A method and system for intelligent scheduling and control of a microgrid

Abstract

The present invention provides a method and system for intelligent scheduling and control of a microgrid, relating to the technical field of microgrid scheduling, including: extracting battery state perception data and timestamp perception data; when it belongs to an abnormal state, stopping the process, and when it belongs to a healthy state, matching scheduling constraint rules; performing local sample adjacency analysis to obtain the production demand power; performing scheduling scheme configuration to obtain a first scheduling scheme; performing analysis to obtain an economic cost evaluation value and an energy-saving parameter evaluation value; when at least one of the economic cost evaluation value is greater than or equal to the economic cost evaluation threshold and the energy-saving parameter evaluation value is less than or equal to the energy-saving parameter evaluation threshold is triggered, performing multi-constraint optimization to obtain a scheduling scheme optimization result; and executing intelligent scheduling control of the microgrid. The present invention solves the technical problem that the existing microgrid scheduling methods often adopt fixed-mode control rules and lack flexibility for rapidly changing market conditions and continuously changing energy supply and demand situations.

Description

Technical Field

[0001] The present invention relates to the technical field of microgrid scheduling, and particularly relates to a method and system for intelligent scheduling and control of a microgrid. Background Art

[0002] With the rapid development of renewable energy technologies and the continuous growth of electricity demand, traditional energy scheduling methods have gradually been unable to meet the complexity and dynamics of modern power grids. Specifically, the rapid development of industrialization and informatization has led to diversified energy consumption patterns, and the demand shows highly dynamic and unpredictable characteristics, making the energy supply-demand balance more complex. However, traditional microgrid scheduling methods often adopt fixed-mode control rules and lack sufficient flexibility to cope with rapidly changing market conditions and constantly changing energy supply-demand situations. This lack of flexibility may lead to energy waste or an inability to effectively meet demand during peak energy demand periods. Summary of the Invention

[0003] This application provides a method and system for intelligent scheduling and control of a microgrid, aiming to solve the technical problem that the microgrid scheduling methods in the prior art often adopt fixed-mode control rules and lack flexibility for rapidly changing market conditions and constantly changing energy supply-demand situations.

[0004] In the first aspect disclosed in this application, a method for intelligent scheduling and control of a microgrid is provided, which is applied to a system for intelligent scheduling and control of a microgrid. The system is embedded in an integrated energy storage, charging and discharging station, and the system includes a sensing node and a scheduling node. The method includes: extracting battery state sensing data and timestamp sensing data according to the sensing node; when the battery state sensing data belongs to an abnormal state, stopping the process, and when the battery state sensing data belongs to a healthy state, matching scheduling constraint rules according to the timestamp sensing data; performing local sample adjacency analysis according to the timestamp sensing data to obtain the production demand power; configuring a scheduling plan through the scheduling plan configuration channel of the scheduling node, and obtaining a first scheduling plan based on the scheduling constraint rules and the production demand power; analyzing the first scheduling plan through the scheduling plan evaluation channel of the scheduling node to obtain an economic cost evaluation value and an energy-saving parameter evaluation value; when at least one of the economic cost evaluation value is greater than or equal to the economic cost evaluation threshold and the energy-saving parameter evaluation value is less than or equal to the energy-saving parameter evaluation threshold is triggered, performing multi-constraint optimization on the first scheduling plan to obtain a scheduling plan optimization result; and performing intelligent scheduling control of the microgrid according to the scheduling plan optimization result.

[0005] The second aspect disclosed in this application provides a system for intelligent scheduling and control of a microgrid. The system is embedded in an integrated photovoltaic energy storage charging and discharging station. The system includes a sensing node and a scheduling node, and is used for the method of intelligent scheduling and control of the above-mentioned microgrid. The system includes: a sensing data extraction module for extracting battery state sensing data and timestamp sensing data according to the sensing node; a scheduling constraint rule matching module for stopping the process when the battery state sensing data belongs to an abnormal state, and matching scheduling constraint rules according to the timestamp sensing data when the battery state sensing data belongs to a healthy state; a local sample adjacency analysis module for performing local sample adjacency analysis according to the timestamp sensing data to obtain the required production power; a scheduling scheme configuration module for configuring a scheduling scheme based on the scheduling constraint rules and the required production power through the scheduling scheme configuration channel of the scheduling node to obtain a first scheduling scheme; an evaluation value acquisition module for analyzing the first scheduling scheme through the scheduling scheme evaluation channel of the scheduling node to obtain an economic cost evaluation value and an energy-saving parameter evaluation value; a multi-constraint optimization module for triggering when at least one of the economic cost evaluation value is greater than or equal to the economic cost evaluation threshold and the energy-saving parameter evaluation value is less than or equal to the energy-saving parameter evaluation threshold, and performing multi-constraint optimization on the first scheduling scheme to obtain a scheduling scheme optimization result; an intelligent scheduling control module for performing intelligent scheduling and control of the microgrid according to the scheduling scheme optimization result.

[0006] One or more technical solutions provided in this application have at least the following beneficial effects:

[0007] By means of real-time monitoring of battery status and timestamp data through sensing nodes, the current energy storage status and time-related data of the power station can be quickly obtained. This real-time data collection provides accurate basic data for subsequent scheduling decisions, ensuring the timeliness and accuracy of scheduling strategies. When the battery status data shows abnormalities, relevant processes are automatically stopped to prevent possible equipment damage or efficiency decline. When the battery is in a healthy state, real-time data is used to match scheduling constraint rules to ensure the optimization of energy distribution. Local sample adjacency analysis is carried out based on timestamp sensing data to predict the upcoming production demand power according to historical and real-time data, so as to carry out energy distribution and planning in advance, optimize energy utilization efficiency, make energy supply more accurate and efficient, and avoid overproduction or insufficient supply. The scheduling scheme configuration channel generates a preliminary scheduling scheme based on the production demand power and preset scheduling constraint rules, which improves the flexibility and adaptability of the scheduling scheme and can cope with variable scheduling requirements. The scheduling scheme evaluation channel conducts a dual evaluation of the generated scheduling scheme in terms of economic cost and energy-saving effect. This evaluation mechanism ensures that the scheduling scheme can not only meet the actual power demand, but also achieve the goals of cost-effectiveness and energy conservation, providing quantitative indicators for subsequent analysis. When the scheduling scheme does not meet the set thresholds in terms of cost or energy conservation, multi-constraint optimization is carried out to find a scheme that can achieve the optimal cost and energy-saving effect while meeting all key performance indicators. This step not only ensures the safety and reliability of power supply, but also emphasizes the maximization of economic and environmental benefits. According to the optimization results, intelligent scheduling control of the microgrid is executed, which not only improves the overall efficiency of energy use, but also ensures that the requirements for power supply stability and sustainability are met, significantly improving the efficiency and effect of energy management.

[0008] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the specific embodiments of this application are hereinafter specifically exemplified. Brief Description of the Drawings

[0009] Figure 1 It is a schematic flow chart of a method for intelligent scheduling and control of a microgrid provided by an embodiment of this application.

[0010] Figure 2 It is a schematic flow chart of multi-constraint optimization in a method for intelligent scheduling and control of a microgrid provided by an embodiment of this application.

[0011] Figure 3 It is a schematic structural diagram of a system for intelligent scheduling and control of a microgrid provided by an embodiment of this application.

[0012] Description of the drawing reference numerals: a perception data extraction module 10, a scheduling constraint rule matching module 20, a local sample adjacency analysis module 30, a scheduling scheme configuration module 40, an evaluation value acquisition module 50, a multi-constraint optimization module 60, and an intelligent scheduling control module 70. Specific embodiments

[0013] In an embodiment of the present application, by providing a method and a system for intelligent scheduling and control of a microgrid, the technical problem in the prior art that the microgrid scheduling method often adopts a fixed-mode control rule and lacks flexibility for rapidly changing market conditions and continuously changing energy supply and demand conditions is solved.

