An intelligent scheduling method and scheduling platform for a photovoltaic energy storage power station

Abstract

The present application provides an intelligent scheduling method and a scheduling platform for a photovoltaic energy storage power station, which relates to the technical field of charging scheduling, and includes: collecting multiple real-time operation data sets of a target photovoltaic energy storage power station in real time; dynamically monitoring the target photovoltaic energy storage power station to obtain operation environment information; determining the power flow of the target photovoltaic energy storage power station based on the multiple real-time operation data sets to obtain multiple power consumption status information; associating and mapping the multiple real-time operation data sets with the multiple power consumption status information according to the operation environment information to formulate a scheduling strategy; executing the scheduling strategy to perform reinforcement learning on the target photovoltaic energy storage power station to generate a learning feedback result, and interactively optimizing the scheduling strategy according to the learning feedback result to generate a scheduling optimization strategy to execute the intelligent scheduling of the target photovoltaic energy storage power station. The present application solves the technical problem that the existing power scheduling method cannot dynamically adjust the scheduling strategy according to the change of the real-time operation environment, resulting in the decrease of the power utilization rate, and realizes the maximization of the power configuration efficiency.

Description

Technical Field

[0001] This application relates to the technical field of charging scheduling, and particularly to an intelligent scheduling method and a scheduling platform for a photovoltaic energy storage power station. Background Art

[0002] With the popularization of new energy vehicles and the demand for energy transformation, the integrated application demand of photovoltaic power generation, energy storage systems, and electric vehicle charging functions has gradually increased. As a new type of energy facility that combines solar power generation and energy storage systems, photovoltaic energy storage power stations have gradually become a key technology in the photovoltaic energy storage charging system.

[0003] Currently, most of the existing charging scheduling for photovoltaic energy storage power stations in the market is a static scheduling strategy based on demand and power prediction. By analyzing historical data to predict future power consumption trends and making scheduling decisions through static optimization algorithms. Although the charging efficiency has been improved to a certain extent, its limitations are also very obvious. Due to the lack of effective integration of real-time operation data, the existing scheduling strategies often cannot flexibly respond to environmental changes and grid load fluctuations. Especially in non-linear situations such as sudden changes in light intensity and sudden surges in power demand, the fixed scheduling logic is difficult to adjust in a timely manner, easily causing resource waste or power supply tension, resulting in a significant decrease in the power utilization rate, unable to achieve the best resource allocation, and affecting the charging efficiency and economy. In summary, the existing charging scheduling methods lack adaptability and have a slow response speed, making it difficult to meet the growing demand for flexible scheduling. Summary of the Invention

[0004] This application provides an intelligent scheduling method and a scheduling platform for a photovoltaic energy storage power station, which solves the technical problem that the existing power scheduling methods rely on power prediction and fixed strategies for scheduling management and cannot dynamically adjust the scheduling strategy according to changes in the real-time operation environment, resulting in a decrease in power utilization rate. It achieves the technical effects of improving the flexibility and adaptability of power scheduling during the charging process of the photovoltaic energy storage power station, and optimizing the power configuration efficiency and resource utilization rate.

[0005] In view of the above problems, on the one hand, this application provides an intelligent scheduling method for a photovoltaic energy storage power station. The method includes: real-time collecting a target photovoltaic energy storage power station through a data collection unit to obtain a plurality of real-time operation data sets; dynamically monitoring the target photovoltaic energy storage power station according to the plurality of real-time operation data sets to obtain operation environment information; determining the power flow of the target photovoltaic energy storage power station based on the plurality of real-time operation data sets to obtain a plurality of power consumption state information; associating and mapping the plurality of real-time operation data sets with the plurality of power consumption state information according to the operation environment information to formulate a scheduling strategy; executing the scheduling strategy to perform reinforcement learning on the target photovoltaic energy storage power station to generate a learning feedback result, and interactively optimizing the scheduling strategy according to the learning feedback result to generate a scheduling optimization strategy to execute the intelligent scheduling of the target photovoltaic energy storage power station.

[0006] On the other hand, the present application also provides an intelligent scheduling platform for a photovoltaic and energy storage power station. The platform includes: an operation data acquisition module, which is used to perform real-time acquisition on a target photovoltaic and energy storage power station through a data acquisition unit to obtain a plurality of real-time operation data sets; an operation environment monitoring module, which is used to perform dynamic monitoring on the target photovoltaic and energy storage power station according to the plurality of real-time operation data sets to obtain operation environment information; a power consumption status determination module, which is used to perform power flow determination on the target photovoltaic and energy storage power station based on the plurality of real-time operation data sets to obtain a plurality of power consumption status information; a scheduling strategy formulation module, which is used to perform association mapping between the plurality of real-time operation data sets and the plurality of power consumption status information according to the operation environment information to formulate a scheduling strategy; a scheduling strategy optimization module, which is used to perform reinforcement learning on the target photovoltaic and energy storage power station by executing the scheduling strategy to generate a learning feedback result, and perform interactive optimization on the scheduling strategy according to the learning feedback result to generate a scheduling optimization strategy to execute the intelligent scheduling of the target photovoltaic and energy storage power station.

[0007] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0008] Through the data acquisition unit, real-time acquisition is performed on the target photovoltaic and energy storage power station to obtain a plurality of real-time operation data sets, timely capturing the state changes of the photovoltaic and energy storage power station, providing a basis for subsequent dynamic monitoring and scheduling decisions. Dynamic monitoring is performed on the target photovoltaic and energy storage power station according to the plurality of real-time operation data sets to obtain operation environment information, ensuring timely adjustment of the scheduling strategy under changing external conditions. Power flow determination is performed on the target photovoltaic and energy storage power station based on the plurality of real-time operation data sets to identify the current power flow situation, obtaining a plurality of power consumption status information, thereby optimizing the configuration and use of electric energy. Association mapping is performed between the plurality of real-time operation data sets and the plurality of power consumption status information according to the operation environment information to formulate a scheduling strategy. Reinforcement learning is performed on the target photovoltaic and energy storage power station by executing the scheduling strategy to generate a learning feedback result, and interactive optimization is performed on the scheduling strategy according to the learning feedback result to generate a scheduling optimization strategy to execute the intelligent scheduling of the target photovoltaic and energy storage power station.

[0009] In summary, the present application significantly improves the scheduling intelligence level of the photovoltaic and energy storage power station by integrating technical means such as real-time data acquisition, dynamic monitoring, power flow determination, association mapping, and reinforcement learning, makes full use of operation data, responds to changes in the operation environment in real time, and improves the operation efficiency and energy management efficiency of the photovoltaic and energy storage power station.

[0010] The above description is only an overview of the technical solution of this application. In order 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 following specific embodiments of this application are specifically given. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a schematic flowchart of an intelligent scheduling method for a photovoltaic energy storage power station provided by an embodiment of this application.

[0012] Figure 2 It is a schematic flowchart of formulating a scheduling strategy in an intelligent scheduling method for a photovoltaic energy storage power station provided by an embodiment of this application.

