Source network load storage intelligent analysis and management method and system based on big data

Abstract

The invention provides a source network load storage intelligent analysis and management method and system based on big data, and the method comprises the following steps: S1, collecting and monitoring the multi-source heterogeneous data of a source network load storage system in real time, carrying out the initial data aggregation, and obtaining the total power generation capability; s2, adopting recursive calculation to dynamically update the photovoltaic system, the energy storage electric quantity and the power grid load; and S3, updating the state of the source network load storage system by using the recursive relationship, performing dynamic weight distribution on the variable quantity of each piece of multi-source heterogeneous data, updating the overall state of the source network load storage system, and performing real-time adjustment on the output of the source network load storage system based on a feedback control mechanism. According to the method, key indexes such as the photovoltaic system, the energy storage equipment and the power grid load are dynamically adjusted according to the data acquired in real time, and a resource scheduling strategy can be timely and accurately adjusted through a recursive calculation and feedback mechanism, so that the stability of the power grid and the continuity of power supply are guaranteed.

Description

Technical Field

[0001] This invention belongs to the field of big data processing technology, specifically relating to a method and system for intelligent analysis and management of source, grid, load and storage based on big data. Background Technology

[0002] With the transformation of the energy structure and the rapid development of smart grids, the widespread application of clean energy (such as photovoltaic and wind power) and the advancement of energy storage technology have provided new opportunities for the optimized management of power systems. However, this also presents traditional power systems with significant challenges, especially given the increasing proportion of renewable energy, which puts the stability and reliability of power systems to a greater test. Traditional power grids struggle to efficiently and dynamically dispatch various energy resources (such as photovoltaics, energy storage, and electric vehicle charging), leading to resource waste or supply-demand imbalances, further exacerbating the difficulty of energy management.

[0003] Existing technologies have the following technical problems: They typically focus only on the management of a single resource, such as the scheduling of photovoltaic power generation or energy storage equipment, lacking comprehensive coordination and optimization of multiple resources such as photovoltaics, energy storage, and grid load, resulting in low resource utilization efficiency; moreover, they rely on static scheduling strategies and cannot make dynamic adjustments based on real-time data, making it difficult to effectively cope with uncertainties in the power system, such as fluctuations in photovoltaic power generation and changes in load demand; their systems have poor scalability and are difficult to adapt to the rapid growth of modern load demand. Summary of the Invention

[0004] To address the problems existing in the above-mentioned technologies, a method and system for intelligent analysis and management of source, grid, load and storage based on big data is provided.

[0005] The technical solution adopted by this invention to solve its technical problem is: This technical solution proposes a source-grid-load-storage intelligent analysis and management method based on big data, including the following steps: S1: Real-time collection and monitoring of multi-source heterogeneous data from the power generation, grid, load and storage system. The multi-source heterogeneous data includes photovoltaic systems, energy storage devices and grid loads. Based on the collected multi-source heterogeneous data, initial data aggregation is performed to obtain the total power generation capacity. S2: Based on the collected real-time multi-source data and total power generation capacity, recursive calculation is used to dynamically update the photovoltaic system, energy storage capacity and grid load; S3: Based on the changes in the multi-source data at the previous moment, update the state of the source-grid-load-storage system using recursive relationships, dynamically assign weights to the changes in each multi-source heterogeneous data, update the overall state of the source-grid-load-storage system, and adjust the output of the source-grid-load-storage system in real time based on the feedback control mechanism.

[0006] Preferably, in step S1, the photovoltaic system collects real-time data on solar radiation and photovoltaic module power generation through smart meters and environmental sensors. The energy storage device collects data on charging and discharging power, battery voltage, current, and remaining power in real time through the battery management system. The power grid load collects the power grid operating status and users' electricity demand in real time through smart meters and load monitoring equipment.

