A storage management system based on solar photovoltaic power generation

Abstract

The present invention discloses an energy storage management system based on solar photovoltaic power generation, which relates to the technical field of energy dispatching management and enhances the adaptability to environmental changes in the process of energy allocation. The present invention compares the historical environmental change curve in the historical energy flow record pre-stored in each energy allocation cycle with the corresponding ideal environmental data straight line, marks the deviation environmental data segment on the historical environmental change curve according to the comparison result, selects the historical environmental change curve with one or more deviation environmental data segments in turn, and then generates a multi-segment linear regression equation, sets a number of energy management time periods according to the energy allocation cycle, establishes an energy allocation decision network according to the location distribution of energy facilities, inputs the real-time data set of each energy facility into the energy allocation decision network, and retrieves the corresponding multi-segment linear regression equation, and then sets and implements energy allocation decisions for each energy facility.

Description

Technical Field

[0001] The present invention relates to the technical field of energy dispatching management, and in particular to an energy storage management system based on solar photovoltaic power generation. Background Art

[0002] In the field of energy management, especially in complex systems involving multiple energy facilities, effective analysis and management of energy flow is crucial to improving energy efficiency and stability. Existing energy management systems often focus on real-time monitoring and basic data recording, but are insufficient in in-depth analysis of the mechanism by which energy flow is affected by the environment and making optimization decisions based on this. At the same time, there is a lack of detailed analysis of the relationship between environmental changes and energy production and transmission in historical energy flow records, which limits the system's adaptability and optimization capabilities in the face of environmental changes.

[0003] In addition, existing systems usually do not make full use of historical data to predict and adjust energy allocation strategies. In particular, the performance of energy facilities can vary significantly under different environmental conditions, and these differences directly affect energy production and transmission efficiency. Therefore, a storage energy management system based on solar photovoltaic power generation is provided. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide an energy storage management system based on solar photovoltaic power generation.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] A solar photovoltaic power generation-based energy storage management system includes a cloud computing platform, wherein the cloud computing platform is communicatively connected with an energy flow impact analysis module, a real-time operation data acquisition module, and an energy storage management decision module;

[0007] The energy flow impact analysis module is used to set the energy allocation cycle, and obtain the ideal environmental data lines of each energy facility under the ideal environmental state, compare the historical environmental change curves in the historical energy flow records pre-stored in each energy allocation cycle with the corresponding ideal environmental data lines, and mark the deviation environmental data segments on the historical environmental change curves according to the comparison results;

[0008] Selecting historical environmental change curves with one or more deviation environmental data segments in turn, and then generating multi-segment linear regression equations between different types of deviation environmental data of each energy facility and the amount of energy produced, and multi-segment linear regression equations between various types of environmental data between each energy facility and the amount of energy transmission;

[0009] The real-time operation data acquisition module is used to obtain real-time data sets of various energy facilities;

[0010] The energy storage management decision module is used to set a number of energy management time periods according to the energy allocation cycle, and establish an energy allocation decision network according to the location distribution of energy facilities, input the real-time data set of each energy facility into the energy allocation decision network, and retrieve the corresponding multi-segment linear regression equation, and then set and implement energy allocation decisions for each energy facility.

[0011] Furthermore, the historical energy circulation records also include historical energy transmission records and historical environmental data records of multiple energy facilities;

[0012] The types of energy facilities include photovoltaic power stations, energy storage stations and electricity consumption areas;

[0013] The historical energy transmission records include energy interaction records between various energy facility areas;

[0014] The historical environmental data records include a variety of historical environmental change curves of various energy facilities within the energy allocation cycle.