[0014] After introducing the basic principle of the present application, various non-limiting embodiments of the present application will be specifically introduced below with reference to the drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0015] Embodiment 1, as Figure 1 shown, an embodiment of the present application provides a method for intelligent scheduling and control of a microgrid, which is applied to a system for intelligent scheduling and control of a microgrid. The system is embedded in a photovoltaic energy storage charging and discharging integrated station. The system includes a sensing node and a scheduling node. The method includes:

[0016] Extract battery state perception data and timestamp perception data according to the sensing node.

[0017] A method for intelligent scheduling and control of a microgrid provided by an embodiment of the present application is applied to a system for intelligent scheduling and control of a microgrid. The system for intelligent scheduling and control of a microgrid is used to optimize and manage the energy distribution in the microgrid. The system can monitor the battery state and energy demand in real time, automatically adjust the energy output to meet the demand and improve the efficiency. The system is embedded in a photovoltaic energy storage charging and discharging integrated station. The photovoltaic energy storage charging and discharging integrated station is a comprehensive facility that integrates photovoltaic power generation, battery energy storage, electric energy charging and discharging functions. The station can not only generate electric energy, but also store electric energy and supply power to the power grid or electrical equipment when needed. The system includes a sensing node and a scheduling node. The sensing node is a sensing device in the system, which is used to collect data on the state of the microgrid in real time, such as battery power, voltage, current, etc., and environmental data, such as light intensity, temperature, etc. The data of the sensing node is crucial for the system to make intelligent decisions. The scheduling node is the part of the system that is responsible for processing the data collected by the sensing node and making scheduling decisions accordingly. The scheduling node uses various algorithms to optimize the energy use, such as the charging and discharging time of the battery and the best utilization of photovoltaic power generation.

[0018] Specifically, the sensing nodes are installed at key positions in the microgrid, such as near the battery system and photovoltaic panels, to monitor in real time parameters such as the voltage, current, and temperature of the battery, and record the timestamps of these data. According to the sensing nodes, battery status sensing data and timestamp sensing data are extracted. Among them, the battery status sensing data includes the charging status, power, health status, etc. of the battery, and these data provide information on the current working condition and expected life of the battery; the timestamp sensing data is the timestamp of each sensing data point, indicating the specific time of data collection, and is used to track changes in the battery status and predict future battery behavior.

[0019] When the battery status sensing data belongs to an abnormal state, the process is stopped. When the battery status sensing data belongs to a healthy state, the scheduling constraint rules are matched according to the timestamp sensing data.

[0020] If the battery status sensing data shows that the battery is in an abnormal state, for example, the voltage is too low or too high, the temperature is abnormal, etc., the relevant operations are immediately stopped to protect the battery from further damage. In this case, safety protocols such as disconnecting the battery connection and sending an alarm are initiated.

[0021] If the battery status sensing data shows that the battery is in a healthy state, the timestamp sensing data is used to determine the current time and the battery's usage requirements, such as whether it is during the peak time of high demand or the valley time of low demand, and the scheduling constraint rules are matched, including the optimal charging and discharging times of the battery, and how to optimize energy use according to electricity prices and grid demand. For example, store energy during the night when electricity prices are low and release energy during the day when electricity prices are high.

[0022] This scheduling constraint rule matching mechanism effectively improves the operating efficiency and reliability of the microgrid, while reducing maintenance costs and extending the service life of the battery. Through real-time data and intelligent analysis, the microgrid can adapt to changing energy demands and market conditions.

[0023] Local sample adjacency analysis is performed according to the timestamp sensing data to obtain the production demand electricity.

[0024] Adjacency analysis refers to analyzing the collected data samples, comparing data points that are close in time to identify patterns or trends, analyzing data at neighboring time points based on the timestamp sensing data, such as the electricity usage data at the same moment the previous day or the same day the previous week, so as to estimate the current production demand electricity. This method can predict short-term changes in electricity demand based on historical data. Through this analysis, the obtained production demand electricity is the predicted electricity required within a specific time period, and this prediction will directly affect the subsequent decisions of the scheduling node.

[0025] Configure a channel through the scheduling node's scheduling plan configuration. Based on the scheduling constraint rules and the production demand electricity, configure the scheduling plan to obtain the first scheduling plan.

[0026] The scheduling node is a core component in the system, responsible for generating scheduling plans based on the collected and analyzed data, including power distribution, determination of charging and discharging times, and interaction with the external power grid, etc. Through the scheduling plan configuration channel of the scheduling node, the scheduling plan configuration channel is a component within the scheduling node used for configuring the scheduling plan. Specifically, based on the scheduling constraint rules and the production demand electricity, a preliminary scheduling plan is formulated. This plan specifies when to use energy storage, when to use directly generated photovoltaic power, and how to interact with the power grid (such as charging or selling electricity). The configured scheduling plan is taken as the first scheduling plan for the subsequent implementation phase.

[0027] Analyze the first scheduling plan through the scheduling plan evaluation channel of the scheduling node to obtain the economic cost evaluation value and the energy-saving parameter evaluation value.

[0028] The scheduling plan evaluation channel is another component within the scheduling node used for comprehensively evaluating the scheduling plan to determine the feasibility and benefits of the plan. Specifically, the scheduling plan evaluation channel receives the first scheduling plan, including the expected power production, consumption, energy storage usage, etc. It converts various operations in the scheduling plan into quantitative indicators of cost and energy saving for economic cost evaluation and energy-saving parameter evaluation. Among them, economic cost evaluation usually involves calculating the energy purchase cost, operation cost, maintenance cost, and potential benefits. Energy-saving parameter evaluation mainly considers whether the scheduling plan can effectively reduce energy consumption and improve energy efficiency. After evaluation, the economic cost evaluation value and the energy-saving parameter evaluation value are obtained, providing quantitative indicators for subsequent analysis.

[0029] When at least one of the economic cost evaluation value being greater than or equal to the economic cost evaluation threshold and the energy-saving parameter evaluation value being less than or equal to the energy-saving parameter evaluation threshold is triggered, perform multi-constraint optimization on the first scheduling plan to obtain the scheduling plan optimization result.

[0030] The economic cost evaluation threshold is a threshold preset according to actual needs, representing the maximum acceptable value of the economic cost evaluation value. If the economic cost evaluation value is greater than or equal to the set cost threshold, it means the cost of the plan may be too high and needs to be adjusted to reduce the cost. The energy-saving parameter evaluation threshold is a threshold preset according to actual needs, representing the minimum acceptable value of the energy-saving parameter evaluation value. If the energy-saving parameter evaluation value is less than or equal to the set energy-saving threshold, it indicates that the energy-saving effect does not meet the standard and the energy-saving performance needs to be improved.

[0031] If any one of the above two thresholds is triggered, or both are triggered simultaneously, the first scheduling scheme is regarded as an optimization problem, where the objective function includes one or both of minimizing cost and maximizing energy-saving effect. Through an optimization algorithm, an optimal or approximately optimal scheduling scheme is searched under a given number of constraints to obtain the optimization result of the scheduling scheme. This optimization result can improve the overall system performance and reliability while meeting economic and energy-saving criteria.

[0032] Execute microgrid intelligent scheduling control according to the optimization result of the scheduling scheme.

[0033] Convert the optimization result of the scheduling scheme into specific operation instructions, such as when to start photovoltaic power generation, when to use the energy storage device to discharge, and how to adjust the load, etc. Perform microgrid intelligent scheduling control according to the operation instructions. Further, during the implementation process, continue to monitor the deviation between the actual operation and the expected scheme and make adjustments as needed to ensure the efficiency and safety of the operation.

[0034] Through the above steps, the microgrid system can manage energy use more precisely, respond to changes in various operating conditions, and at the same time ensure the realization of economic benefits and energy-saving goals. This method helps to dynamically adapt to changing energy demands and environmental conditions and achieve sustainable development goals.