[0007] Preferably, the source-grid-load-storage system is defined in t The initial state at time 0 includes the status of photovoltaic power generation, energy storage capacity, and grid load. The preliminary multi-source heterogeneous data collected includes: Photovoltaic power generation is measured using smart meters and environmental sensors. P pv ( t 0); Monitor the energy storage capacity of the energy storage device through the battery management system. E s ( t 0); Monitor users' grid load through smart meters and load monitoring equipment. P load ( t 0).

[0008] Preferably, the initial power generation capacity of the power generation system (source-grid-load-storage system) is aggregated into the total power generation capacity. The total power generation capacity is the initial power generation of the power generation system (source-grid-load-storage system). The initial power generation represents the power output provided by the power generation system at the initial moment. The formula for calculating the initial power generation is as follows: (1); In the formula, P gen ( t 0) indicates that the source-grid-load-storage system is in ( t Total power generation capacity at time 0) P gen,i ( t 0) indicates the first i One resource in ( t Power generation capacity at time 0) n Indicates the quantity of power generation resources. α i Indicates the first i The contribution coefficient of each resource to the total power generation capacity.

[0009] Preferably, in step S2, the updating of the photovoltaic system includes adjusting the photovoltaic power generation based on real-time environmental factors, wherein the formula for calculating the photovoltaic power generation is as follows: (2); In the formula, P pv ( t () indicates the current time. t The photovoltaic power generation is the photovoltaic system's output. t Actual power generation at any given time I ( t )and I ( t -1) indicates t Time and t Solar radiation intensity at time -1 β This represents the sensitivity coefficient of a photovoltaic system to changes in radiation intensity. The initial photovoltaic power generation is obtained by multiplying the solar radiation intensity at the initial moment by the efficiency coefficient of the photovoltaic system, and the photovoltaic power generation is optimized in real time through dynamic response to environmental changes.

[0010] Preferably, in step S2, the updating of the energy storage device includes: the energy storage device's capacity in each time step is determined by the charging power and discharging power; the charging efficiency and discharging efficiency represent the actual energy conversion efficiency of the energy storage device during charging and discharging, respectively; the energy storage device's capacity is updated in each time step according to the current charging and discharging power; this simulates the energy storage device's response and regulation capability to the grid load; and the energy storage capacity update formula is expressed as: (3); In the formula, E s ( t ) indicates that the energy storage device is in t The battery charge at any given time represents the electrical energy currently stored in the energy storage device, and determines the power capacity provided by the device. or ch and or dis This represents the charge / discharge efficiency coefficient. P ch ( t )and Pdis ( t ) respectively represent t The charging and discharging power of the energy storage system at all times, with the initial energy storage capacity being the battery's maximum capacity.

[0011] Preferably, in step S2, the grid load update includes matching the grid load with photovoltaic power generation and total power generation capacity, and the grid load update formula is expressed as: (4); In the formula, P load ( t )express tThe grid load at a given time represents the total electricity consumption of the grid at that current moment. d The load change response coefficient represents the sensitivity of the grid load to changes in power generation. The initial grid load is obtained by weighting the base load and the loads of each user group and then adding them together.

[0012] Preferably, in S3, the overall state of the power generation, grid, load and storage system is jointly determined by the current value and change of the photovoltaic system, energy storage equipment and grid load, and the state of the power generation, grid, load and storage system is updated at each moment by the weighted average of the state at the previous moment and the change of each resource.

[0013] Preferably, the update formula for the source-grid-load-storage system is expressed as: (5); In the formula, S state ( t )express t The overall state vector of the source-grid-load-storage system at any given time. ∆P pv ( t ) indicates that photovoltaic power generation is t Changes over time ∆E s ( t ) indicates the amount of energy stored. t Changes over time ∆P load ( t ) indicates that the grid load is t Changes over time c 1. c 2. c 3 represents the influence weight of each resource on the overall state change of the source-grid-load-storage system. The initial state of the source-grid-load-storage system is a vector composed of photovoltaic power generation, energy storage power and grid load at the initial moment.