[0015] Furthermore, the process of labeling the deviation environment data segment includes:

[0016] According to the historical energy transmission records, the historical energy production curves of each photovoltaic power station in the corresponding energy allocation cycle are obtained, and a multi-dimensional coordinate system is established. According to the historical environmental data records, the historical environmental change curves and historical energy production curves of the photovoltaic power station in each energy allocation cycle are input into each two-dimensional plane in the multi-dimensional coordinate system respectively;

[0017] Obtain the ideal energy production line of each photovoltaic power station under the ideal environmental conditions, and input the ideal energy production line and various ideal environmental data lines into the corresponding two-dimensional plane in the multi-dimensional coordinate system;

[0018] According to the duration of the energy allocation cycle, several energy management periods are set, and according to the distribution of the energy management periods, corresponding coordinate intervals are divided on the coordinate axis corresponding to time in the multidimensional coordinate system;

[0019] Starting from the first energy management period, the multidimensional coordinate system generated by the same photovoltaic power station according to the historical energy flow records is integrated to set an ideal deviation threshold for each environmental data. If the difference between the historical environmental change curve and the corresponding ideal environmental data straight line is less than or equal to the ideal deviation threshold during the energy management period, the historical environmental change curve segment during the energy management period is regarded as an ideal environmental data segment, otherwise it is marked as a deviation environmental data segment.

[0020] Furthermore, the process of generating the multi-segment linear regression equation between different types of deviation environmental data and production energy includes:

[0021] First, from each multidimensional coordinate system corresponding to the same photovoltaic power generation point, a multidimensional coordinate system where the historical environmental change curve has only one and the same type of deviation environmental data fragment is located is selected, and then the deviation environmental data fragment and the corresponding historical energy production curve fragment in the selected multidimensional coordinate system are mapped to the same multidimensional coordinate system;

[0022] The deviation environment data segments and historical energy production curve segments from different multi-dimensional coordinate systems are spliced ​​respectively, and then a multi-segment linear regression equation between the corresponding types of deviation environment data and the production energy amount is obtained;

[0023] Set an energy production anomaly threshold, map the historical energy production curve and the ideal energy production line corresponding to the multi-segment linear regression equation of a single deviation environment data segment into the same two-dimensional coordinate system, and then remove the corresponding numerical interval in the multi-segment linear regression equation according to the numerical interval where the difference between the historical energy production curve and the ideal energy production line is greater than or equal to the energy production anomaly threshold, and retain the remaining numerical intervals;

[0024] Then, a multidimensional coordinate system is selected in which the historical environmental change curves containing only two, three or even all types of deviation environmental data segments exist, and a multi-segment linear regression equation is generated between the deviation environmental data and the production energy amount.

[0025] Furthermore, the process of generating a multi-segment linear regression equation between various types of environmental data and energy transmission between various energy facilities includes:

[0026] The process of generating a multi-segment linear regression equation between each type of environmental data and the amount of energy produced for each photovoltaic power station is adopted. The multi-segment linear regression equation between each type of environmental data and the energy usage in the power consumption area is obtained according to the historical energy flow records. The multi-segment linear regression equation between each type of environmental data and the energy transmission amount between any two energy facilities in the energy facility area is also obtained, and the corresponding energy facility numbers are marked.

[0027] Furthermore, the process of acquiring real-time data sets of various energy facilities includes;

[0028] According to the start and end time of the energy allocation cycle of each energy facility, a data collection cycle equal to the energy management period is set for each energy facility, and multiple sensors are installed at each energy facility;

[0029] Whenever a data collection cycle ends, all sensors of each energy facility send the real-time data collected in the current data collection cycle to the real-time operation data collection module, and then the real-time operation data collection module integrates the real-time data corresponding to the same energy facility into a real-time data set and marks the number of the corresponding energy facility.

[0030] Furthermore, the process of establishing the energy allocation decision network includes:

[0031] Set up a number of energy allocation nodes according to the total number of energy facilities in the energy facility area, and establish an energy allocation decision network;

[0032] According to the different types of historical environmental data associated with photovoltaic power stations, energy storage stations and power consumption areas in historical energy flow records, multiple environmental factor nodes are set for each energy facility;

[0033] According to the energy management period set according to the energy allocation cycle, during any energy allocation cycle, whenever the energy storage management decision module receives the real-time data set of each energy facility, it inputs each real-time environmental data in the real-time data set into the corresponding environmental factor node;

[0034] Then, it is determined whether the difference between each real-time environmental data and the corresponding ideal environmental data straight line is less than or equal to the ideal deviation threshold. If the difference is less than or equal to the ideal deviation threshold, the corresponding environmental factor node is ignored.

