed scenario, where multiple devices cooperate to perform the method. In such a distributed scenario, one of the multiple devices may only perform one or more steps of the method of the embodiments of the present disclosure, and the multiple devices will interact with each other to complete the method.

[0114] It should be noted that the above describes some embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, it should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention. The actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-tasking and parallel processing are also possible or may be advantageous.

[0115] Example 2

[0116] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present invention further provides a flexible load regulation system for a microgrid, wherein the system is used to implement any of the above-mentioned methods, and comprises: a comprehensive operating status assessment module, a load characteristics identification module, a power quality analysis module, a load dispatching strategy optimization module, a load power scheduling module, and a rapid response mechanism module;

[0117] The comprehensive operation status evaluation module is used to obtain the comprehensive operation status evaluation results of the microgrid by using data fusion algorithm to comprehensively analyze the multi-source heterogeneous data of load power and power output based on the real-time operation status data of the microgrid;

[0118] The load characteristic identification module is used to identify and classify various loads in the microgrid based on the comprehensive operation status evaluation results and through the load characteristic identification algorithm, and obtain the power characteristic parameters of different types of loads;

[0119] The power quality analysis module is used to evaluate the power quality indicators of the microgrid in real time by combining the power consumption characteristic parameters of the load and using the power quality analysis algorithm;

[0120] The load dispatch strategy optimization module is used to build a load dispatch strategy optimization model based on the power quality assessment results, combined with load priority and electricity price policy factors. It optimizes the power distribution of controllable loads and interruptible loads while ensuring continuous power supply to key loads.

[0121] The load power dispatch module is used to generate power dispatch instructions for various loads based on the load dispatch strategy optimization results, and to regulate the load power in real time. During the regulation process, it continuously monitors the changes in power output. When the power output fluctuates, it activates the load dispatch strategy rapid response mechanism.

[0122] The fast response mechanism module is used for load allocation strategy. The fast response mechanism is based on preset response rules. According to the power output fluctuation amplitude and load priority, it calculates the load power adjustment amount to ensure the power balance and stable operation of the microgrid.

[0123] The system of the above embodiment is used to implement a corresponding flexible load regulation method applied to a microgrid in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0124] It should be noted that the flexible load regulation system for microgrids is implemented in the form of functional units. The term "module" here can be implemented in software and / or hardware, and is not specifically limited to this.

[0125] For example, a "module" may be a software program, a hardware circuit, or a combination of the two that implements the aforementioned functionality. The hardware circuit may include an application specific integrated circuit (ASIC), an electronic circuit, a processor (e.g., a shared processor, a dedicated processor, or a group of processors) and memory for executing one or more software or firmware programs, combined logic circuits, and / or other suitable components that support the described functionality.