[0014] A big data-based intelligent analysis and management system for source-grid-load-storage, used to implement the aforementioned big data-based intelligent analysis and management method for source-grid-load-storage, is characterized by comprising: The data acquisition module acquires real-time data from the photovoltaic system, energy storage equipment, and grid load through smart meters, environmental sensors, battery management systems, and load monitoring equipment, and transmits it to the initial resource aggregation module. The initial resource aggregation module calculates and sets the initial state of the source-grid-load-storage system. By aggregating various resources, it calculates the initial total power generation capacity of the source-grid-load-storage system and transmits it to the resource state update module. The resource status update module is used to update the status of photovoltaic power generation, energy storage capacity and grid load. The photovoltaic power generation is dynamically adjusted according to environmental changes, the energy storage capacity is dynamically updated according to the charging and discharging status, and the grid load is dynamically adjusted according to the balance between power generation and load demand. The updated resource status is transmitted to the system status update module. The system status update module calculates the overall status of the source-grid-load-storage system. By calculating the coordinated control of photovoltaic, energy storage and grid load, it calculates the mutual influence between resources. Based on the status at the previous moment and the changes of each resource, it dynamically adjusts the resource allocation of the source-grid-load-storage system and transmits the updated status of the source-grid-load-storage system to the feedback module. The feedback module provides feedback on the real-time status of the power generation, grid, load, and energy storage system. The system responds promptly to changes in load demand, photovoltaic power generation, and energy storage capacity, and adjusts the output of the power generation, grid, load, and energy storage system in real time.

[0015] Compared with the prior art, the present invention has the following advantages: 1. This invention dynamically adjusts key indicators such as photovoltaic system, energy storage capacity, and grid load based on real-time collected data. Through recursive calculation and feedback mechanisms, the source-grid-load-storage system can adjust resource scheduling strategies in a timely manner when facing changes in the external environment, such as climate change and fluctuations in electricity demand, thereby ensuring grid stability and the continuity of power supply.

[0016] 2. This invention ensures that the grid load is rationally allocated among different power generation resources through intelligent scheduling. When the photovoltaic power generation is high, the excess power can be used first to reduce energy storage discharge or increase the grid load and avoid grid overload. When the photovoltaic power generation is low, energy storage devices and traditional power generation facilities can supplement the power in time to ensure grid load balance.

[0017] 3. This invention updates the state of the source-grid-load-storage system through recursive relationships and weighted updates. The source-grid-load-storage system can accurately control the balance between photovoltaic systems, energy storage devices and grid loads. The introduction of the feedback mechanism enables the source-grid-load-storage system to automatically adjust the scheduling strategy when errors occur, avoiding grid instability caused by load forecasting errors or changes in equipment status. Attached Figure Description

[0018] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which: Figure 1 This is the overall flowchart of the present invention; Figure 2 This is a diagram showing the overall system module composition of the present invention. Detailed Implementation

[0019] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0020] Example 1 like Figure 1 As shown, this embodiment proposes a big data-based intelligent analysis and management method for source-grid-load-storage systems, including the following steps: S1: Real-time collection and monitoring of multi-source heterogeneous data from the power generation, grid, load and storage system. The multi-source heterogeneous data includes photovoltaic systems, energy storage devices and grid loads. Based on the collected multi-source heterogeneous data, initial data aggregation is performed to obtain the total power generation capacity. S2: Based on the collected real-time multi-source data and total power generation capacity, recursive calculation is used to dynamically update the photovoltaic system, energy storage capacity and grid load; S3: Based on the changes in the multi-source data at the previous moment, update the state of the source-grid-load-storage system using recursive relationships, dynamically assign weights to the changes in each multi-source heterogeneous data, update the overall state of the source-grid-load-storage system, and adjust the output of the source-grid-load-storage system in real time based on the feedback control mechanism.