[0035] Furthermore, when the battery state perception data belongs to the healthy state, match the scheduling constraint rules according to the timestamp perception data, including:

[0036] The scheduling constraint rules include power supply constraint types, power supply type priorities, and power supply constraint tasks. The sum of the power supply type priorities is equal to 1; when the battery state perception data belongs to the healthy state and the timestamp perception data belongs to the valley time zone, the power supply constraint types include main grid power supply and photovoltaic power supply, the main grid power supply priority ∈ [0, 0.5], and the photovoltaic power supply priority ∈ [0.5, 1]. The power supply constraint tasks both include production power supply and energy storage charging; when the battery state perception data belongs to the healthy state, the timestamp perception data belongs to the flat value time zone, and the energy storage battery power is greater than the discharge power threshold, the power supply constraint types include main grid power supply, photovoltaic power supply, and energy storage power supply. The sum of the main grid power supply priority and the energy storage power supply priority ∈ [0, 0.5], and the photovoltaic power supply priority ∈ [0.5, 1]. The power supply constraint task includes production power supply; when the battery state perception data belongs to the healthy state, the timestamp perception data belongs to the peak time zone, and the energy storage battery power is greater than the discharge power threshold, the power supply constraint types include main grid power supply, photovoltaic power supply, and energy storage power supply. The main grid power supply priority is equal to ∈ [0, 0.2], and the sum of the energy storage power supply and the photovoltaic power supply priority ∈ (0.2, 1]. The power supply constraint task includes production power supply.

[0037] The scheduling constraint rules include power supply constraint types, power supply type priorities, and power supply constraint tasks. Among them, the power supply constraint types refer to different power supply sources that can be selected during the scheduling process, such as power grid power supply, photovoltaic power supply, energy storage power supply, etc.; the power supply type priorities are the priorities set for various power supply types, and their sum is equal to 1, ensuring that the weights of each power supply type add up to maintain balance during the decision-making process. The setting of priorities reflects the importance and cost-effectiveness of different power sources in power supply. For example, in some cases, photovoltaic power generation with lower costs may be preferred; the power supply constraint tasks are the specific tasks that each power supply method needs to meet, such as only supplying production electricity, energy storage charging, or both.

[0038] When the battery status perception data belongs to the healthy state, this condition ensures that the system operates when the battery is in good working condition, thus avoiding strategies that may exacerbate battery loss when the battery performance deteriorates; when the timestamp perception data belongs to the valley time zone, the valley time zone usually refers to the period with lower electricity prices. At this time, the cost of using electricity is low, which is an ideal time for charging and large-scale electricity use.

[0039] Under this condition, the power supply constraint types include power grid power supply and photovoltaic power supply. The selection of these two power supply types is based on their availability and cost-effectiveness. The power grid usually provides a stable power supply, and photovoltaic power generation provides environmentally friendly and low-cost electricity. Among them, the priority of power grid power supply ∈ [0, 0.5]. This range indicates that the weight of power grid power supply in the total power supply strategy is relatively low. The lower priority may be due to the higher electricity price of the power grid or the strategic desire to reduce dependence on the traditional power grid and support more renewable energy use; the priority of photovoltaic power supply ∈ [0.5, 1], indicating that within the valley time zone, the priority of photovoltaic power supply is higher than that of the power grid, reflecting the priority support for renewable energy. Photovoltaic power generation has lower costs and is environmentally friendly, making it an ideal choice for optimizing energy configuration, reducing costs, and supporting environmental sustainability.

[0040] The power supply constraint tasks all include production power supply and energy storage charging. Among them, the production power supply ensures that production activities receive sufficient power support to maintain production efficiency and continuity; energy storage charging is to use low-cost electricity for energy storage operations, which can not only be used for peak shaving and valley filling during periods with higher electricity prices, but also improve the flexibility and safety of energy use.

[0041] Through this strategy, the microgrid intelligent scheduling system can maximize the utilization of renewable energy during periods with lower costs, while performing energy storage to prepare for high-demand or high-cost periods, thereby optimizing the overall energy management and cost-effectiveness. Such a scheduling strategy not only helps with economic savings but also meets the goals of environmental protection and sustainable development.

[0042] When the timestamp-aware data belongs to the flat value time zone, which is the period when the electricity price is neither the highest nor the lowest, representing a medium level of electricity cost and demand; when the energy storage battery power is greater than the discharge power threshold, this ensures that the energy storage system has sufficient power to supply electricity without causing power outages due to insufficient power.

[0043] Under this condition, the power supply constraint types include main grid power supply, photovoltaic power supply, and energy storage power supply. These options provide flexible energy management methods to adapt to different power supply demands and cost-effectiveness. Among them, the sum of the main grid power supply priority and the energy storage power supply priority ∈ [0, 0.5], which means that in the flat value time zone, the total priority of these two power supply methods is restricted to a relatively low level, and the sum does not exceed 0.5, reflecting the demand for cost control and encouraging the use of more renewable energy; the photovoltaic power supply priority ∈ [0.5, 1], indicating that in the flat value time zone with moderate electricity prices, there is a tendency to utilize renewable energy, which is both environmentally friendly and cost-effective.

[0044] The power supply constraint tasks include production power supply. That is, in the flat value time zone, the main task of the system is to ensure that production activities receive sufficient power support because the flat value time zone may be the main working hours of weekdays with stable demand.

[0045] This strategy setting helps to ensure that the microgrid system optimizes the power supply structure when the electricity cost is moderate and the battery power is sufficient, reduces dependence on the traditional grid, and fully utilizes renewable energy at the same time. Such a power supply configuration not only ensures the continuity and stability of production but also supports the sustainable use of energy and the improvement of cost efficiency.

[0046] When the timestamp-aware data belongs to the peak time zone, which is the period with the highest electricity price, usually corresponding to the moment of the highest power demand. In this time zone, power cost control is particularly crucial.

[0047] Under this condition, the power supply constraint types include main grid power supply, photovoltaic power supply, and energy storage power supply. Among them, the main grid power supply priority ∈ [0, 0.2], indicating that during peak hours, the priority of the main grid power supply is very low, which means minimizing the dependence on purchasing electricity from the high-cost grid to reduce operating costs; the sum of the energy storage power supply and the photovoltaic power supply priority ∈ (0.2, 1], that is, the total priority of these two power supply methods occupies the vast majority, reflecting that during the high-cost peak hours, the stored electrical energy or renewable energy is preferentially used to maximize cost-effectiveness and sustainability.

[0048] The power supply constraint tasks include production power supply, indicating that in the peak time zone, even though the power cost is high, production power supply is still the main task, which requires the system to ensure that production activities are not affected by power cost fluctuations through optimizing the power supply method.

[0049] Through this power supply constraint strategy, the microgrid system can effectively utilize energy storage and photovoltaic power generation during peak periods of both electricity demand and cost, reducing its dependence on expensive large-grid power supply. This not only helps reduce operating costs but also improves the system's energy self-sufficiency rate and environmental sustainability.

[0050] Furthermore, it also includes:

[0051] When the battery state perception data belongs to the healthy state, and the timestamp perception data belongs to the flat value time zone, and the energy storage battery power is less than or equal to the discharge power threshold, the power supply constraint tasks all include production power supply and energy storage charging; when the battery state perception data belongs to the healthy state, and the timestamp perception data belongs to the peak time zone, and the energy storage battery power is less than or equal to the discharge power threshold, the large-grid power supply constraint task includes production power supply, and the photovoltaic power supply constraint task includes production power supply and energy storage charging.

[0052] When the energy storage battery power is less than or equal to the discharge power threshold, it indicates that the energy storage system's power is at a low level and needs to be carefully managed to prevent power depletion, while also considering recharging. Under this condition, the power supply constraint tasks all include production power supply and energy storage charging, which means that even in a power shortage situation, ensuring production power consumption is still a high-priority task because production activities usually have strict requirements for continuous power supply. Given that the energy storage power has approached or reached the discharge threshold, an important task at this time is to charge the energy storage system to ensure that the energy storage battery can provide sufficient power support in the future, especially during expected high-demand or high-cost periods.