[0013] Figure 3 It is a schematic flowchart of generating a learning feedback result in an intelligent scheduling method for a photovoltaic energy storage power station provided by an embodiment of this application.

[0014] Figure 4 It is a schematic structural diagram of an intelligent scheduling platform for a photovoltaic energy storage power station provided by an embodiment of this application.

[0015] Description of reference numerals: The operation data acquisition module 10, the operation environment monitoring module 20, the power consumption status determination module 30, the scheduling strategy formulation module 40, and the scheduling strategy optimization module 50. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] An embodiment of this application provides an intelligent scheduling method and a scheduling platform for a photovoltaic energy storage power station, which can collect the operation data of the target photovoltaic energy storage power station in real time, dynamically monitor the operation environment, determine the power consumption status information in combination with the real-time operation data, formulate a scheduling strategy according to the power consumption logic and priority, and generate a final scheduling optimization strategy through reinforcement learning. It solves the technical problem that the existing power energy scheduling method depends on power energy prediction and fixed strategies for scheduling management, and cannot dynamically adjust the scheduling strategy according to the changes in the real-time operation environment, resulting in a decrease in power energy utilization rate, and achieves the technical effects of improving the flexibility and adaptability of power energy scheduling during the charging process of the photovoltaic energy storage power station, and optimizing the power energy configuration efficiency and resource utilization rate.

[0017] Embodiment 1, as Figure 1 shown, an embodiment of this application provides an intelligent scheduling method for a photovoltaic energy storage power station, and the method includes:

[0018] Step S1: Perform real-time collection on the target photovoltaic energy storage power station through a data collection unit to obtain a plurality of real-time operation data sets.

[0019] Specifically, the data acquisition unit is a system composed of a combination of hardware and software, which is responsible for collecting the operation data of the photovoltaic energy storage power station in real time. It usually includes various sensors, as well as data recorders and communication devices. The real-time operation data set refers to various data on the state of the photovoltaic energy storage power station collected within a specific time, such as power generation, energy storage power, environmental temperature, etc.

[0020] Through various sensors of the data acquisition unit, the performance data of photovoltaic panels (such as voltage, current, temperature, and power generation), the operation data of the energy storage system (such as the charge and discharge state, voltage, current, and temperature of the battery), and the inverter and grid connection data are continuously recorded, and then the collected data is transmitted to the central data processing unit through communication devices (such as wireless networks or wired networks). In this process, the data recorder formats and stores the received raw data to form multiple real-time operation data sets. These real-time operation data sets can reflect the operation state of the photovoltaic energy storage power station and provide data support for the subsequent formulation of dispatching strategies. For example, the light intensity and power generation per hour are recorded through the sensors on the photovoltaic panels, and the power state of the battery, such as the number of charge and discharge times and the battery temperature, is recorded through the battery management system.

[0021] Step S2: Dynamically monitor the target photovoltaic energy storage power station based on the multiple real-time operation data sets to obtain operation environment information.

[0022] Specifically, the operation environment information includes all factors affecting the performance of the photovoltaic energy storage power station, such as weather conditions (light intensity, air temperature, wind speed), grid load conditions, and equipment status, etc. Based on the multiple real-time operation data sets obtained in Step S1, the target photovoltaic energy storage power station is dynamically monitored to evaluate the operation environment information of the photovoltaic energy storage power station. First, analyze the photovoltaic power generation data and combine the real-time weather information (such as the light intensity and air temperature data provided by the meteorological station) to evaluate the current power generation capacity of the photovoltaic energy storage power station. Secondly, monitor the grid load conditions and analyze the real-time demand of the grid to facilitate adjusting the operation strategy of the photovoltaic energy storage power station according to the fluctuations of the grid load. In addition, it also includes monitoring the equipment status in combination with the real-time operation data set, including the health status of the battery, the efficiency of the power generation equipment, etc., to ensure the stability of the operation of the target photovoltaic energy storage power station.

[0023] Through dynamic monitoring, the operation environment information of the photovoltaic energy storage power station can be obtained in real time, providing a basis for subsequent adjustment of the operation strategy, improving the overall operation efficiency, and optimizing the utilization of electric energy.

[0024] Step S3: Determine the power flow of the target photovoltaic energy storage power station based on the multiple real-time operation data sets to obtain multiple power consumption status information.

[0025] Specifically, by using multiple real-time operation datasets collected previously, analyze and judge the internal power flow situation of the photovoltaic and energy storage power station, including the charge and discharge status, storage status, etc. of the electric energy, so as to obtain multiple power consumption status information.

[0026] Extract relevant data points from the real-time operation dataset, such as the voltage, charging current, and discharging current of the battery, etc. Evaluate the power flow path and status in the photovoltaic and energy storage power station according to these data points. If the charging current of the battery is greater than the discharging current, it is determined that the battery is charging; otherwise, it is determined that the battery is in the discharging state. In addition, if the battery is in the standby state and there is no power flow, it is marked as the standby state. For example, assume that at a certain moment, the charging current of the battery is recorded as 5A and the discharging current is 2A, which means the battery is charging. In this process, the determination of the power flow can also be based on the output of the photovoltaic power generation. For example, the power generation of the photovoltaic system is 10kW, and the charging state of the battery and the grid load state determine the direction of the power flow.

[0027] Through these power consumption status information, the operation status of the target photovoltaic and energy storage power station can be understood in real time, and at the same time, it provides an important basis for subsequent scheduling decisions, so as to ensure that the photovoltaic and energy storage power station can optimize resource allocation while efficiently utilizing energy.

[0028] Step S4: According to the operation environment information, perform an association mapping between the multiple real-time operation datasets and the multiple power consumption status information, and formulate a scheduling strategy.

[0029] Specifically, deeply integrate all the real-time operation datasets collected in Step S2 and Step S3 with the power consumption status information. According to the collected operation environment information, analyze the power consumption status under specific conditions and the corresponding real-time operation datasets, identify the best operation mode under specific conditions, and establish a mapping relationship between the multiple real-time operation datasets and the multiple power consumption status information. Formulate a specific scheduling strategy according to the result of the association mapping. The scheduling strategy can include: when the light intensity exceeds a certain threshold, give priority to charging. When the grid load is low and the battery charging status is good, allow the power to flow back to the grid. When the power consumption demand is at a peak, adjust the battery discharge to support the charging pile load. By formulating a scheduling strategy, the resources of the photovoltaic and energy storage power station can be effectively utilized, while improving the overall operation efficiency, reducing energy waste and costs.

[0030] Step S5: Execute the scheduling strategy to perform reinforcement learning on the target photovoltaic and energy storage power station, generate a learning feedback result, and perform interactive optimization on the scheduling strategy according to the learning feedback result to generate a scheduling optimization strategy to execute the intelligent scheduling of the target photovoltaic and energy storage power station.