[0035] If the judgment difference is greater than the ideal deviation threshold, the corresponding environmental factor node is recorded as an abnormal environmental factor node.

[0036] Furthermore, the generation process of the energy allocation decision includes:

[0037] For the energy allocation node corresponding to the photovoltaic power station, the corresponding multi-segment linear regression equation is retrieved according to the type of environmental data corresponding to the abnormal environmental factor node in the current energy management period and the energy allocation node number, and the real-time environmental data in the abnormal environmental factor node is input into the multi-segment linear regression equation to obtain the estimated energy production in the next energy management period;

[0038] At the same time, for the energy allocation nodes corresponding to the power consumption areas, the estimated energy usage in the next energy management period is obtained;

[0039] The energy allocation node corresponding to each power consumption area is the first demand node, the energy allocation node corresponding to the energy storage station is the second demand node and the second distribution node, and the energy allocation node corresponding to the photovoltaic power station is the first distribution node;

[0040] Then, according to the abnormal environmental factor nodes of each demand node and distribution node, a multi-segment linear regression equation with the numbers of the demand node and the distribution node is retrieved, and the real-time environmental data in the abnormal environmental factor nodes of the demand node and the distribution node are input into the multi-segment linear regression equation, and then the slope of the point obtained by the multi-segment linear regression equation is recorded as the energy transmission efficiency between the corresponding demand node and the distribution node;

[0041] According to the numbering sequence, the estimated energy production of the first distribution node with the highest energy transmission efficiency of each first demand node is judged in turn to see whether it is greater than or equal to the estimated energy usage. Based on the judgment result and the optimization algorithm, the energy allocation requests of each first demand node and the first distribution node are met under the condition of minimum global energy loss, and the energy allocation decision between the corresponding demand nodes and the distribution nodes is generated and implemented.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] 1. The present invention uses the energy allocation cycle and compares the historical environmental change curve in the historical energy flow record with the ideal environmental data straight line to identify the deviation environmental data segment, and then generates a multi-segment linear regression equation to quantify the relationship between different types of deviation environmental data and the production energy and energy transmission amount, laying a data foundation for subsequent judgment of the status of each energy facility and energy allocation decision.

[0044] 2. The present invention dynamically generates an energy allocation strategy by calling the corresponding multi-segment linear regression equation according to the current environmental conditions, real-time data and the energy allocation decision network, thereby enhancing the adaptability to environmental changes in the energy allocation process and achieving more sustainable and reliable energy management. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0046] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation mode, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0047] like Figure 1 As shown, an energy storage management system based on solar photovoltaic power generation includes a cloud computing platform, and the cloud computing platform is communicatively connected with an energy flow impact analysis module, a real-time operation data acquisition module, and an energy storage management decision module;

[0048] The energy flow impact analysis module is used to set the energy allocation cycle, and obtain the ideal environmental data lines of each energy facility under the ideal environmental state, compare the historical environmental change curves in the historical energy flow records pre-stored in each energy allocation cycle with the corresponding ideal environmental data lines, and mark the deviation environmental data segments on the historical environmental change curves according to the comparison results;

[0049] Selecting historical environmental change curves with one or more deviation environmental data segments in turn, and then generating multi-segment linear regression equations between different types of deviation environmental data of each energy facility and the amount of energy produced, and multi-segment linear regression equations between various types of environmental data between each energy facility and the amount of energy transmission;

[0050] The real-time operation data acquisition module is used to obtain real-time data sets of various energy facilities;

[0051] The energy storage management decision module is used to set a number of energy management time periods according to the energy allocation cycle, and establish an energy allocation decision network according to the location distribution of energy facilities, input the real-time data set of each energy facility into the energy allocation decision network, and retrieve the corresponding multi-segment linear regression equation, and then set and implement energy allocation decisions for each energy facility.