[0053] Through such a power supply strategy, the microgrid system can effectively address the challenge of insufficient power while ensuring the stability of production activities and the timely charging of the energy storage system. This strategy helps improve the energy efficiency and reliability of the entire system, ensuring normal operation under various power conditions.

[0054] When the timestamp-aware data belongs to the peak time zone and the energy storage battery power is less than or equal to the discharge power threshold, it indicates that the electricity cost is high and the energy storage power is insufficient, and it is impossible to fully rely on energy storage power supply to meet the electricity demand during peak hours. Under this condition, the large power grid power supply constraint task includes production power supply. That is, during the peak time zone, although the power grid electricity cost is high, considering the insufficient energy storage power, the system needs to rely on the large power grid to ensure the stable operation of production facilities, which is to ensure that production is not interrupted due to power shortage; the photovoltaic power supply constraint task includes production power supply and energy storage charging. That is, the photovoltaic system can provide direct power supply during the day. If conditions permit, photovoltaic power should be preferentially used to support production, reducing the demand for purchasing high-price electricity from the grid. When the electricity generated by the photovoltaic system exceeds the production demand, the extra electricity is used for charging the energy storage device, which is to maximize the utilization of renewable resources during sufficient sunshine and prepare for possible power shortage moments.

[0055] Through such a power supply strategy, the microgrid system can improve the economy and sustainability of energy use as much as possible while ensuring production continuity. This flexible power management strategy helps to maintain the high efficiency and stability of the system under various operating conditions.

[0056] Furthermore, local sample adjacency analysis is performed according to the timestamp-aware data to obtain the production demand electricity, including:

[0057] According to the timestamp-aware data, adjacent local production logs are collected, where the local production logs include a power consumption record data set; mode analysis is performed on the power consumption record data set to obtain the production demand electricity.

[0058] The timestamp-aware data provides an accurate time mark to identify the electricity usage situation during a specific period. According to the timestamp-aware data, local production logs at adjacent time points are automatically collected. These logs include a power consumption record data set, which records the actual power consumption in production activities. Through these data, a comprehensive energy consumption view can be obtained, providing a basis for further analysis.

[0059] Mode analysis is used to find the value that appears most frequently in a set of data. In the power consumption records, the mode represents the most common or typical power consumption. Specifically, mode analysis is performed on the collected power consumption record data set to determine the most common power consumption patterns during different production cycles or time periods, which helps to predict the possible maximum power demand under similar production conditions. The analysis results point out the main trends in power use during the production process and determine the production demand electricity under normal production conditions, enabling the scheduling system to more effectively plan the allocation of power resources, especially during periods when the power demand may reach its peak.

[0060] Furthermore, through the scheduling scheme evaluation channel of the scheduling node, the first scheduling scheme is analyzed to obtain an economic cost evaluation value and an energy-saving parameter evaluation value, including:

[0061] According to the scheduling constraint rules, the associated scheduling scheme evaluation nodes are activated; the first scheduling scheme is preprocessed through the encoding layer to obtain a dimensionless input vector; the dimensionless input vector is fitted through the economic cost evaluation layer of the associated scheduling scheme evaluation nodes to output the economic cost evaluation value; the dimensionless input vector is fitted through the energy-saving evaluation layer of the associated scheduling scheme evaluation nodes to output the energy-saving parameter evaluation value.

[0062] According to the scheduling constraint rules, the associated scheduling scheme evaluation nodes are activated. The associated scheduling scheme evaluation nodes are components in the system responsible for analyzing and evaluating the performance of scheduling schemes. They use various algorithms and models to evaluate the economy, reliability, and efficiency of scheduling schemes.

[0063] The encoding layer is a key part of data preprocessing and is responsible for converting various parameters in the scheduling scheme (such as power supply, time, cost, etc.) into a dimensionless input vector. The preprocessing step aims to convert the data of the first scheduling scheme into a format suitable for model analysis, usually including standardization processing to remove the dimension, so that different data types can be compared and analyzed under the same standard. After preprocessing, a dimensionless input vector is obtained, eliminating the unit and scale differences in the original data. The dimensionless input vector enables the model to evaluate the scheduling scheme only based on the relative importance and relevance of the data, without being affected by the original magnitude.

[0064] The economic cost evaluation layer is used to evaluate the economy of the scheduling scheme, including cost-benefit analysis and financial sustainability assessment. It converts the data in the dimensionless input vector into a quantitative indicator of economic cost through the model fitting process. Specifically, using a predetermined economic model, the data in the input vector, such as power consumption, power supply type, time distribution, and other cost-related factors, are combined to calculate the expected total cost or unit cost. This fitting process includes regression analysis, cost function calculation, or other statistical methods to ensure the accuracy and reliability of the evaluation value. The output economic cost evaluation value provides a quantitative indicator indicating the financial performance of the scheduling scheme, including direct costs, operating costs, and potential economic benefits.

[0065] The energy-saving evaluation layer is used to evaluate the energy efficiency and energy-saving potential of the scheduling scheme, and to examine the performance of the scheme in reducing energy consumption and improving energy use efficiency. Similar to the economic cost evaluation, the energy-saving evaluation layer also uses a dimensionless input vector for model fitting, aiming to identify and calculate the effects of energy-saving measures, such as reducing energy consumption and the proportion of using renewable energy. The energy-saving effect of the scheduling scheme can be evaluated using environmental protection indicators, energy consumption data, and efficiency standards. The finally output energy-saving parameter evaluation value provides quantitative information on the energy-saving performance of the scheduling scheme, including the estimated energy savings, reduced emissions, and improved energy efficiency, etc.

[0066] Furthermore, as Figure 2 shown, when at least one of the economic cost evaluation value is greater than or equal to the economic cost evaluation threshold and the energy-saving parameter evaluation value is less than or equal to the energy-saving parameter evaluation threshold is triggered, multi-constraint optimization is performed on the first scheduling scheme to obtain the scheduling scheme optimization result, including:

[0067] Configure a first weight for the economic cost evaluation value and a second weight for the energy-saving parameter evaluation value, where the sum of the first weight and the second weight is equal to 1; according to the first weight and the second weight, fuse the economic cost evaluation value and the energy-saving parameter evaluation value to obtain a first fitness evaluation value; associate and store the first scheduling scheme and the first fitness evaluation value, and add them to the scheduling scheme group; when the number of schemes in the scheduling scheme group is greater than or equal to the number threshold, perform multi-constraint optimization based on the scheduling scheme group to obtain the scheduling scheme optimization result.

[0068] The weight configuration aims to determine the relative importance of the economic cost evaluation value and the energy-saving parameter evaluation value in the overall evaluation. This configuration reflects the strategic focus of the organization. For example, whether more emphasis is placed on cost savings or environmental sustainability. According to actual needs, assign the first weight to the economic cost evaluation value, indicating the importance of the cost factor in the decision-making process; assign the second weight to the energy-saving parameter evaluation value, indicating the importance of the energy-saving effect in the decision-making process. The sum of these two weights is equal to 1, ensuring the consistency and balance of the evaluation system.

[0069] Use the first weight and the second weight to perform weighted fusion on the economic cost evaluation value and the energy-saving parameter evaluation value. This fusion process takes into account their respective weights and synthesizes a comprehensive evaluation index as the first fitness evaluation value. The first fitness evaluation value reflects the overall performance of the first scheduling scheme under the established weights. A high fitness evaluation value indicates that the scheme performs well in terms of economy and environmental protection and is a choice with relatively good comprehensive performance.