[0031] Specifically, reinforcement learning is a machine learning method that learns the optimal strategy through interaction with the environment to maximize the cumulative reward. The learning feedback result is the result data collected after executing the scheduling strategy, which is used to evaluate the effectiveness of the strategy and usually includes performance metrics and actual operating conditions. The scheduling optimization strategy is a more effective scheduling strategy generated after reinforcement learning and interactive optimization, which can improve the overall performance of the PV energy storage power station. Execute the pre-established scheduling strategy to perform actual operations on the PV energy storage power station, such as controlling the charging and discharging of the battery and grid interaction. During this process, a large amount of operation data is collected, such as power changes, power generation, power consumption status, and its impact on the performance of the PV energy storage power station. These data constitute the learning feedback result. Use the reinforcement learning algorithm to evaluate the scheduling strategy. Commonly used reinforcement learning algorithms include Q-learning or Deep Q-Network (DQN). Evaluate the effectiveness of the scheduling strategy according to a specific reward function. For example, if the power purchase cost is reduced or the reverse power flow income is increased while meeting the load demand, a positive reward is given; otherwise, a negative reward is given. Based on the learning feedback result, perform interactive optimization. Specifically, analyze the learning feedback result, identify which scheduling decisions have produced good results, and adjust the scheduling strategy accordingly. For example, if it is found that the PV power generation efficiency is high under a certain specific weather condition and this advantage is not fully utilized according to the current scheduling strategy, then adjust the strategy accordingly to increase the charging frequency under this condition. After interactive optimization, a new scheduling optimization strategy is generated. This strategy will be used to guide the future operation of the PV energy storage power station. For example, the scheduling optimization strategy may specify that under high-light and high-temperature weather, priority should be given to charging and reducing dependence on the grid, thereby improving the utilization efficiency of renewable energy.

[0032] Through the feedback optimization process, the PV energy storage power station can achieve intelligent scheduling, continuously adapt to environmental changes, optimize the operation efficiency, ultimately maximize energy management and minimize costs, improve the flexibility and response speed of power scheduling, and ensure that the PV energy storage power station can achieve the best performance under different operating conditions.

[0033] Furthermore, step S1 of the embodiment of the present application further includes:

[0034] Step S11: Perform power consumption simulation according to multiple power consumption demand information to generate multiple power consumption simulation data.

[0035] Step S12: Perform power consumption analysis according to multiple power consumption simulation data to generate a power consumption simulation analysis result, score the power consumption simulation analysis result, and obtain multiple power consumption score data.

[0036] Step S13: Serialize the multiple power consumption score data in descending order to determine the PV energy storage sequence.

[0037] Step S14: Based on the photovoltaic energy sequence, multiple power storage data of the photovoltaic power station are retrieved, and the multiple power storage data of the photovoltaic power station are judged in turn whether they meet the preset power threshold, and the photovoltaic power consumption scheduling priority is generated.

[0038] Step S15: select multiple data acquisition devices according to the priority of PV-storage-power-consumption scheduling, perform associated configuration, and construct the data acquisition unit.

[0039] Step S16: setting a collection frequency based on the plurality of electricity demand information, and performing data sensing on the target photovoltaic power station through the data collection unit according to the collection frequency to obtain a plurality of initial sensing data.

[0040] Step S17: synchronizing the multiple initial sensing data according to the operating sequence to obtain the multiple real-time operating data sets.

[0041] Specifically, electricity demand information refers to the specific data and indicators of electricity demand during the operation of the photovoltaic power station, including but not limited to grid demand, charging pile demand, energy storage system demand, other power loads (such as lighting, air conditioning, etc.). Use simulation software (such as MATLAB Simulink) to build models, simulate different electricity demand scenarios, and generate multiple hypothetical data sets about electricity demand, supply and operation status, namely electricity simulation data.

[0042] Conduct in-depth electricity analysis on these simulation data to identify different electricity trends, demand patterns and performance indicators, determine the electricity consumption corresponding to different electricity demands, including valley electricity consumption, photovoltaic power consumption, energy storage system power consumption, etc., and generate electricity simulation analysis results. Evaluate the energy loss, acquisition efficiency and electricity cost of the electricity simulation analysis results, score these simulation analysis results, and obtain multiple electricity scoring data corresponding to multiple electricity demands. These scores reflect the efficiency and economy of electricity consumption under different simulation scenarios. Serialize these scoring data in descending order to form a photovoltaic energy storage sequence, which represents the priority of electricity demand. This sequence provides a basis for subsequent scheduling decisions.

[0043] Based on the photovoltaic energy sequence, multiple power storage data of the photovoltaic power station are retrieved, and the data are judged one by one whether they meet the preset power threshold, so as to generate the priority of photovoltaic power dispatch. In power dispatch, in order to maximize energy benefits and save electricity costs, valley electricity and photovoltaic power are preferentially dispatched to provide power for charging pile users; at the same time, under the premise of meeting the power load, it is judged whether to reverse the grid.

[0044] The judgment of the dispatching priority of photovoltaic, energy storage, and electric vehicle charging mainly depends on the power of photovoltaic, energy storage, charging piles, and other electrical loads. Specifically, it includes: First, detect whether the charging pile is in the charging state, that is, whether the power of the charging pile is zero. When the charging pile is in the charging state (P cp > 0), power is supplied to the charging pile in the order of photovoltaic power generation, valley electricity, and energy storage system. If the current time period is the valley electricity period and the photovoltaic power just meets the demand of the charging pile, that is, P cp -P pv = 0, use photovoltaic power to supply power to the charging pile; if the current time period is the valley electricity period and the photovoltaic power is excessive, that is, P cp -P pv < 0, use photovoltaic power to supply power to the charging pile and use the remaining electric energy to supplement the energy storage system; if the current time period is the valley electricity period and the photovoltaic power is insufficient, that is, P cp -P pv > 0, use photovoltaic power and draw on the power grid to supply power to the charging pile.

[0045] If the current time period is not the valley electricity period and the photovoltaic power just meets the demand of the charging pile, that is, P cp -P pv = 0, use photovoltaic power to supply power to the charging pile; if the current time period is the valley electricity period and the photovoltaic power is excessive, that is, P cp -P pv < 0, use photovoltaic power to supply power to the charging pile and use the remaining electric energy to supplement the energy storage system; if the current time period is the valley electricity period and the photovoltaic power is insufficient, that is, P cp -P pv > 0, use photovoltaic power and draw on the electric energy of the energy storage system to supply power to the charging pile.

[0046] When the charging pile is in the standby state (P cp = 0), electric energy is supplied to the energy storage system in the order of photovoltaic power generation and valley electricity. If the current time period is the valley electricity period and the photovoltaic is in the power generation state, on the premise of giving priority to meeting other loads, use photovoltaic electric energy to charge the energy storage system. When the photovoltaic power generation power does not meet the maximum charging power, draw on the power grid electric energy to supplement it to achieve charging the energy storage system with the maximum charging power. If the current time period is the valley electricity period and the photovoltaic is not in the power generation state, on the premise of giving priority to meeting other loads, draw on the power grid electric energy to charge the energy storage system. If the current time period is not the valley electricity period, use photovoltaic electric energy to charge the energy storage system.