[0052] Further, the working principle of the present invention is described below by way of examples:

[0053] Each energy facility is provided with the same energy allocation cycle, the time length corresponding to the historical energy flow records pre-stored in the energy flow impact analysis module is equal to the energy allocation cycle length, and the historical energy flow records simultaneously include historical energy transmission records and historical environmental data records of multiple energy facilities;

[0054] The types of energy facilities include photovoltaic power stations, energy storage stations and power consumption areas, wherein the photovoltaic power stations, energy storage stations and power consumption areas in the energy facility area are scattered, and then the energy flow impact analysis module sets numbers a1, a2, ..., a for each photovoltaic power station, energy storage station and power consumption area. n , b1, b2, ..., b m , c1, c2, ..., c k , where n, m, and k are positive integers greater than 0 and represent the total number of photovoltaic power stations, energy storage stations, and power consumption areas, respectively;

[0055] The historical energy transmission records include energy interaction records between various energy facility areas, such as the energy dispatch change curve between the photovoltaic power station numbered a1, the energy reserve station numbered b2 and the power consumption area numbered c2 during the energy dispatch cycle;

[0056] The historical environmental data records include various historical environmental change curves of various energy facilities within the energy allocation cycle, such as historical temperature change curves, historical light curves, etc.;

[0057] For any photovoltaic power station, the energy dispatch change curve between it and other energy facilities is recorded according to the historical energy transmission, and then its historical energy production curve under the corresponding energy dispatch cycle is obtained;

[0058] Establish a multidimensional coordinate system, and input the historical environmental change curves and historical energy production curves of the photovoltaic power station in each energy allocation cycle into each two-dimensional plane in the multidimensional coordinate system according to the historical environmental data records;

[0059] Obtain the single maximum energy production rate of all power generation devices in each photovoltaic power station under ideal environmental conditions from the Internet, and obtain the maximum energy production rate of the corresponding photovoltaic power station under ideal environmental conditions by accumulating the single maximum energy production rate of all power generation devices under ideal environmental conditions;

[0060] It should be noted that the ideal environmental state represents the range of changes in various environmental data when the power generation device reaches the maximum energy production rate of a single unit;

[0061] Generate an ideal energy production line under an energy allocation cycle according to the maximum energy production rate under ideal conditions, and input the ideal energy production line and various ideal environmental data lines into the corresponding two-dimensional plane in the multi-dimensional coordinate system;

[0062] It should be noted that the ideal energy production line is a straight line parallel to the time axis in the multidimensional coordinate system;

[0063] According to the duration of the energy allocation cycle, i energy management periods are set. The duration of the energy management period is generally between 10 and 30 seconds, and i is a natural number greater than 100;

[0064] According to the distribution of energy management periods, the corresponding coordinate intervals are divided on the coordinate axis corresponding to the time in the multidimensional coordinate system. Starting from the first energy management period, the multidimensional coordinate system generated by the same photovoltaic power station according to the historical energy flow record is integrated to set an ideal deviation threshold for each environmental data. If the difference between the historical environmental change curve and the corresponding ideal environmental data straight line is less than or equal to the ideal deviation threshold during the energy management period, the historical environmental change curve segment during the energy management period is regarded as the ideal environmental data segment, otherwise it is marked as a deviation environmental data segment;

[0065] First, from each multidimensional coordinate system corresponding to the same photovoltaic power generation point, a multidimensional coordinate system where the historical environmental change curve has only one and the same type of deviation environmental data fragment is located is selected, and then the deviation environmental data fragment and the corresponding historical energy production curve fragment in the selected multidimensional coordinate system are mapped to the same multidimensional coordinate system;

[0066] The deviation environment data segments and historical energy production curve segments from different multi-dimensional coordinate systems are spliced ​​respectively, and then a multi-segment linear regression equation between the corresponding types of deviation environment data and the production energy amount is obtained;

[0067] Set an energy production anomaly threshold, map the historical energy production curve and the ideal energy production line corresponding to the multi-segment linear regression equation of a single deviation environment data segment into the same two-dimensional coordinate system, and then remove the corresponding numerical interval in the multi-segment linear regression equation according to the numerical interval where the difference between the historical energy production curve and the ideal energy production line is greater than or equal to the energy production anomaly threshold, and retain the remaining numerical intervals;

[0068] Then select the multidimensional coordinate system where the historical environmental change curves with only two, three, or even all types of deviation environmental data segments are located, repeat the operation of generating and partially eliminating the multi-segment linear regression equations between only one type of deviation environmental data segment and the historical energy production curve segment, and generate the multi-segment linear regression equations between the deviation environmental data corresponding to two, three, or even all types of environmental data and the production energy amount.