[0070] Associate and store the first scheduling scheme and the first fitness evaluation value for subsequent comparison and selection. This can clearly show the performance of each scheme in the comprehensive evaluation, help compare the advantages and disadvantages of different schemes, and add them to the scheduling scheme group after associated storage. This scheduling scheme group contains multiple potential scheduling schemes, and each scheme has a specific fitness evaluation value, reflecting its performance under the current set conditions.

[0071] Preset a quantity threshold, which is the minimum number of schemes required before starting the multi-constraint optimization. This threshold ensures that the system has enough data for effective comparison and selection. When the number of schemes in the scheduling scheme group is greater than or equal to the quantity threshold, it means that there are enough schemes for optimization analysis. Multi-constraint optimization is an optimization process that considers multiple constraints, such as cost, energy efficiency, reliability, etc. The goal is to find the best comprehensive performance scheme. In this step, analyze all the schemes in the scheduling scheme group and use optimization algorithms to determine which schemes can best meet all the constraints. After the optimization process is completed, output the optimal scheduling scheme as the result of the scheduling scheme optimization. The optimal scheduling scheme provides the highest comprehensive benefit on the premise of meeting all the key performance indicators and constraint conditions.

[0072] Furthermore, according to the first weight and the second weight, fuse the economic cost evaluation value and the energy-saving parameter evaluation value to obtain the first fitness evaluation value, including:

[0073] When the economic cost evaluation value is less than the economic cost evaluation threshold and the energy-saving parameter evaluation value is less than or equal to the energy-saving parameter evaluation threshold, the first fitness evaluation value = the second weight * the normalized value of the energy-saving parameter evaluation value; when the economic cost evaluation value is greater than or equal to the economic cost evaluation threshold and the energy-saving parameter evaluation value is less than or equal to the energy-saving parameter evaluation threshold, the first fitness evaluation value = the second weight * the normalized value of the energy-saving parameter evaluation value - the first weight * the normalized value of the economic cost evaluation value; when the economic cost evaluation value is greater than or equal to the economic cost evaluation threshold and the energy-saving parameter evaluation value is greater than the energy-saving parameter evaluation threshold, the first fitness evaluation = - the first weight * the normalized value of the economic cost evaluation value.

[0074] When the economic cost evaluation value is less than the economic cost evaluation threshold, it indicates that the cost efficiency of the scheduling scheme is high and lower than the preset cost threshold, so the cost consideration can be relatively reduced; when the energy-saving parameter evaluation value is less than or equal to the energy-saving parameter evaluation threshold, it indicates that the scheduling scheme is not performing well in terms of energy saving and does not meet the preset energy-saving target. In this case, since the cost is already at a qualified level, energy-saving performance becomes a more critical evaluation indicator. In order to ensure the fairness and consistency of the evaluation, the energy-saving parameter evaluation value is normalized, and the original evaluation value is converted into a standardized proportional value, usually ranging from 0 to 1, to obtain the normalized value of the energy-saving parameter evaluation value. The calculation formula for the fitness evaluation value is: the first fitness evaluation value = the second weight * the normalized value of the energy-saving parameter evaluation value. This calculation method ensures that when cost is no longer the main limiting factor, the evaluation of the scheduling scheme depends more on its energy-saving effect.

[0075] When the economic cost evaluation value is greater than or equal to the economic cost evaluation threshold, it indicates that the scheduling scheme performs poorly in terms of cost control, and the cost exceeds the preset acceptable range; when the energy-saving parameter evaluation value is less than or equal to the energy-saving parameter evaluation threshold, it indicates that the scheduling scheme also fails to reach the expected level in terms of energy saving, that is, the energy consumption is relatively high. In this case, both the economic cost evaluation value and the energy-saving parameter evaluation value are normalized, and the fitness evaluation value is calculated as follows: first fitness evaluation value = second weight * normalized value of energy-saving parameter evaluation value - first weight * normalized value of economic cost evaluation value. This calculation method emphasizes the importance of balancing different performance indicators in the comprehensive evaluation, ensuring that the scheduling scheme can meet certain standards in terms of both cost and energy saving.

[0076] When the economic cost evaluation value is greater than or equal to the economic cost evaluation threshold, it indicates that the scheduling scheme performs poorly in cost control and the cost exceeds the preset acceptable range, so it needs to be analyzed in detail; when the energy-saving parameter evaluation value is greater than the energy-saving parameter evaluation threshold, it indicates that the scheduling scheme performs well in energy saving and meets the preset energy saving target. In this case, since the energy-saving performance is already at a qualified level, the economic cost becomes a more critical evaluation indicator, so the calculation formula of the fitness evaluation value is: the first fitness evaluation value = - the first weight * the normalized value of the economic cost evaluation value. This calculation method ensures that when energy saving is no longer the main limiting factor, the evaluation of the scheduling scheme depends more on its economic cost effect.

[0077] Furthermore, performing multi-constraint optimization based on the scheduling scheme group to obtain the scheduling scheme optimization result includes:

[0078] Sort the group of scheduling plans in descending order based on the fitness evaluation value to obtain the scheduling plan sorting result; extract the first quantity of head fitness plans and the second quantity of fitness tail plans of the scheduling plan sorting result; target the first quantity of head fitness plans, perform same-dimensional parameter mutation on the second quantity of fitness tail plans to obtain a set of new scheduling plans; when there are new scheduling plans in the set of new scheduling plans that simultaneously meet the two conditions that the economic cost evaluation value is less than the economic cost evaluation threshold and the energy-saving parameter evaluation value is greater than the energy-saving parameter evaluation threshold, output the scheduling plan optimization result; otherwise, perform loop analysis.

[0079] Sort the group of scheduling plans in descending order according to the fitness evaluation value, which can quickly identify which plans are superior to others in terms of comprehensive performance. This sorting is to ensure that the optimal scheduling plan is ranked at the front. After sorting, the scheduling plan sorting result is obtained. Among them, the plans with high fitness evaluation values show better economy and higher energy-saving effects, so they are regarded as better plans.

[0080] Extract the first quantity of head fitness plans from the scheduling plan sorting result. These are the plans with the highest fitness evaluation values in the sorting result, that is, the plans with the best performance. Selecting such plans can provide the best expected results for implementation; extract the second quantity of fitness tail plans from the scheduling plan sorting result. These are the plans with the lowest fitness evaluation values in the sorting result, that is, the plans with the worst performance. Identifying such plans helps to analyze which factors lead to poor scheduling performance and thus make improvements.

[0081] Same-dimensional parameter mutation is an optimization technique. The mutation of parameters is carried out in the same parameter dimension as the best plan. This means that the mutation operation does not introduce new variables or change the parameter structure, but adjusts the values of existing parameters to explore potential better solutions. Specifically, target the first quantity of head fitness plans to guide the mutation process, and perform same-dimensional parameter mutation on the second quantity of fitness tail plans. The purpose of mutation is to adjust these parameters in the same parameter dimension as the best plan to make them closer to or better than the performance of the best plan. Mutation includes increasing or decreasing certain parameter values, adjusting the time arrangement, changing the resource allocation, etc., depending on the nature and requirements of the scheduling plan. After performing same-dimensional parameter mutation on the parameters of the worst plan, a set of new scheduling plans is generated, forming a set of new scheduling plans for further evaluation and selection.

[0082] Check whether there is at least one solution in the newly generated set of scheduling enhancement solutions whose economic cost evaluation value is less than the economic cost evaluation threshold and whose energy-saving parameter evaluation value is greater than the energy-saving parameter evaluation threshold. These two conditions ensure that the selected solution is not only acceptable in terms of cost but also meets the target standard in terms of energy saving. If there are solutions that meet the above conditions, these solutions are determined to be optimization successes, and these solutions are output as recommended scheduling strategies and output as the optimization result of the scheduling solution.