[0047] Among them, P cp is the real-time power consumption of the charging pile. If there are multiple charging piles, it is the sum of multiple charging piles; P pv is the real-time power generation of photovoltaic power generation.

[0048] According to the dispatching priority of photovoltaic energy storage and electricity consumption, select suitable data acquisition devices for associated configuration to construct a data acquisition unit. For example, a light intensity sensor can be selected to monitor the light intensity, a battery management system (BMS) can be selected to monitor the battery status, and an electricity meter can be selected to measure the power of photovoltaic, energy storage, charging piles and other electrical loads in real time. Integrate the selected multiple data acquisition devices to construct a complete data acquisition unit to meet the requirements of real-time data acquisition and ensure the accurate acquisition of the operation data of the power station.

[0049] Based on the determined electricity demand information, set an appropriate acquisition frequency. A higher frequency can be set for key parameters, and the frequency for non-key parameters can be appropriately reduced. This not only ensures the timeliness of the data but also avoids unnecessary resource consumption. For example, the power generation data is acquired once a minute. Then, through the configured data acquisition unit, data sensing is performed according to the set frequency to obtain multiple initial sensing data.

[0050] Integrate the multiple initial sensing data collected according to the time stamp to ensure that the data is continuous and consistent in time, forming a complete set of multiple real-time operation data sets, providing an accurate and reliable data basis for subsequent dynamic monitoring and decision-making analysis.

[0051] Furthermore, step S3 of the embodiment of the present application further includes:

[0052] Step S31: Capture power generation data according to the multiple real-time operation data sets according to the acquisition frequency.

[0053] Step S32: Set a power flow determination condition based on the power generation data, and formulate a power flow determination rule based on the power flow determination condition.

[0054] Step S33: Analyze and integrate the multiple real-time operation data sets to construct a set of operation state vectors.

[0055] Step S34: According to the power flow determination rule, determine whether the set of operation state vectors meets the power flow determination condition.

[0056] Step S35: If the set of operation state vectors meets the power flow determination condition, perform power consumption analysis on the target photovoltaic energy storage power station according to the set of operation state vectors to generate power consumption preference data.

[0057] Step S36: Perform power consumption identification according to the power consumption preference data to generate multiple power consumption labels.

[0058] Step S37: Add the multiple power consumption labels to the multiple power consumption status information.

[0059] Specifically, photovoltaic power generation data refers to the power data generated by a photovoltaic power generation system, usually measured in kilowatts (kW) or kilowatt-hours (kWh), which reflects the power generation capacity. The power flow determination conditions are the criteria used to evaluate the power flow status, including specific current values, power, and voltage, etc. The power flow determination rules are the specific determination logics formulated according to the power flow determination conditions, which clarify how to judge the power flow status. The electricity consumption preference data is the information obtained based on electricity consumption analysis, which reflects the electricity consumption trends and habits of the power station. The electricity consumption label is an identifier assigned to different electricity consumption states or modes, which is used for classifying and managing the electricity consumption.

[0060] Precisely extract the photovoltaic power generation data from the real-time operation dataset according to the previously set collection frequency. This is the basis for understanding the power generation capacity of the power station and is also the key to subsequent determination of power flow. Based on the operating characteristics and operating objectives of the power station (such as minimizing energy consumption and maximizing benefits), set the power flow determination conditions. For example, when the charging pile power is greater than 0, it means the charging pile is charging; when the charging pile power is equal to 0, it means the charging pile is in standby state. According to the power flow determination conditions, formulate the power flow determination rules. For example, during the charging process of the charging pile, if the current time is in the valley electricity period, the grid power is preferentially used for charging; if the current time is not in the valley electricity period, the photovoltaic power is preferentially used for charging. When the photovoltaic power is insufficient, the energy storage system power is released for charging; when the photovoltaic power is excessive, the excess power is stored. During the standby process of the charging pile, if the current time is in the valley electricity period, the grid power is preferentially used for charging the energy storage system; if the current time is not in the valley electricity period, the photovoltaic power is used for charging the energy storage system.

[0061] Parse and integrate multiple real-time operation datasets to construct an operation status vector set. The operation status vector set includes multi-dimensional data such as photovoltaic power generation, battery power, charging current, and discharging current, which is represented in the form of vectors for subsequent calculation and analysis.

[0062] According to the power flow determination rules, determine whether the operation status vector set meets the power flow determination conditions. If the operation status vector set meets the power flow determination conditions, conduct electricity consumption analysis on the target photovoltaic energy storage power station based on the operation status vector set to identify electricity consumption preferences, such as high energy consumption periods, electricity consumption patterns, etc., which reflect the electricity consumption patterns of the power station under different conditions. Conduct electricity consumption identification based on the electricity consumption preference data to generate multiple electricity consumption labels, such as "efficient charging", "low load discharging", etc. These labels are used to describe the electricity consumption status of the power station in different scenarios. Add the generated multiple electricity consumption labels to multiple electricity consumption status information to enrich the data dimension, providing more comprehensive information support for subsequent scheduling and optimization decisions, so as to better understand and manage the electricity consumption of the target photovoltaic energy storage power station and achieve efficient energy utilization.

[0063] Furthermore, as Figure 2As shown in the figure, step S4 of the embodiment of the present application further includes:

[0064] Step S41: Perform multi-dimensional demand analysis on the target photovoltaic energy storage power station according to the operation environment information to determine the power station demand analysis result, and the power station demand analysis result includes multiple operation demand information.

[0065] Step S42: Map the multiple real-time operation data sets to the operation state vector set according to the power consumption preference data, and draw a power consumption trend curve graph.

[0066] Step S43: Based on the power consumption trend curve graph, perform associated matching with the multiple power consumption labels to construct a power consumption priority list.

[0067] Step S44: Traverse and connect the target photovoltaic energy storage power station according to the power consumption priority list to construct a power consumption topology structure.

[0068] Step S45: Set a scheduling target according to the power consumption topology structure in combination with the multiple power consumption demand information, and formulate the scheduling strategy of the target photovoltaic energy storage power station according to the scheduling target in combination with the multiple operation demand information.

[0069] Specifically, the power consumption trend curve graph is a graphical representation of the power consumption change trend of the power station over a period of time, usually used to identify power consumption patterns and predict future demands. The power consumption priority list is the order of power consumption priorities determined according to power consumption demands and power consumption labels, which helps to guide the formulation of the power energy scheduling strategy. The power consumption topology structure is the structure representing the connection relationship between the power consumption devices of the power station, which helps to visualize the power flow path and dependencies. The scheduling target is the power energy scheduling direction and target set according to the actual demands and operation status of the power station.

[0070] Based on the operation environment information, comprehensively analyze the operation demands of the photovoltaic energy storage power station, such as the charging demands of charging piles, the status of the energy storage system, the photovoltaic power generation amount, etc., to determine the power station demand analysis result. These analysis results include detailed operation demand information (system stability, cost control, etc.).