[0069] Further, a process of generating a multi-segment linear regression equation between each type of environmental data and the amount of energy produced for each photovoltaic power station is adopted, and a multi-segment linear regression equation between each type of environmental data and the amount of energy used in the power consumption area is obtained based on the historical energy flow records, and a multi-segment linear regression equation between each type of environmental data and the amount of energy transferred between any two energy facilities in the energy facility area is obtained;

[0070] Then, the energy flow impact analysis module labels each multi-segment linear regression equation with the corresponding energy facility number, and then sends all the multi-segment linear regression equations to the energy storage management decision module.

[0071] Furthermore, the real-time operation data acquisition module sets a data acquisition period of equal duration to the energy management period for each energy facility according to the start and end time of the energy allocation period of each energy facility, and installs a variety of sensors in each energy facility, wherein the types of sensors include temperature sensors, humidity sensors, power sensors, etc.;

[0072] Whenever a data collection cycle ends, all sensors of each energy facility send the real-time data collected in the current data collection cycle to the real-time operation data collection module. The real-time operation data collection module then integrates the real-time data corresponding to the same energy facility into a real-time data set, marks the number of the corresponding energy facility, and then sends the real-time data set of all energy facilities to the energy storage management decision module.

[0073] Furthermore, the energy storage management decision module sets m+n+k energy allocation nodes according to the total number of energy facilities in the energy facility area, and establishes an energy allocation decision network;

[0074] According to the spatial location distribution of each energy facility in the energy facility area, each energy allocation node is mapped to the energy allocation decision network, and a corresponding energy facility number is set for each energy allocation node;

[0075] According to the different types of historical environmental data associated with photovoltaic power stations, energy storage stations and power consumption areas in historical energy flow records, multiple environmental factor nodes are set for each energy facility, and the multi-segment linear regression equations associated with each energy facility are input into the corresponding energy allocation node;

[0076] It should be noted that, for the energy dispatching nodes corresponding to the energy storage stations, the energy storage management decision module directly obtains the real-time energy storage capacity and real-time free storage capacity of each energy storage station, and marks the real-time energy storage capacity and real-time free storage capacity on the energy dispatching nodes corresponding to the energy storage stations;

[0077] According to the energy management period set according to the energy allocation cycle, during any energy allocation cycle, whenever the energy storage management decision module receives the real-time data set of each energy facility, it inputs each real-time environmental data in the real-time data set into the corresponding environmental factor node;

[0078] Then, it is determined whether the difference between each real-time environmental data and the corresponding ideal environmental data straight line is less than or equal to the ideal deviation threshold. If the difference is less than or equal to the ideal deviation threshold, the corresponding environmental factor node is ignored.

[0079] If the judgment difference is greater than the ideal deviation threshold, the corresponding environmental factor node is recorded as an abnormal environmental factor node.

[0080] Furthermore, for the energy allocation node corresponding to the photovoltaic power station, the corresponding multi-segment linear regression equation is retrieved according to the type of environmental data corresponding to the abnormal environmental factor node in the current energy management period and the energy allocation node number, and the real-time environmental data in the abnormal environmental factor node is input into the multi-segment linear regression equation to obtain the estimated energy production in the next energy management period;

[0081] At the same time, for the energy allocation nodes corresponding to the power consumption areas, the estimated energy usage in the next energy management period is obtained, with the energy allocation nodes corresponding to each power consumption area as the first demand node, the energy allocation nodes corresponding to the energy storage station as the second demand node and the second distribution node, and the energy allocation node corresponding to the photovoltaic power station as the first distribution node;