[0083] Conversely, if no solution simultaneously meets the set thresholds for economic cost and energy saving, continue with analysis and adjustment, including readjusting parameters, rerunning the optimization algorithm, or exploring other potential adjustment strategies. Use a feedback loop to make fine adjustments to the scheduling strategy based on the performance of previous solutions, generate new scheduling solutions again, and re-evaluate whether these solutions meet the set criteria. This cyclic analysis process helps to continuously improve the quality of the scheduling solution and ensure that the final strategy is optimized in both key dimensions of cost and energy saving. The cyclic mechanism ensures that in the face of a complex operating environment and changing requirements, it can flexibly adapt and provide the best solution.

[0084] In summary, the method for intelligent scheduling and control of a microgrid provided by the embodiments of the present application has the following technical effects:

[0085] By means of the sensing nodes, the battery status and timestamp data are monitored in real time, enabling the rapid acquisition of the current energy storage status and time-related data of the power station. This real-time data collection provides accurate basic data for subsequent scheduling decisions, ensuring the timeliness and accuracy of the scheduling strategy. When the battery status data shows an anomaly, the relevant processes are automatically stopped to prevent possible equipment damage or efficiency degradation. When the battery is in a healthy state, the real-time data is used to match the scheduling constraint rules to ensure the optimization of energy distribution. Local sample adjacency analysis is performed based on the timestamp sensing data to predict the upcoming production demand power according to historical and real-time data, thereby enabling early energy distribution and planning, optimizing the energy utilization efficiency, making the energy supply more precise and efficient, and avoiding overproduction or insufficient supply. The scheduling scheme configuration channel generates a preliminary scheduling scheme based on the production demand power and the preset scheduling constraint rules, which improves the flexibility and adaptability of the scheduling scheme and can handle variable scheduling requirements. The scheduling scheme evaluation channel conducts a dual evaluation of the generated scheduling scheme in terms of economic cost and energy-saving effect. This evaluation mechanism ensures that the scheduling scheme can not only meet the actual power demand but also achieve the goals of cost-effectiveness and energy conservation, providing quantitative indicators for subsequent analysis. When the scheduling scheme does not meet the set thresholds in terms of cost or energy conservation, multi-constraint optimization is performed to find a scheme that can achieve the optimal cost and energy-saving effect while meeting all key performance indicators. This step not only ensures the safety and reliability of power supply but also emphasizes the maximization of economic and environmental benefits. According to the optimization results, intelligent scheduling control of the microgrid is executed, which not only improves the overall efficiency of energy use but also ensures that the requirements for power supply stability and sustainability are met, significantly enhancing the efficiency and effectiveness of energy management.

[0086] Embodiment 2. Based on the same inventive concept as the method for intelligent scheduling and control of a microgrid in the foregoing embodiment, as Figure 3 shown, an embodiment of the present application provides a system for intelligent scheduling and control of a microgrid. The system is embedded in a photovoltaic energy storage charging and discharging integrated station. The system includes sensing nodes and scheduling nodes. The system includes:

[0087] The perception data extraction module 10 is used to extract battery state perception data and timestamp perception data according to perception nodes; the scheduling constraint rule matching module 20 is used to stop the process when the battery state perception data belongs to an abnormal state, and when the battery state perception data belongs to a healthy state, match the scheduling constraint rules according to the timestamp perception data; the local sample adjacency analysis module 30 is used to perform local sample adjacency analysis according to the timestamp perception data to obtain the production demand power; the scheduling scheme configuration module 40 is used to configure the scheduling scheme based on the scheduling constraint rules and the production demand power through the scheduling scheme configuration channel of the scheduling node to obtain the first scheduling scheme; the evaluation value acquisition module 50 is used to analyze the first scheduling scheme through the scheduling scheme evaluation channel of the scheduling node to obtain the economic cost evaluation value and the energy-saving parameter evaluation value; the multi-constraint optimization module 60 is used to trigger when at least one of the economic cost evaluation value is greater than or equal to the economic cost evaluation threshold and the energy-saving parameter evaluation value is less than or equal to the energy-saving parameter evaluation threshold, perform multi-constraint optimization on the first scheduling scheme to obtain the scheduling scheme optimization result; the intelligent scheduling control module 70 is used to perform microgrid intelligent scheduling control according to the scheduling scheme optimization result.

[0088] Furthermore, the scheduling constraint rule matching module 20 includes:

[0089] The scheduling constraint rule description unit is used to describe that the scheduling constraint rules include power supply constraint types, power supply type priorities, and power supply constraint tasks, and the sum of the power supply type priorities is equal to 1; the first rule description unit is used to describe that when the battery state perception data belongs to the healthy state and the timestamp perception data belongs to the valley time zone, the power supply constraint types include large grid power supply and photovoltaic power supply, the large grid power supply priority ∈ [0, 0.5], the photovoltaic power supply priority ∈ [0.5, 1], and the power supply constraint tasks all include production power supply and energy storage charging; the second rule description unit is used to describe that when the battery state perception data belongs to the healthy state, the timestamp perception data belongs to the flat value time zone, and the energy storage battery power is greater than the discharge power threshold, the power supply constraint types include large grid power supply, photovoltaic power supply, and energy storage power supply, the sum of the large grid power supply priority and the energy storage power supply priority ∈ [0, 0.5], the photovoltaic power supply priority ∈ [0.5, 1], and the power supply constraint task includes production power supply; the third rule description unit is used to describe that when the battery state perception data belongs to the healthy state, the timestamp perception data belongs to the peak time zone, and the energy storage battery power is greater than the discharge power threshold, the power supply constraint types include large grid power supply, photovoltaic power supply, and energy storage power supply, the large grid power supply priority is equal to ∈ [0, 0.2], the sum of the energy storage power supply and the photovoltaic power supply priority ∈ (0.2, 1], and the power supply constraint task includes production power supply.

[0090] Furthermore, the scheduling constraint rule matching module 20 includes:

[0091] The fourth rule description unit is used to describe that when the battery state perception data belongs to the healthy state, and the timestamp perception data belongs to the flat value time zone, and the energy storage battery power is less than or equal to the discharge power threshold, the power supply constraint tasks all include production power supply and energy storage charging; the fifth rule description unit is used to describe that when the battery state perception data belongs to the healthy state, and the timestamp perception data belongs to the peak time zone, and the energy storage battery power is less than or equal to the discharge power threshold, the large power grid power supply constraint task includes production power supply, and the photovoltaic power supply constraint task includes production power supply and energy storage charging.

[0092] Furthermore, the local sample adjacency analysis module 30 includes:

[0093] The local production log collection unit is used to collect adjacent local production logs according to the timestamp perception data, wherein the local production logs include power consumption record data sets; the mode analysis unit is used to perform mode analysis on the power consumption record data sets to obtain the production demand power.

[0094] Furthermore, the evaluation value acquisition module 50 includes:

[0095] The evaluation node activation unit is used to activate the associated scheduling scheme evaluation node according to the scheduling constraint rule; the preprocessing unit is used to preprocess the first scheduling scheme through the encoding layer to obtain a dimensionless input vector; the first fitting unit is used to fit the dimensionless input vector through the economic cost evaluation layer of the associated scheduling scheme evaluation node and output the economic cost evaluation value; the second fitting unit is used to fit the dimensionless input vector through the energy-saving evaluation layer of the associated scheduling scheme evaluation node and output the energy-saving parameter evaluation value.

[0096] Furthermore, the multi-constraint optimization module 60 includes:

[0097] A weight configuration unit is used to configure a first weight for the economic cost evaluation value and a second weight for the energy-saving parameter evaluation value, where the sum of the first weight and the second weight is equal to 1; A fusion unit is used to fuse the economic cost evaluation value and the energy-saving parameter evaluation value according to the first weight and the second weight to obtain a first fitness evaluation value; An associated storage unit is used to store the first scheduling scheme and the first fitness evaluation value in an associated manner and add them to the scheduling scheme group; A multi-constraint optimization unit is used to perform multi-constraint optimization based on the scheduling scheme group when the number of schemes in the scheduling scheme group is greater than or equal to a threshold number to obtain the scheduling scheme optimization result.