[0021] In S1, to ensure the effective operation of the power generation, grid, load and storage system, data acquisition technology is used to monitor the photovoltaic system, energy storage equipment and grid load in real time. Data acquisition includes not only data from individual photovoltaic or energy storage equipment, but also the overall operation of the power system. The collected data is transmitted to the cloud platform through wireless communication technologies (such as LoRa, 5G, etc.) to form a comprehensive big data set, providing real-time data support for the intelligent scheduling and optimization of the power generation, grid, load and storage system.

[0022] The photovoltaic system collects meteorological data in real time, such as solar radiation and photovoltaic module power generation, through smart meters and environmental sensors (such as radiation intensity and temperature). The energy storage device uses a battery management system to collect data such as charging and discharging power, battery voltage, current and remaining power in real time, ensuring that the status information of the energy storage device can be updated at any time. The power grid load collects the real-time operating status of the power grid and the electricity demand of users through smart meters and load monitoring equipment, covering a variety of electricity consumption scenarios such as households, businesses and industries.

[0023] In the initial state setting phase, the source-grid-load-storage system is defined as follows: t The initial state at time 0 includes the status of photovoltaic power generation, energy storage capacity, and grid load. The preliminary multi-source heterogeneous data collected includes: Photovoltaic power generation is obtained by measuring solar radiation, temperature, historical power generation, etc. using smart meters and environmental sensors. P pv ( t 0); Monitor the energy storage capacity of the energy storage device through the battery management system. E s ( t 0); Monitor the power grid load of users (residential, industrial, commercial, etc.) through smart meters and load monitoring equipment. P load ( t 0).

[0024] The initial generating capacity of the power generation system (source-grid-load-storage system) is aggregated into the total generating capacity, which is the initial generating output of the system. The initial generating output represents the power output provided by the system at the initial moment, and the formula for calculating the initial generating output is as follows: (1); In the formula, P gen ( t 0) indicates that the source-grid-load-storage system is in ( t Total power generation capacity at time 0) P gen,i ( t 0) indicates the first i Resources (such as photovoltaics, energy storage, etc.) in ( t Power generation capacity at time 0) n Indicates the quantity of power generation resources. α i Indicates the first i The contribution coefficient of each resource to the total power generation capacity is obtained through historical data analysis or estimated based on the ratio of the rated capacity of the resource to the total system capacity. The value range is [0,1]. The initial power generation calculation formula comes from the resource balance principle of the power system, ensuring that the contribution of each resource can be reflected in the system.

[0025] In S2, the photovoltaic system update includes adjusting photovoltaic power generation based on real-time environmental factors (such as solar radiation intensity). There is a linear relationship between photovoltaic power generation and solar radiation intensity; changes in solar radiation intensity directly affect the power output of the photovoltaic system. Therefore, the current photovoltaic power generation is obtained by adding a correction factor for changes in radiation intensity to the photovoltaic power generation from the previous moment. Dynamically adjusting photovoltaic power generation based on changes in solar radiation ensures that the power generation accurately reflects changes in current environmental conditions. The formula for calculating photovoltaic power generation is as follows: (2); In the formula, P pv ( t () indicates the current time. t The photovoltaic power generation is the photovoltaic system's output. t Actual power generation at any given time I ( t )and I ( t -1) indicates t Time and t The solar radiation intensity at -1 hour was obtained through weather station, radiation sensor, or satellite remote sensing data. β The sensitivity coefficient of a photovoltaic system to changes in radiation intensity is obtained through experiments or historical data and ranges from [0,1].

[0026] The initial photovoltaic (PV) power generation is obtained by multiplying the initial solar radiation intensity by the efficiency coefficient of the PV system. The efficiency coefficient of the PV module represents the relationship between radiation intensity and power generation, and is obtained from the technical specifications of the PV module. The updated formula for PV power generation reflects how the PV system adjusts its power generation capacity based on real-time environmental data (such as changes in solar radiation), optimizing PV power generation in real time through dynamic response to environmental changes.