[0082] It should be noted that the demand priority of the first demand node is greater than that of the second demand node, and the delivery priority of the first delivery node is greater than that of the second delivery node;

[0083] Then, according to the abnormal environmental factor nodes of each demand node and distribution node, a multi-segment linear regression equation with the numbers of the demand node and the distribution node is retrieved, and the real-time environmental data in the abnormal environmental factor nodes of the demand node and the distribution node are input into the multi-segment linear regression equation, and then the slope of the point obtained by the multi-segment linear regression equation is recorded as the energy transmission efficiency between the corresponding demand node and the distribution node;

[0084] According to the numbering sequence, the estimated energy production of the first distribution node with the highest energy transmission efficiency of each first demand node is judged in turn to see whether it is greater than or equal to the estimated energy usage. Based on the judgment result and the optimization algorithm, the energy allocation requests of each first demand node and the first distribution node are met under the condition of minimum global energy loss, and the energy allocation decision between the corresponding demand nodes and the distribution nodes is generated and implemented.

[0085] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A solar photovoltaic power generation-based energy storage management system, including a cloud computing platform, characterized in that: The cloud computing platform is communicatively connected to an energy flow impact analysis module, a real-time operation data acquisition module, and an energy storage management decision module; The energy flow impact analysis module is used to set the energy allocation cycle, and obtain the ideal environmental data lines of each energy facility under the ideal environmental state, compare the historical environmental change curves in the historical energy flow records pre-stored in each energy allocation cycle with the corresponding ideal environmental data lines, and mark the deviation environmental data segments on the historical environmental change curves according to the comparison results; Selecting historical environmental change curves with one or more deviation environmental data segments in turn, and then generating multi-segment linear regression equations between different types of deviation environmental data of each energy facility and the amount of energy produced, and multi-segment linear regression equations between various types of environmental data between each energy facility and the amount of energy transmission; The process of generating the multi-segment linear regression equation between different types of deviation environmental data and production energy includes: First, from each multidimensional coordinate system corresponding to the same photovoltaic power generation point, a multidimensional coordinate system where the historical environmental change curve has only one and the same type of deviation environmental data fragment is located is selected, and then the deviation environmental data fragment and the corresponding historical energy production curve fragment in the selected multidimensional coordinate system are mapped to the same multidimensional coordinate system; The deviation environment data segments and historical energy production curve segments from different multi-dimensional coordinate systems are spliced ​​respectively, and then a multi-segment linear regression equation between the corresponding types of deviation environment data and the production energy amount is obtained; Set an energy production anomaly threshold, map the historical energy production curve and the ideal energy production line corresponding to the multi-segment linear regression equation of a single deviation environment data segment into the same two-dimensional coordinate system, and then remove the corresponding numerical interval in the multi-segment linear regression equation according to the numerical interval where the difference between the historical energy production curve and the ideal energy production line is greater than or equal to the energy production anomaly threshold, and retain the remaining numerical intervals; Then, a multidimensional coordinate system is selected where the historical environmental change curves of only two, three or even all types of deviation environmental data segments exist, and a multi-segment linear regression equation between the deviation environmental data and the production energy is generated; The process of generating the multi-segment linear regression equation between various types of environmental data and energy transmission between various energy facilities includes: The process of generating a multi-segment linear regression equation between various types of environmental data and the amount of energy produced of each photovoltaic power station is adopted, and the multi-segment linear regression equation between various types of environmental data and the amount of energy used in the power consumption area is obtained according to the historical energy flow records, and the multi-segment linear regression equation between various types of environmental data and the amount of energy transmitted between any two energy facilities in the energy facility area is obtained, and the corresponding energy facility numbers are marked; The real-time operation data acquisition module is used to obtain real-time data sets of various energy facilities; The energy storage management decision module is used to set a number of energy management time periods according to the energy allocation cycle, and establish an energy allocation decision network according to the location distribution of energy facilities, input the real-time data set of each energy facility into the energy allocation decision network, and retrieve the corresponding multi-segment linear regression equation, and then set and implement energy allocation decisions for each energy facility; The process of establishing the energy allocation decision network includes: Set up a number of energy allocation nodes according to the total number of energy facilities in the energy facility area, and establish an energy allocation decision network; According to the different types of historical environmental data associated with photovoltaic power stations, energy storage stations and power consumption areas in historical energy flow records, multiple environmental factor nodes are set for each energy facility; According to the energy management period set according to the energy allocation cycle, in any energy allocation cycle, whenever the energy storage management decision module receives the real-time data set of each energy facility, each real-time environmental data in the real-time data set is input into the corresponding environmental factor node, and then it is determined whether the difference between each real-time environmental data and the corresponding ideal environmental data straight line is less than or equal to the ideal deviation threshold, and the corresponding environmental factor node is recorded as an abnormal environmental factor node according to the judgment result; For the energy allocation node corresponding to the photovoltaic power station, the corresponding multi-segment linear regression equation is retrieved according to the type of environmental data corresponding to the abnormal environmental factor node in the current energy management period and the energy allocation node number, and the real-time environmental data in the abnormal environmental factor node is input into the multi-segment linear regression equation to obtain the estimated energy production in the next energy management period; At the same time, for the energy allocation nodes corresponding to the power consumption areas, the estimated energy usage in the next energy management period is obtained; The energy allocation node corresponding to each power consumption area is the first demand node, the energy allocation node corresponding to the energy storage station is the second demand node and the second distribution node, and the energy allocation node corresponding to the photovoltaic power station is the first distribution node; Then, according to the abnormal environmental factor nodes of each demand node and distribution node, a multi-segment linear regression equation with the numbers of the demand node and the distribution node is retrieved, and the real-time environmental data in the abnormal environmental factor nodes of the demand node and the distribution node are input into the multi-segment linear regression equation, and then the slope of the point obtained by the multi-segment linear regression equation is recorded as the energy transmission efficiency between the corresponding demand node and the distribution node; According to the numbering sequence, the estimated energy production of the first distribution node with the highest energy transmission efficiency of each first demand node is judged in turn to see whether it is greater than or equal to the estimated energy usage. Based on the judgment result and the optimization algorithm, the energy allocation requests of each first demand node and the first distribution node are met under the condition of minimum global energy loss, and the energy allocation decision between the corresponding demand nodes and the distribution nodes is generated and implemented.