[0098] Furthermore, the fusion unit includes:

[0099] A first evaluation value description channel is used to describe that when the economic cost evaluation value is less than the economic cost evaluation threshold and the energy-saving parameter evaluation value is less than or equal to the energy-saving parameter evaluation threshold, the first fitness evaluation value = the second weight * the normalized value of the energy-saving parameter evaluation value; A second evaluation value description channel is used to describe that when the economic cost evaluation value is greater than or equal to the economic cost evaluation threshold and the energy-saving parameter evaluation value is less than or equal to the energy-saving parameter evaluation threshold, the first fitness evaluation value = the second weight * the normalized value of the energy-saving parameter evaluation value - the first weight * the normalized value of the economic cost evaluation value; A third evaluation value description channel is used to describe that when the economic cost evaluation value is greater than or equal to the economic cost evaluation threshold and the energy-saving parameter evaluation value is greater than the energy-saving parameter evaluation threshold, the first fitness evaluation = - the first weight * the normalized value of the economic cost evaluation value.

[0100] Furthermore, the multi-constraint optimization unit includes:

[0101] An evaluation value sorting channel is used to sort the scheduling scheme group based on the fitness evaluation value from largest to smallest to obtain a scheduling scheme sorting result; A scheme extraction channel is used to extract the first number of leading fitness schemes and the second number of trailing fitness schemes of the scheduling scheme sorting result; A same-dimensional parameter mutation channel is used to perform same-dimensional parameter mutation on the second number of trailing fitness schemes with the first number of leading fitness schemes as the target to obtain a set of scheduling new schemes; An optimization result output channel is used to output the scheduling scheme optimization result when the set of scheduling new schemes has two conditions of simultaneously satisfying that the economic cost evaluation value is less than the economic cost evaluation threshold and the energy-saving parameter evaluation value is greater than the energy-saving parameter evaluation threshold; A loop analysis channel is used to otherwise perform loop analysis.

[0102] Through the foregoing detailed description of a method for intelligent scheduling and control of a microgrid, those skilled in the art can clearly understand a system for intelligent scheduling and control of a microgrid in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For related parts, reference can be made to the description in the method part.

[0103] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for intelligent dispatching and control of a microgrid, characterized in that: A system for intelligent dispatching and control of a microgrid, wherein the system is embedded in a photovoltaic storage charging and discharging integrated station, the system includes a sensing node and a dispatching node, and the method includes: According to the sensing node, extract the battery status sensing data and timestamp sensing data; When the battery status sensing data belongs to an abnormal state, the process is stopped; when the battery status sensing data belongs to a healthy state, the scheduling constraint rule is matched according to the timestamp sensing data; Performing local sample adjacency analysis based on the timestamp sensing data to obtain production demand power; Through the scheduling scheme configuration channel of the scheduling node, a scheduling scheme is configured based on the scheduling constraint rule and the production demand power to obtain a first scheduling scheme; Analyze the first scheduling scheme through the scheduling scheme evaluation channel of the scheduling node to obtain an economic cost evaluation value and an energy-saving parameter evaluation value; When at least one of the economic cost evaluation value is greater than or equal to the economic cost evaluation threshold and the energy-saving parameter evaluation value is less than or equal to the energy-saving parameter evaluation threshold is triggered, multi-constraint optimization is performed on the first scheduling scheme to obtain a scheduling scheme optimization result; Execute microgrid intelligent dispatching control according to the dispatching scheme optimization result; Among them, the optimization results of the scheduling scheme are obtained, including: Assigning a first weight to the economic cost evaluation value and a second weight to the energy-saving parameter evaluation value, wherein the sum of the first weight and the second weight is equal to 1; According to the first weight and the second weight, the economic cost evaluation value and the energy-saving parameter evaluation value are integrated to obtain a first fitness evaluation value; The first scheduling scheme and the first fitness evaluation value are associated and stored, and added into a scheduling scheme group; When the number of solutions in the scheduling solution group is greater than or equal to a quantity threshold, a multi-constraint optimization search is performed based on the scheduling solution group to obtain the scheduling solution optimization result.

2. A method for intelligent dispatching and control of a microgrid as claimed in claim 1, characterized in that: When the battery state sensing data belongs to a healthy state, matching the scheduling constraint rule according to the timestamp sensing data includes: The scheduling constraint rule includes a power supply constraint type, a power supply type priority, and a power supply constraint task, and the sum of the power supply type priority is equal to 1; When the battery state sensing data belongs to the healthy state, and the timestamp sensing data belongs to the valley time zone, the power supply constraint types include large power grid power supply and photovoltaic power supply, the large power grid power supply priority ∈ [0, 0.5], the photovoltaic power supply priority ∈ [0.5, 1], and the power supply constraint tasks include production power supply and energy storage charging; When the battery state sensing data belongs to the healthy state, and the timestamp sensing data belongs to the average time zone, and the energy storage battery power is greater than the discharge power threshold, the power supply constraint types include large grid power supply, photovoltaic power supply and energy storage power supply, the large grid power supply priority plus the energy storage power supply priority ∈ [0, 0.5], the photovoltaic power supply priority ∈ [0.5, 1], and the power supply constraint task includes production power supply; When the battery status sensing data belongs to the healthy state, and the timestamp sensing data belongs to the peak time zone, and the energy storage battery power is greater than the discharge power threshold, the power supply constraint types include large power grid power supply, photovoltaic power supply and energy storage power supply, the large power grid power supply priority is equal to ∈[0,0.2], the energy storage power supply plus the photovoltaic power supply priority ∈(0.2,1], and the power supply constraint task includes production power supply.

3. A method for intelligent dispatching and control of a microgrid as claimed in claim 2, characterized in that: Also includes: When the battery status sensing data belongs to the healthy state, and the timestamp sensing data belongs to the average time zone, and the energy storage battery power is less than or equal to the discharge power threshold, the power supply constraint tasks include production power supply and energy storage charging; When the battery status sensing data belongs to the healthy state, and the timestamp sensing data belongs to the peak time zone, and the energy storage battery power is less than or equal to the discharge power threshold, the large power grid power supply constraint task includes production power supply, and the photovoltaic power supply constraint task includes production power supply and energy storage charging.

4. A method for intelligent dispatching and controlling a microgrid according to claim 1, characterized in that: Perform local sample adjacency analysis based on the timestamp sensing data to obtain the production demand power, including: Collecting adjacent local production logs according to the timestamp sensing data, wherein the local production logs include a power consumption record data set; Performing mode analysis on the power consumption record data set to obtain the production demand power.

5. A method for intelligent dispatching and controlling a microgrid according to claim 1, characterized in that: The first scheduling scheme is analyzed through the scheduling scheme evaluation channel of the scheduling node to obtain an economic cost evaluation value and an energy-saving parameter evaluation value, including: According to the scheduling constraint rule, activating the associated scheduling scheme evaluation node; Preprocessing the first scheduling scheme through a coding layer to obtain a dimensionless input vector; Fitting the dimensionless input vector through the economic cost evaluation layer of the associated scheduling scheme evaluation node and outputting the economic cost evaluation value; The dimensionless input vector is fitted through the energy-saving evaluation layer of the associated scheduling scheme evaluation node, and the energy-saving parameter evaluation value is output.

6. A method for intelligent dispatching and controlling a microgrid according to claim 1, characterized in that: According to the first weight and the second weight, the economic cost evaluation value and the energy-saving parameter evaluation value are integrated to obtain a first fitness evaluation value, including: When the economic cost evaluation value is less than the economic cost evaluation threshold, and the energy-saving parameter evaluation value is less than or equal to the energy-saving parameter evaluation threshold, the first fitness evaluation value = the second weight * the normalized value of the energy-saving parameter evaluation value; When the economic cost evaluation value is greater than or equal to the economic cost evaluation threshold, and the energy-saving parameter evaluation value is less than or equal to the energy-saving parameter evaluation threshold, the first fitness evaluation value = the second weight * the normalized value of the energy-saving parameter evaluation value - the first weight * the normalized value of the economic cost evaluation value; When the economic cost evaluation value is greater than or equal to the economic cost evaluation threshold, and the energy-saving parameter evaluation value is greater than the energy-saving parameter evaluation threshold, the first fitness evaluation value=-the first weight*the normalized value of the economic cost evaluation value.