[0071] According to the power consumption preference data, map the real-time operation data set to the operation state vector set, and use a data visualization tool (such as Matplotlib) to draw a power consumption trend curve graph, and draw a curve graph reflecting the power consumption change law, that is, the power consumption trend curve graph. Based on the power consumption trend curve graph, perform associated matching with multiple power consumption labels, and identify the power consumption state with the highest priority through data analysis to construct a power consumption priority list.

[0072] According to the electricity consumption priority list, traverse all electricity-consuming units, construct a detailed electricity consumption topology structure, display the connection relationships among photovoltaic power generation, energy storage devices, and the power grid, and ensure the efficient distribution and utilization of electric energy. Combine the electricity consumption demand information, operation demand information, and electricity consumption topology structure to set clear scheduling objectives. Based on the scheduling objectives, comprehensively consider the photovoltaic output, energy storage status, and power grid conditions, and formulate a scheduling strategy to ensure that both the operation requirements are met and the operation cost is optimized.

[0073] Step S4 transforms the complex power station operation requirements into concrete strategic instructions through in-depth analysis and meticulous planning, achieving comprehensive and intelligent scheduling management of the photovoltaic and energy storage power station.

[0074] Furthermore, step S43 of the embodiment of the present application further includes:

[0075] Step S43-1: Conduct feature analysis based on the electricity consumption trend curve graph, and extract multiple electricity consumption features.

[0076] Step S43-2: Conduct electricity consumption evaluation according to the multiple electricity consumption features, identify the electricity consumption trend curve graph based on the evaluation results, and determine multiple electricity consumption extreme values, where the multiple electricity consumption extreme values include multiple electricity consumption peaks and multiple electricity consumption valleys.

[0077] Step S43-3: Traverse the multiple electricity consumption tags to perform correlation matching on the multiple electricity consumption peaks, and obtain the first correlation matching result.

[0078] Step S43-4: Traverse the multiple electricity consumption tags to perform correlation matching on the multiple electricity consumption valleys, and obtain the second correlation matching result.

[0079] Step S43-5: Perform weight allocation according to the first correlation matching result and the second correlation matching result, generate multiple weight coefficients, and construct the electricity consumption priority list according to the multiple weight coefficients in combination with the electricity consumption trend curve graph.

[0080] Specifically, conduct feature analysis based on the electricity consumption trend curve graph to extract multiple electricity consumption features. This process can use time series analysis tools (such as the Statsmodels library in Python) to identify the periodicity and trends in the data. Conduct electricity consumption evaluation based on the extracted electricity consumption features, including calculating statistical indicators such as the standard deviation and mean of electricity consumption, and using peak detection algorithms to identify the extreme values in the electricity consumption trend, namely multiple electricity consumption peaks and multiple electricity consumption valleys.

[0081] Traverse multiple electricity consumption tags, find the tags that match the electricity peak value, generate the first associated matching result to identify the main electricity consumption types during peak electricity consumption periods. Similarly, traverse multiple electricity consumption tags, perform associated matching on multiple electricity valley values, and obtain the second associated matching result to identify the electricity consumption characteristics during valley electricity consumption periods.

[0082] Use a weighted algorithm to assign weights according to the importance and occurrence frequency of the electricity consumption tags in the first associated matching result and the second associated matching result, calculate the weight coefficients for different electricity consumption states, and these weight coefficients reflect the importance levels of different electricity consumption states. After generating multiple weight coefficients, combine with the electricity consumption trend curve graph to construct an electricity consumption priority list, providing a basis for formulating subsequent scheduling strategies.

[0083] Through this series of steps, the electricity consumption pattern can be identified in detail, and based on this, a priority list can be constructed to provide a basis for subsequent scheduling decisions, ensuring efficient response and resource allocation in different electricity consumption scenarios.

[0084] Further, as Figure 3 shown, in step S5 of the embodiment of the present application, when implementing the scheduling strategy for the target photovoltaic energy storage power station to perform reinforcement learning and generate a learning feedback result, it further includes:

[0085] Step S51: Implement the scheduling strategy for the target photovoltaic energy storage power station according to the multiple electricity consumption state information to determine multiple electricity consumption scheduling actions.

[0086] Step S52: Calculate rewards based on the multiple electricity consumption scheduling actions to obtain multiple scheduling reward data, and the multiple scheduling reward data includes positive reward data and negative reward data.

[0087] Step S53: Use the positive reward data as the positive learning target and the negative reward data as the negative learning target to perform reinforcement learning on the target photovoltaic energy storage power station to generate a learning record data set.

[0088] Step S54: Set a self-check cycle based on the multiple real-time operation data sets, and perform self-check feedback on the learning record data set according to the self-check cycle to generate the learning feedback result.

[0089] Specifically, the power consumption dispatching action refers to the specific operations performed on the photovoltaic energy storage power station according to the dispatching strategy, including behaviors such as charging, discharging, and backflow to the power grid. The dispatching reward data is the reward data calculated based on the effect of the power consumption dispatching action, including positive rewards and negative rewards. The positive learning objective is the positive effect expected to be achieved in reinforcement learning, usually related to positive rewards. The negative learning objective is the effect that needs to be avoided in reinforcement learning, usually related to negative rewards. The learning record data set is a data set that records the reward data and execution results obtained during the reinforcement learning process, and is used for subsequent learning and optimization. The self-check cycle is the set time period for regularly evaluating and feedbacking the effect of the dispatching strategy.

[0090] According to the previously formulated dispatching strategy, for different power consumption states, specific dispatching operations are performed, such as adjusting the angle of the photovoltaic panels and controlling the charge and discharge of the energy storage, to ensure efficient power distribution.

[0091] Based on the effect of the dispatching action, the dispatching reward data is calculated. On the premise of meeting the load demand, if the power purchase cost is reduced or the backflow income is increased, a positive reward is given; otherwise, a negative reward is given. The success or failure of each dispatching action is evaluated according to the actual operation effect, and multiple dispatching reward data are calculated.

[0092] Taking the positive reward data as the positive learning objective and the negative reward data as the negative learning objective, using reinforcement learning algorithms such as Q-learning or deep reinforcement learning for reinforcement learning to optimize the dispatching strategy. By updating the strategy to strengthen the successful dispatching actions, a learning record data set is generated to record each dispatching action and its corresponding reward result.

[0093] Based on multiple real-time operation data sets, a self-check cycle is set, for example, a self-check is performed once a day or once an hour. During the self-check cycle, the learning record data set is analyzed and feedbacked to generate a learning feedback result. This feedback can include which dispatching actions have a good reward distribution and which need to be optimized, so as to provide a basis for the subsequent learning process.

[0094] Through this series of steps, the dispatching strategy is continuously adjusted and optimized to improve the operation efficiency and adaptability of the photovoltaic energy storage power station. The reinforcement learning mechanism ensures that the dispatching strategy can be self-adjusted according to the actual operation situation to better respond to the power consumption demands under different power consumption states and optimize the resource allocation.

[0095] Furthermore, in step S5 of the embodiment of the present application, when the dispatching strategy is interactively optimized according to the learning feedback result to generate a dispatching optimization strategy, it further includes:

[0096] Step S55: Based on the learning record data set, combined with the priority of the photovoltaic energy storage power consumption dispatching, power consumption analysis is performed to obtain a preset power consumption component.