2. The energy storage management system based on solar photovoltaic power generation according to claim 1, characterized in that: The historical energy flow records also include historical energy transmission records and historical environmental data records of multiple energy facilities; The types of energy facilities include photovoltaic power stations, energy storage stations and power consumption areas, and each energy facility is numbered; The historical energy transmission records include energy interaction records between various energy facility areas; The historical environmental data records include a variety of historical environmental change curves of various energy facilities within the energy allocation cycle.

3. The energy storage management system based on solar photovoltaic power generation according to claim 2 is characterized in that: The process of labeling the deviation environment data segment includes: According to the historical energy transmission records, the historical energy production curves of each photovoltaic power station in the corresponding energy allocation cycle are obtained, a multi-dimensional coordinate system is established, and the historical environmental change curves and historical energy production curves of the photovoltaic power station in each energy allocation cycle are input into the multi-dimensional coordinate system respectively; Obtain the ideal energy production line of each photovoltaic power station under the ideal environmental conditions, and input the ideal energy production line and various ideal environmental data lines into the multidimensional coordinate system; Several energy management periods are set according to the length of the energy allocation cycle. Starting from the first energy management period, an ideal deviation threshold is set for each environmental data. If, within the energy management period, the difference between the historical environmental change curve and the corresponding ideal environmental data straight line is less than or equal to the ideal deviation threshold, the historical environmental change curve segment within the energy management period is regarded as an ideal environmental data segment, otherwise it is marked as a deviation environmental data segment.

4. The energy storage management system based on solar photovoltaic power generation according to claim 1, characterized in that: The process of acquiring real-time data sets of various energy facilities includes; A data collection cycle of equal length to the energy management period is set for each energy facility. At the end of each data collection cycle, the real-time data of each energy facility is integrated into a real-time data set and marked with the number of the corresponding energy facility.

Images