[0126] The embodiments of the present disclosure are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A flexible load regulation method applied to a microgrid, characterized in that: The method comprises: Based on the real-time operating status data of the microgrid, a data fusion algorithm is used to comprehensively analyze the multi-source heterogeneous data of load power and power output to obtain the comprehensive operating status evaluation results of the microgrid; Based on the comprehensive operation status assessment results, the load characteristics identification algorithm is used to identify and classify various loads in the microgrid and obtain the power consumption characteristic parameters of different types of loads; Combined with the load's power consumption characteristic parameters, the power quality analysis algorithm is used to conduct real-time evaluation of the microgrid's power quality indicators; Based on the power quality assessment results, combined with load priority and electricity price policy factors, a load dispatch strategy optimization model is constructed to optimize the power allocation of controllable loads and interruptible loads while ensuring continuous power supply to critical loads; Based on the load allocation strategy optimization results, power dispatch instructions for various loads are generated, and load power is regulated in real time. During the regulation process, changes in power output are continuously monitored. When power output fluctuates, the load allocation strategy rapid response mechanism is activated; The load dispatch strategy rapid response mechanism is based on preset response rules. It calculates the load power adjustment amount according to the power output fluctuation amplitude and load priority to ensure the power balance and stable operation of the microgrid. Based on the power quality assessment results, combined with load priority and electricity price policy factors, a load dispatch strategy optimization model is constructed. Under the premise of ensuring continuous power supply to critical loads, the power distribution of controllable loads and interruptible loads is optimized, including: Obtain power quality assessment results, load priority data, and electricity price policy information, and determine critical loads, controllable loads, and interruptible loads based on the power quality assessment results; Based on the load priority data, a clustering algorithm is used to classify the loads and obtain a set of loads with different priorities; Based on electricity price policy information, a load dispatch optimization model considering electricity price factors is constructed, with load priority and electricity price factors as model constraints; With the optimization goals of maximizing energy utilization efficiency and minimizing operating costs, a multi-objective optimization model is established, and power balance and voltage limit constraints are set; The particle swarm optimization algorithm is used to solve the multi-objective optimization model and the Pareto optimal solution set is obtained through iterative search; Select the optimal allocation plan that balances energy utilization efficiency and operating costs from the Pareto optimal solution set and determine the power allocation for each load; Generate load dispatch control instructions, perform power control on controllable and interruptible loads based on optimization results, and monitor load responses to ensure continuous power supply to critical loads; Selecting the optimal allocation scheme that balances energy efficiency and operating costs from the Pareto optimal solution set and determining the power allocation for each load includes: Obtain all optimal solutions in the Pareto optimal solution set; for each optimal solution, calculate its energy utilization efficiency and operating cost; construct a two-dimensional efficiency-cost evaluation matrix based on energy utilization efficiency and operating cost; plot the three solutions in a two-dimensional coordinate system with energy utilization efficiency as the horizontal axis and operating cost as the vertical axis to form a matrix; use the weighted summation method to assign weights to efficiency and cost respectively, and convert the two-dimensional matrix into a one-dimensional scoring vector; sort the Pareto optimal solution set based on the scoring vector to obtain the optimal solution that balances energy utilization efficiency and operating cost; extract the power allocation plan for each load from the optimal solution; and optimize power allocation by solving a linear programming model. With the goal of minimizing operating costs and taking power balance, voltage limit and load priority as constraints, a linear programming model is constructed to further optimize the power allocation scheme of the optimal solution; Monte Carlo simulation is used to verify the optimal power allocation scheme in multiple scenarios to ensure its robustness; different load fluctuations and electricity price fluctuations are simulated to verify the effectiveness and stability of the optimal power allocation scheme under various conditions; the final optimal power allocation scheme is sent to each load control unit to achieve optimal energy scheduling; the power allocation scheme after optimization of the optimal solution is sent to the control unit of each load, and the control unit adjusts the power of the load according to the instructions to ultimately achieve optimal energy scheduling.

2. The method according to claim 1, characterized in that Based on the real-time operating status data of the microgrid, a data fusion algorithm is used to comprehensively analyze the multi-source heterogeneous data of load power and power output to obtain the comprehensive operating status assessment results of the microgrid, including: Obtain real-time operating status data of each component of the microgrid; Preprocess the acquired multi-source heterogeneous data and convert the data into a unified format; The Kalman filter algorithm is used to fuse the pre-processed data to obtain an estimate of the overall operating status of the microgrid; According to the fused estimated values ​​of the microgrid operation status, key indicators reflecting the microgrid operation characteristics are extracted; Compare the extracted key indicators with preset thresholds to evaluate the operating status of the microgrid; If key indicators exceed the normal range, the early warning mechanism will be triggered, the warning level will be determined according to the degree of deviation, and an operation status assessment report will be generated; The operation status assessment report details the specific values, normal ranges, and deviations of each key indicator of the microgrid, providing a basis for decision-making for dispatchers.

3. The method according to claim 1, characterized in that Based on the comprehensive operating status assessment results, the load characteristics identification algorithm is used to identify and classify various loads in the microgrid. The power consumption characteristic parameters of different types of loads are obtained, including: Obtain real-time operation data of the microgrid by comprehensively evaluating its operation status; Based on the acquired microgrid operating status data, a load characteristic recognition algorithm based on machine learning is used to identify and classify various loads in the microgrid and obtain labels for different types of loads. For the different types of loads identified, the power consumption characteristic parameters of each type of load are obtained by analyzing the historical power consumption data.