[0097] Step S56: Randomly adjust the preset power consumption components according to the learning feedback results to obtain multiple power consumption adjustment amounts.

[0098] Step S57: Randomly select one from the multiple power consumption adjustment amounts as the first power consumption adjustment amount, and perform interactions according to the first power consumption adjustment amount to obtain the first granularity optimization score.

[0099] Step S58: Randomly select one from the multiple power consumption adjustment amounts as the second power consumption adjustment amount, and perform interactions according to the second power consumption adjustment amount to obtain the second granularity optimization score. The second power consumption adjustment amount is different data from the first power consumption adjustment amount.

[0100] Step S59: Determine whether the second granularity optimization score is greater than the first granularity optimization score. If so, use the second power consumption adjustment amount as the real-time optimal power consumption adjustment amount. If not, continue to compare and judge according to the probability parameter, where the probability parameter decreases as the number of iterative optimizations increases, and continue iterative optimization until the preset number of iterations is reached, and output the final real-time optimal power consumption adjustment amount to obtain the optimal power consumption adjustment amount.

[0101] Step S510: Interactively optimize the scheduling strategy according to the optimal power consumption adjustment amount to generate the scheduling optimization strategy.

[0102] Specifically, analyze the data in the learning record dataset, and combine the previously determined priority of photovoltaic and energy storage power consumption scheduling to obtain the preset power consumption components, that is, the components of the decomposed power demand, which can be the demand situations of the load for different types of electrical energy, such as the power consumption of photovoltaic electrical energy, the power consumption of grid electrical energy, the power consumption of battery electrical energy, etc. Randomly adjust these preset power consumption components according to the learning feedback results to obtain multiple power consumption adjustment amounts. For example, if the demand in a certain period is too high, randomly increase the power consumption component in that period to test the performance of the photovoltaic and energy storage power station under different loads.

[0103] Randomly select one power consumption adjustment amount from the multiple power consumption adjustment amounts as the first power consumption adjustment amount, and perform interactions according to this adjustment amount to evaluate the cost-benefit and operating status after the power consumption adjustment, and obtain the first granularity optimization score. This score reflects the preliminary effect of the first power consumption adjustment amount on the optimization of the scheduling strategy.

[0104] Randomly select a power consumption adjustment amount different from the first power consumption adjustment amount from the multiple power consumption adjustment amounts as the second power consumption adjustment amount, and perform interactions according to this adjustment amount to obtain the second granularity optimization score. This adjustment amount must be different from the first power consumption adjustment amount to ensure diversity.

[0105] Compare the second-granularity optimization score with the first-granularity optimization score to determine whether the second-granularity optimization score is greater than the first-granularity optimization score. If so, regard the second power adjustment amount as the real-time optimal power adjustment amount. Otherwise, perform continuous comparison according to the probability parameter to ensure gradual optimization. As the number of iterative optimization increases, the probability parameter gradually decreases, which means that in the early stage, a wider range of possible adjustment amounts are explored, and in the later stage, a preference is given to the relatively optimal results that have been discovered. The continuous iteration process continues until the preset number of iterations is reached, and finally the real-time optimal power adjustment amount is output. Apply the obtained optimal power adjustment amount to the scheduling strategy, and perform targeted interactive optimization on the scheduling strategy to generate a more efficient and accurate scheduling optimization strategy.

[0106] Through this series of interactive optimization steps, it can adapt to different power consumption demands, continuously self-learn and optimize, ensure that the scheduling strategy of the photovoltaic energy storage power station can efficiently and flexibly respond to the changing operating environment and demands, and significantly improve the adaptive ability and resource utilization efficiency of the scheduling process.

[0107] In summary, the intelligent scheduling method for a photovoltaic energy storage power station provided by the embodiment of the present application has the following technical effects:

[0108] Through the data acquisition unit, real-time acquisition of the target photovoltaic energy storage power station is carried out to obtain multiple real-time operation data sets, timely capture the state changes of the photovoltaic energy storage power station, and provide a basis for subsequent dynamic monitoring and scheduling decisions. Based on the multiple real-time operation data sets, dynamic monitoring of the target photovoltaic energy storage power station is carried out to obtain operation environment information, ensuring timely adjustment of the scheduling strategy under changing external conditions. Based on the multiple real-time operation data sets, power flow determination of the target photovoltaic energy storage power station is carried out to identify the current power flow situation, obtain multiple power consumption state information, so as to optimize the configuration and use of electric energy. According to the operation environment information, the multiple real-time operation data sets are associated and mapped with the multiple power consumption state information to formulate a scheduling strategy. Execute the scheduling strategy to perform reinforcement learning on the target photovoltaic energy storage power station, generate a learning feedback result, and perform interactive optimization on the scheduling strategy according to the learning feedback result to generate a scheduling optimization strategy to execute the intelligent scheduling of the target photovoltaic energy storage power station.

[0109] Overall, the embodiment of the present application integrates technical means such as real-time data acquisition, dynamic monitoring, power flow determination, association mapping, and reinforcement learning, makes full use of real-time operation data, optimizes the charge and discharge strategy, realizes the intelligent scheduling of the photovoltaic energy storage power station, improves the operation efficiency and energy management efficiency of the photovoltaic energy storage power station, significantly enhances the adaptability to different power consumption demands and operating environments, and promotes the efficient utilization and sustainable development of renewable energy.

[0110] Embodiment 2, as Figure 4 shown, the embodiment of the present application provides an intelligent scheduling platform for a photovoltaic energy storage power station, and the platform includes:

[0111] The operation data acquisition module 10 is configured to perform real-time acquisition on a target photovoltaic and energy storage power station through a data acquisition unit to obtain multiple real-time operation data sets.

[0112] The operation environment monitoring module 20 is configured to perform dynamic monitoring on the target photovoltaic and energy storage power station according to the multiple real-time operation data sets to obtain operation environment information.

[0113] The power consumption status determination module 30 is configured to perform power flow determination on the target photovoltaic and energy storage power station based on the multiple real-time operation data sets to obtain multiple power consumption status information.

[0114] The scheduling strategy formulation module 40 is configured to associate and map the multiple real-time operation data sets with the multiple power consumption status information according to the operation environment information to formulate a scheduling strategy.

[0115] The scheduling strategy optimization module 50 is configured to perform reinforcement learning on the target photovoltaic and energy storage power station by executing the scheduling strategy to generate a learning feedback result, and interactively optimize the scheduling strategy according to the learning feedback result to generate a scheduling optimization strategy for intelligent scheduling of the target photovoltaic and energy storage power station.