[0027] In S2, the energy storage device update includes the fact that the stored energy capacity is directly affected by the charging and discharging power, and the charging and discharging efficiency of the energy storage battery plays a key role in the change of energy capacity. The energy capacity of the energy storage system in each time step is determined by the charging power and discharging power. Simultaneously, considering the efficiency loss during charging and discharging, the charging efficiency and discharging efficiency represent the actual energy conversion efficiency of the energy storage device during charging and discharging, respectively. The energy capacity of the energy storage device is updated in each time step according to the current charging and discharging power, simulating the energy storage system's response and regulation capability to the grid load, ensuring that the energy capacity of the energy storage device always remains within a reasonable range. The energy storage capacity update formula is expressed as: (3); In the formula, E s ( t ) indicates that the energy storage device is in t The battery charge at any given time represents the electrical energy currently stored in the energy storage device, and determines the power capacity provided by the device. or ch and or dis This represents the charge / discharge efficiency coefficient, which depends on the performance of the specific equipment and ranges from (0,1). P ch ( t )and Pdis ( t) respectively represent t The charging and discharging power of the energy storage system at all times, with the initial energy storage capacity being the battery's maximum capacity.

[0028] In S2, the grid load update includes matching the grid load with photovoltaic (PV) power generation and total power generation capacity. The update is related to the difference between PV power generation and total power generation capacity at the current moment. When PV power generation exceeds total power generation capacity, the grid load needs to increase accordingly to meet higher electricity demand; conversely, when PV power generation is lower than total power generation capacity, the load demand decreases relatively. Therefore, the change in grid load depends not only on the load state at the previous moment but also on the difference between PV power generation and the system's total power generation capacity. The grid load update formula is expressed as: (4); In the formula, P load ( t )express t The grid load at a given time represents the total electricity consumption of the grid at that current moment. d The load change response coefficient represents the sensitivity of the grid load to changes in power generation. It is obtained through historical data analysis or experimental data regression, and its value ranges from [0,1]. The initial grid load is obtained by weighting and adding the base load (i.e., minimum load demand) with the loads of each user group. The grid load update formula helps the source-grid-load-storage system balance power generation and load demand, ensuring the stability of grid operation.

[0029] In S3, during the recursive calculation process, the overall state of the source-grid-load-storage system is jointly determined by the current values ​​and changes of the photovoltaic system, energy storage equipment, and grid load. The state of the source-grid-load-storage system at each moment is updated by the weighted average of the state at the previous moment and the changes of each resource.

[0030] At any given moment, the photovoltaic power generation, energy storage battery capacity, and grid load are all affected by the state of the previous moment. Therefore, it is necessary to calculate the current state of the power generation, grid, load, and storage system through weighted updates to ensure that the system can dynamically adjust and optimize based on real-time data of various resources. The recursive relationship ensures that the system can flexibly adjust resource scheduling strategies when facing real-time changes, avoiding imbalances or resource waste, thereby ensuring the stability and efficient operation of the power system.

[0031] The update formula for the source-grid-load-storage system is expressed as: (5); In the formula, S state ( t )express tThe overall state vector of the power grid-source-load-storage system at any given time contains state information of all resources in the power system, such as photovoltaic power generation, energy storage capacity, and grid load. ∆P pv ( t ) indicates that photovoltaic power generation is t The change over time, i.e. P pv ( t )- P pv ( t -1), ∆E s ( t ) indicates the amount of energy stored. t The change over time, i.e. E s ( t )- Es ( t -1), ∆P load ( t ) indicates that the grid load is t The change over time, i.e. P load ( t )- P load ( t -1), c 1. c 2. c 3 represents the influence weight of each resource (photovoltaic system, energy storage power, and grid load) on the overall state change of the source-grid-load-storage system. It is estimated by data fitting, machine learning model or optimization algorithm. The initial state of the source-grid-load-storage system is a vector composed of photovoltaic power generation, energy storage power and grid load at the initial time.