4. The method according to claim 1, wherein Combined with the load's power consumption characteristic parameters, the power quality analysis algorithm is used to conduct real-time evaluation of the microgrid's power quality indicators, including: Obtain real-time operating data of the microgrid and the power demand and characteristic parameters of different types of loads; The acquired data is fed into a pre-built power quality assessment model, which uses a support vector machine algorithm and is obtained by training historical data; The model outputs real-time evaluation values ​​of various power quality indicators; The evaluation value of the power quality index is compared with the preset quality threshold to determine whether the current power quality meets the power supply requirements of different loads.

5. The method according to claim 1, wherein Based on the load dispatch strategy optimization results, power dispatch instructions for various loads are generated to regulate load power in real time. During the regulation process, changes in power output are continuously monitored. When power output fluctuates, the load dispatch strategy rapid response mechanism is activated, including: After receiving the power dispatch instruction, each load control unit uses the PID control algorithm to adjust the actual operating power of each load according to the power value in the instruction, thus realizing real-time control of the load power; During the load power control process, the power output data is continuously collected and the data analysis algorithm is used to determine whether the power output fluctuates. If the power output fluctuation exceeds the preset threshold, the load allocation strategy rapid response mechanism is triggered; After the rapid response mechanism is activated, a heuristic optimization algorithm is used to quickly calculate the load power adjustment plan based on the power output fluctuation and load priority, and generate a new load power dispatch instruction; The newly generated load power dispatching instructions are sent to the corresponding load control units through the microgrid energy management system. The load control units quickly adjust the operating power of each load according to the new instructions to achieve dynamic balance of load power. During the dynamic balancing of load power, the power output and load power data are continuously monitored, and an adaptive control algorithm is used to dynamically optimize the load power control parameters. According to the evaluation results of load regulation effect, the reinforcement learning algorithm is used to perform self-learning optimization on the load dispatching strategy to realize adaptive optimization control of microgrid energy management.

6. The method according to claim 1, characterized in that The load dispatch strategy rapid response mechanism is based on preset response rules. It calculates the load power adjustment amount according to the power output fluctuation amplitude and load priority to ensure the power balance and stable operation of the microgrid. It includes: Obtain real-time data on power output and calculate and judge the fluctuation range of power output; Determine the priority adjustment order of each load according to the preset load priority rules; Through a fast response mechanism, the power adjustment amount of each load is calculated according to the power output fluctuation amplitude and load priority; The calculated load power adjustment amount is sent to each load control unit in real time through the energy management system; After receiving the adjustment instruction, each load control unit quickly performs power adjustment to achieve dynamic allocation of load power.

7. A flexible load regulation system applied to a microgrid, characterized in that: The system is used to implement the method described in any one of claims 1 to 6, comprising: a comprehensive operating status assessment module, a load characteristics identification module, a power quality analysis module, a load dispatch strategy optimization module, a load power scheduling module, and a rapid response mechanism module; The comprehensive operation status evaluation module is used to comprehensively analyze the load power and power output multi-source heterogeneous data based on the real-time operation status data of the microgrid using a data fusion algorithm to obtain a comprehensive operation status evaluation result of the microgrid; The load characteristic identification module is used to identify and classify various types of loads in the microgrid based on the comprehensive operation status evaluation results and obtain power consumption characteristic parameters of different types of loads through the load characteristic identification algorithm; The power quality analysis module is used to combine the power consumption characteristic parameters of the load and adopt the power quality analysis algorithm to perform real-time evaluation of the power quality indicators of the microgrid; The load dispatch strategy optimization module is used to construct a load dispatch strategy optimization model based on the power quality assessment results, combined with load priority and electricity price policy factors, to optimize the power distribution of controllable loads and interruptible loads while ensuring continuous power supply to key loads; The load power scheduling module is used to generate power scheduling instructions for various loads based on the load allocation strategy optimization results, and to regulate the load power in real time. During the regulation process, it continuously monitors the changes in power output. When the power output fluctuates, it activates the load allocation strategy rapid response mechanism; The quick response mechanism module is used for the load allocation strategy. The quick response mechanism is based on preset response rules and calculates the load power adjustment amount according to the power output fluctuation amplitude and load priority to ensure the power balance and stable operation of the microgrid.

Images