[0116] Furthermore, the operation data acquisition module 10 in the embodiment of the present application is further configured to perform the following steps:

[0117] Perform power consumption simulation and simulation according to multiple power consumption demand information to generate multiple power consumption simulation data; perform power consumption analysis according to the multiple power consumption simulation data to generate a power consumption simulation analysis result, score the power consumption simulation analysis result to obtain multiple power consumption score data; serialize the multiple power consumption score data in descending order to determine the photovoltaic and energy storage energy sequence; retrieve multiple power storage data of the photovoltaic and energy storage power station based on the photovoltaic and energy storage energy sequence, and sequentially determine whether the multiple power storage data of the photovoltaic and energy storage power station meet the preset power threshold to generate a photovoltaic and energy storage power consumption scheduling priority; select multiple data acquisition devices for associated configuration according to the photovoltaic and energy storage power consumption scheduling priority to construct the data acquisition unit; set the acquisition frequency based on the multiple power consumption demand information, and perform data sensing on the target photovoltaic and energy storage power station through the data acquisition unit according to the acquisition frequency to obtain multiple initial sensing data; synchronize the multiple initial sensing data according to the operation time sequence to obtain the multiple real-time operation data sets.

[0118] Furthermore, the power consumption status determination module 30 in the embodiment of the present application is further configured to perform the following steps:

[0119] Data capture is performed on the basis of the multiple real-time operation data sets according to the collection frequency to obtain photovoltaic power generation data; power flow determination conditions are set based on the photovoltaic power generation data, and power flow determination rules are formulated based on the power flow determination conditions; the multiple real-time operation data sets are parsed and integrated to construct an operation state vector set; according to the power flow determination rules, it is determined whether the operation state vector set meets the power flow determination conditions; if the operation state vector set meets the power flow determination conditions, power consumption analysis is performed on the target photovoltaic energy storage power station according to the operation state vector set to generate power consumption preference data; power consumption identification is performed according to the power consumption preference data to generate multiple power consumption tags; the multiple power consumption tags are added to the multiple power consumption state information.

[0120] Further, the scheduling strategy formulation module 40 in the embodiment of the present application is further configured to perform the following steps:

[0121] Perform multi-dimensional demand analysis on the target photovoltaic energy storage power station according to the operation environment information to determine the power station demand analysis result, where the power station demand analysis result includes multiple operation demand information; map the multiple real-time operation data sets to the operation state vector set according to the power consumption preference data, and draw a power consumption trend curve graph; perform correlation matching on the power consumption trend curve graph and the multiple power consumption tags to construct a power consumption priority list; traverse and connect the target photovoltaic energy storage power station according to the power consumption priority list to construct a power consumption topology structure; set a scheduling target according to the power consumption topology structure in combination with the multiple power consumption demand information, and formulate the scheduling strategy of the target photovoltaic energy storage power station according to the scheduling target in combination with the multiple operation demand information.

[0122] Further, the scheduling strategy formulation module 40 in the embodiment of the present application is further configured to perform the following steps:

[0123] Perform feature analysis on the power consumption trend curve graph to extract multiple power consumption features; perform power consumption evaluation according to the multiple power consumption features, and mark the power consumption trend curve graph according to the evaluation result to determine multiple power consumption extreme values, where the multiple power consumption extreme values include multiple power consumption peaks and multiple power consumption valleys; traverse the multiple power consumption tags to perform correlation matching on the multiple power consumption peaks to obtain a first correlation matching result; traverse the multiple power consumption tags to perform correlation matching on the multiple power consumption valleys to obtain a second correlation matching result; perform weight distribution according to the first correlation matching result and the second correlation matching result to generate multiple weight coefficients, and construct the power consumption priority list according to the multiple weight coefficients in combination with the power consumption trend curve graph.

[0124] Further, the scheduling strategy optimization module 50 in the embodiment of the present application is further configured to perform the following steps:

[0125] Execute the scheduling strategy for the target optical storage power station according to the multiple power consumption status information to determine multiple power consumption scheduling actions; calculate rewards based on the multiple power consumption scheduling actions to obtain multiple scheduling reward data, where the multiple scheduling reward data includes positive reward data and negative reward data; use the positive reward data as the positive learning target and the negative reward data as the negative learning target to perform reinforcement learning on the target optical storage power station to generate a learning record data set; set a self-check period based on the multiple real-time operation data sets, and perform self-check feedback on the learning record data set according to the self-check period to generate the learning feedback result.

[0126] Further, the scheduling strategy optimization module 50 in the embodiment of the present application is further configured to perform the following steps:

[0127] Perform power consumption analysis based on the learning record data set in combination with the priority of optical storage power consumption scheduling to obtain a preset power consumption component; randomly adjust the preset power consumption component according to the learning feedback result to obtain multiple power consumption adjustment amounts; randomly select from the multiple power consumption adjustment amounts as the first power consumption adjustment amount, and perform interaction according to the first power consumption adjustment amount to obtain a first granularity optimization score; randomly select from the multiple power consumption adjustment amounts as the second power consumption adjustment amount, and perform interaction according to the second power consumption adjustment amount to obtain a second granularity optimization score, where the second power consumption adjustment amount is different from the first power consumption adjustment amount; determine whether the second granularity optimization score is greater than the first granularity optimization score. If so, use the second power consumption adjustment amount as the real-time optimal power consumption adjustment amount. If not, perform continuous comparison and judgment according to the probability parameter, where the probability parameter decreases as the number of iterative optimizations increases, and continue iterative optimization until the preset number of iterations is reached, and output the final real-time optimal power consumption adjustment amount to obtain the optimal power consumption adjustment amount; perform interaction optimization on the scheduling strategy according to the optimal power consumption adjustment amount to generate the scheduling optimization strategy.

[0128] Through the foregoing detailed description of an intelligent scheduling method for an optical storage power station in this specification, those skilled in the art can clearly know an intelligent scheduling platform for an optical storage power station in this embodiment. For the platform disclosed in Embodiment 2, since it corresponds to the method disclosed in Embodiment 1, it has corresponding functional modules and beneficial effects. For the relevant parts, refer to the description in the method part.

[0129] 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 readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Thus, the present application is not intended to 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 of a photovoltaic power station, characterized in that: The method comprises: The target photovoltaic power station is collected in real time through the data acquisition unit to obtain multiple real-time operation data sets; Dynamically monitor the target photovoltaic power station according to the multiple real-time operation data sets to obtain operation environment information; Based on the multiple real-time operation data sets, the target photovoltaic power station is judged for power flow to obtain multiple power consumption status information; According to the operating environment information, the multiple real-time operating data sets are associated and mapped with the multiple power usage status information to formulate a scheduling strategy; Execute the scheduling strategy to perform reinforcement learning on the target photovoltaic power station, generate learning feedback results, interactively optimize the scheduling strategy according to the learning feedback results, and generate a scheduling optimization strategy to execute intelligent scheduling of the target photovoltaic power station; The target photovoltaic power station is collected in real time by a data collection unit to obtain multiple real-time operation data sets, and the method includes: Performing power consumption simulation according to multiple power consumption demand information to generate multiple power consumption simulation data; Performing power consumption analysis according to multiple power consumption simulation data, generating power consumption simulation analysis results, and scoring the power consumption simulation analysis results to obtain multiple power consumption scoring data; Serialize multiple electricity consumption score data in descending order to determine the photovoltaic energy storage sequence; Based on the photovoltaic energy sequence, multiple power storage data of the photovoltaic power station are retrieved, and the multiple power storage data of the photovoltaic power station are judged in turn whether they meet the preset power threshold, and the photovoltaic power dispatch priority is generated; According to the priority of the photovoltaic power storage and electricity consumption scheduling, multiple data acquisition devices are selected for association configuration to construct the data acquisition unit; Setting a collection frequency based on the plurality of electricity demand information, and performing data sensing on a target photovoltaic power station through the data collection unit according to the collection frequency to obtain a plurality of initial sensing data; The multiple initial sensor data are synchronized according to the operating sequence to obtain the multiple real-time operating data sets.