7. A method for intelligent dispatching and controlling a microgrid according to claim 1, characterized in that: Performing multi-constraint optimization based on the scheduling scheme group to obtain the scheduling scheme optimization result includes: Sort the scheduling scheme group from large to small based on the fitness evaluation value to obtain a scheduling scheme sorting result; Extracting a first number of head fitness schemes and a second number of tail fitness schemes from the scheduling scheme sorting results; Taking the first number of head fitness schemes as the target, performing the same-dimensional parameter mutation on the second number of tail fitness schemes to obtain a set of scheduling enhancement schemes; When the scheduling scheme set includes a scheduling scheme that satisfies both the conditions that the economic cost evaluation value is less than the economic cost evaluation threshold and the energy-saving parameter evaluation value is greater than the energy-saving parameter evaluation threshold, outputting the scheduling scheme optimization result; Otherwise, loop the analysis.

8. A microgrid intelligent dispatching and control system, characterized in that: The system is embedded in a photovoltaic storage charging and discharging integrated station, and the system includes a sensing node and a scheduling node, and is used to implement a method for intelligent scheduling and control of a microgrid according to any one of claims 1 to 7, and the system includes: A sensing data extraction module, used for extracting battery status sensing data and timestamp sensing data according to sensing nodes; A scheduling constraint rule matching module, used to stop the process when the battery status sensing data belongs to an abnormal state, and match the scheduling constraint rule according to the timestamp sensing data when the battery status sensing data belongs to a healthy state; A local sample adjacency analysis module, used to perform local sample adjacency analysis based on the timestamp sensing data to obtain production demand power; A scheduling scheme configuration module, configured to configure a scheduling scheme based on the scheduling constraint rule and the production demand power through a scheduling scheme configuration channel of a scheduling node to obtain a first scheduling scheme; An evaluation value acquisition module, used to analyze the first scheduling scheme through the scheduling scheme evaluation channel of the scheduling node to obtain an economic cost evaluation value and an energy-saving parameter evaluation value; A multi-constraint optimization module, configured to perform multi-constraint optimization on the first scheduling scheme to obtain a scheduling scheme optimization result when at least one of the economic cost evaluation value is greater than or equal to the economic cost evaluation threshold and the energy-saving parameter evaluation value is less than or equal to the energy-saving parameter evaluation threshold is triggered; An intelligent dispatching control module is used to perform microgrid intelligent dispatching control according to the optimization result of the dispatching scheme; Wherein, the multi-constraint optimization module includes: a weight configuration unit, configured to configure a first weight for the economic cost evaluation value and a second weight for the energy-saving parameter evaluation value, wherein the sum of the first weight and the second weight is equal to 1; a fusion unit, configured to fuse the economic cost evaluation value and the energy-saving parameter evaluation value according to the first weight and the second weight to obtain a first fitness evaluation value; an associative storage unit, used to associate and store the first scheduling scheme and the first fitness evaluation value, and add them into a scheduling scheme group; The multi-constraint optimization unit is used to perform multi-constraint optimization based on the scheduling scheme group when the number of schemes in the scheduling scheme group is greater than or equal to a quantity threshold, so as to obtain the scheduling scheme optimization result.

9. A microgrid intelligent dispatching and control system as claimed in claim 8, characterized in that: The scheduling constraint rule matching module includes: A scheduling constraint rule description unit, used to describe that the scheduling constraint rule includes a power supply constraint type, a power supply type priority, and a power supply constraint task, and the sum of the power supply type priority is equal to 1; A first rule description unit is used to describe that when the battery state sensing data belongs to the healthy state, and the timestamp sensing data belongs to the valley time zone, the power supply constraint types include large power grid power supply and photovoltaic power supply, the large power grid power supply priority ∈ [0,0.5], the photovoltaic power supply priority ∈ [0.5,1], and the power supply constraint tasks include production power supply and energy storage charging; A second rule description unit is used to describe that when the battery state sensing data belongs to the healthy state, and the timestamp sensing data belongs to the average time zone, and the energy storage battery power is greater than the discharge power threshold, the power supply constraint types include large power grid power supply, photovoltaic power supply and energy storage power supply, the large power grid power supply priority plus the energy storage power supply priority ∈ [0,0.5], the photovoltaic power supply priority ∈ [0.5,1], and the power supply constraint task includes production power supply; The third rule description unit is used to describe that when the battery state sensing data belongs to the healthy state, and the timestamp sensing data belongs to the peak time zone, and the energy storage battery power is greater than the discharge power threshold, the power supply constraint types include large power grid power supply, photovoltaic power supply and energy storage power supply, the large power grid power supply priority is equal to ∈[0,0.2], the energy storage power supply plus the photovoltaic power supply priority ∈(0.2,1], and the power supply constraint task includes production power supply.

10. A microgrid intelligent dispatching and control system as claimed in claim 9, characterized in that: The scheduling constraint rule matching module includes: A fourth rule description unit, used to describe that when the battery state sensing data belongs to the healthy state, and the timestamp sensing data belongs to the average time zone, and the energy storage battery power is less than or equal to the discharge power threshold, the power supply constraint tasks include production power supply and energy storage charging; The fifth rule description unit is used to describe that when the battery status perception data belongs to the healthy state, and the timestamp perception data belongs to the peak time zone, and the energy storage battery power is less than or equal to the discharge power threshold, the large power grid power supply constraint task includes production power supply, and the photovoltaic power supply constraint task includes production power supply and energy storage charging.

11. A microgrid intelligent dispatching and control system as claimed in claim 8, characterized in that: The local sample adjacency analysis module includes: A local production log collection unit, configured to collect adjacent local production logs according to the timestamp sensing data, wherein the local production logs include a power consumption record data set; The mode analysis unit is used to perform mode analysis on the power consumption record data set to obtain the production demand power.

12. A microgrid intelligent dispatching and control system as claimed in claim 8, characterized in that: The evaluation value acquisition module includes: An evaluation node activation unit, used to activate the associated scheduling scheme evaluation node according to the scheduling constraint rule; A preprocessing unit, configured to preprocess the first scheduling scheme through a coding layer to obtain a dimensionless input vector; A first fitting unit, configured to fit the dimensionless input vector through the economic cost evaluation layer of the associated scheduling scheme evaluation node, and output the economic cost evaluation value; The second fitting unit is used to fit the dimensionless input vector through the energy-saving evaluation layer of the associated scheduling scheme evaluation node, and output the energy-saving parameter evaluation value.

13. A microgrid intelligent dispatching and control system as claimed in claim 8, characterized in that: The fusion unit comprises: A first evaluation value description channel, used to describe that when the economic cost evaluation value is less than the economic cost evaluation threshold, and the energy-saving parameter evaluation value is less than or equal to the energy-saving parameter evaluation threshold, the first fitness evaluation value = the second weight * the normalized value of the energy-saving parameter evaluation value; The second evaluation value description channel is used to describe that when the economic cost evaluation value is greater than or equal to the economic cost evaluation threshold, and the energy-saving parameter evaluation value is less than or equal to the energy-saving parameter evaluation threshold, the first fitness evaluation value = the second weight * the normalized value of the energy-saving parameter evaluation value - the first weight * the normalized value of the economic cost evaluation value; The third evaluation value description channel is used to explain that when the economic cost evaluation value is greater than or equal to the economic cost evaluation threshold, and the energy-saving parameter evaluation value is greater than the energy-saving parameter evaluation threshold, the first fitness evaluation value = - the first weight * the normalized value of the economic cost evaluation value.

Images