2. The intelligent dispatching method for a photovoltaic power station according to claim 1, characterized in that: Based on the multiple real-time operation data sets, the target photovoltaic power station is judged for power flow, and multiple power consumption status information is obtained, the method comprising: Capturing data according to the acquisition frequency based on the multiple real-time operation data sets to obtain photovoltaic power generation data; Setting a power flow determination condition based on the photovoltaic power generation data, and formulating a power flow determination rule based on the power flow determination condition; Analyzing and integrating the multiple real-time operation data sets to construct an operation status vector set; According to the power flow determination rule, determining whether the operating state vector set meets the power flow determination condition; If the operation state vector set meets the power flow determination condition, then the target photovoltaic power station is analyzed for power consumption according to the operation state vector set to generate power consumption preference data; Identify electricity usage according to the electricity usage preference data to generate multiple electricity usage tags; The plurality of power usage tags are added to the plurality of power usage status information.

3. The intelligent dispatching method of a photovoltaic power station according to claim 2, characterized in that: According to the operating environment information, the multiple real-time operating data sets are associated and mapped with the multiple power usage status information to formulate a scheduling strategy, the method comprising: Performing a multi-dimensional demand analysis on the target photovoltaic power station according to the operating environment information to determine a power station demand analysis result, wherein the power station demand analysis result includes multiple operating demand information; According to the power consumption preference data, the multiple real-time operation data sets are mapped to the operation status vector set, and a power consumption trend curve is drawn; Based on the electricity consumption trend curve graph and the plurality of electricity consumption tags, an electricity consumption priority list is constructed; Traversing and connecting the target photovoltaic power stations according to the power consumption priority list to construct a power consumption topology structure; The scheduling target is set according to the power consumption topology structure combined with the multiple power consumption demand information, and the scheduling strategy of the target photovoltaic power station is formulated according to the scheduling target combined with the multiple operation demand information.

4. The intelligent dispatching method for a photovoltaic power station according to claim 3, characterized in that: Based on the electricity consumption trend curve graph and the plurality of electricity consumption tags, an electricity consumption priority list is constructed, and the method includes: Perform feature analysis based on the power consumption trend curve graph to extract multiple power consumption features; Performing an electricity consumption evaluation according to the plurality of electricity consumption characteristics, marking the electricity consumption trend curve according to the evaluation result, and determining a plurality of electricity consumption extreme values, wherein the plurality of electricity consumption extreme values ​​include a plurality of electricity consumption peak values ​​and a plurality of electricity consumption valley values; Traversing the multiple power usage tags to perform correlation matching on the multiple power usage peaks to obtain a first correlation matching result; Traversing the multiple power usage tags to perform association matching on the multiple power usage valley values ​​to obtain a second association matching result; Weight allocation is performed according to the first association matching result and the second association matching result to generate a plurality of weight coefficients, and the power consumption priority list is constructed according to the plurality of weight coefficients combined with the power consumption trend curve.

5. The intelligent dispatching method for a photovoltaic power station according to claim 1, characterized in that: The scheduling strategy is executed to perform reinforcement learning on the target photovoltaic power station and generate learning feedback results, and the method includes: Executing the scheduling strategy on the target photovoltaic power station according to the plurality of power consumption status information, and determining a plurality of power consumption scheduling actions; Perform reward calculation according to the multiple electricity scheduling actions to obtain multiple scheduling reward data, wherein the multiple scheduling reward data include positive reward data and negative reward data; Using the positive reward data as a positive learning target and using the negative reward data as a negative learning target to perform reinforcement learning on the target photovoltaic power station, and generating a learning record data set; A self-check cycle is set based on the multiple real-time operation data sets, and self-check feedback is performed on the learning record data set according to the self-check cycle to generate the learning feedback result.

6. The intelligent dispatching method for a photovoltaic power station according to claim 5, characterized in that: Interactively optimizing the scheduling strategy according to the learning feedback result to generate a scheduling optimization strategy, the method comprising: Based on the learning record data set and the priority of photovoltaic power storage scheduling, power consumption analysis is performed to obtain a preset power consumption component; Randomly adjusting the preset power consumption component according to the learning feedback result to obtain multiple power consumption adjustment amounts; Randomly selecting a first power adjustment amount based on the multiple power adjustment amounts, and interacting according to the first power adjustment amount to obtain a first granularity optimization score; Randomly selecting a second power consumption adjustment amount based on the multiple power consumption adjustment amounts, interacting according to the second power consumption adjustment amount to obtain a second granularity optimization score, wherein the second power consumption adjustment amount and the first power consumption adjustment amount are different data; Determine whether the second granularity optimization score is greater than the first granularity optimization score. If so, use the second power adjustment amount as the real-time optimal power adjustment amount. If not, perform continuous comparison and judgment according to the probability parameter, wherein the probability parameter decreases as the number of iterative optimization increases. Continue iterative optimization until a preset number of iterations is reached, output the final real-time optimal power adjustment amount, and obtain the optimal power adjustment amount. The scheduling strategy is interactively optimized according to the optimal power consumption adjustment amount to generate the scheduling optimization strategy.

7. An intelligent dispatching platform for photovoltaic power plants, characterized in that: The platform is used to execute the intelligent scheduling method of a photovoltaic power station according to any one of claims 1 to 6, and the platform includes: An operation data acquisition module, which is used to collect data from a target photovoltaic power station in real time through a data acquisition unit to obtain multiple real-time operation data sets; An operating environment monitoring module, the operating environment monitoring module is used to dynamically monitor the target photovoltaic power station according to the multiple real-time operating data sets to obtain operating environment information; A power consumption status determination module, the power consumption status determination module is used to determine the power flow of the target photovoltaic power station based on the multiple real-time operation data sets to obtain multiple power consumption status information; A scheduling strategy formulation module, the scheduling strategy formulation module is used to associate and map the multiple real-time operation data sets with the multiple power consumption status information according to the operation environment information, and formulate a scheduling strategy; A scheduling strategy optimization module, wherein the scheduling strategy optimization module is used to execute the scheduling strategy to perform reinforcement learning on the target photovoltaic power station, generate learning feedback results, interactively optimize the scheduling strategy according to the learning feedback results, and generate a scheduling optimization strategy to execute intelligent scheduling of the target photovoltaic power station.

Images