[0032] The state update formula of the power generation, grid, load and storage system is the core of the dynamic scheduling of the power generation, grid, load and storage system. It ensures that the state update at each point in time is not only based on the input data at the current moment, but also affected by the state changes at the previous moment. Through the recursive relationship, the power generation, grid, load and storage system can adjust the scheduling strategy of various resources in real time and maintain the balance of the power system.

[0033] Through existing feedback mechanisms, adjustments are made in real time based on the actual operation of the power grid, load changes, and the status of power resources (such as the remaining power of energy storage batteries). For example, if the predicted load demand changes are inconsistent with the actual load, the system will adjust the charging and discharging strategy of the energy storage equipment or adjust the scheduling mode of photovoltaic power generation based on the feedback.

[0034] Example 2 like Figure 2As shown, this embodiment proposes a big data-based intelligent analysis and management system for source-grid-load-storage, used to implement a big data-based intelligent analysis and management method for source-grid-load-storage, including: The data acquisition module acquires real-time data from the photovoltaic system, energy storage equipment, and grid load through smart meters, environmental sensors, battery management systems, and load monitoring equipment, and transmits it to the initial resource aggregation module. The initial resource aggregation module calculates and sets the initial state of the power generation, grid, load and storage system (including photovoltaic power generation, energy storage power, grid load, etc.) based on real-time data provided by the data acquisition module. By aggregating various resources (photovoltaic system, energy storage power, grid load), it calculates the initial total power generation capacity of the power generation, grid, load and storage system and transmits it to the resource status update module. The resource status update module updates the status of photovoltaic power generation, energy storage capacity and grid load based on the initial total power generation capacity provided by the initial resource aggregation module and the real-time data provided by the data acquisition module. The photovoltaic power generation is dynamically adjusted according to environmental changes (such as solar radiation), the energy storage capacity is dynamically updated according to the charging and discharging status, and the grid load is dynamically adjusted according to the balance between power generation and load demand. The updated resource status is then transmitted to the system status update module. The system status update module calculates the overall status of the source-grid-load-storage system based on the resource status changes provided by the resource status update module. By calculating the coordinated control of photovoltaic, energy storage and grid load, it calculates the mutual influence between resources (such as the impact of photovoltaic power generation on grid load). Based on the status at the previous moment and the changes of each resource, it dynamically adjusts the resource allocation of the source-grid-load-storage system and transmits the updated status of the source-grid-load-storage system to the feedback module. The feedback module provides feedback on the real-time status of the power generation, grid, load, and energy storage system. The system responds promptly to changes in load demand, photovoltaic power generation, and energy storage capacity, and adjusts the output of the power generation, grid, load, and energy storage system in real time to ensure that the system remains stable even under conditions of large load fluctuations.

[0035] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A big data-based intelligent analysis and management method for power generation, grid, load, and storage, characterized in that: Includes the following steps: S1: Real-time collection and monitoring of multi-source heterogeneous data from the power generation, grid, load and storage system. The multi-source heterogeneous data includes photovoltaic systems, energy storage devices and grid loads. Based on the collected multi-source heterogeneous data, initial data aggregation is performed to obtain the total power generation capacity. S2: Based on the collected real-time multi-source data and total power generation capacity, recursive calculation is used to dynamically update the photovoltaic system, energy storage capacity and grid load; S3: Based on the changes in the multi-source data at the previous moment, update the state of the source-grid-load-storage system using recursive relationships, dynamically assign weights to the changes in each multi-source heterogeneous data, update the overall state of the source-grid-load-storage system, and adjust the output of the source-grid-load-storage system in real time based on the feedback control mechanism.

2. The intelligent analysis and management method for source-grid-load-storage based on big data as described in claim 1, characterized in that, In S1, the photovoltaic system collects real-time data on solar radiation and photovoltaic module power generation through smart meters and environmental sensors. The energy storage device collects data on charging and discharging power, battery voltage, current, and remaining power in real time through the battery management system. The power grid load collects the power grid operating status and users' electricity demand in real time through smart meters and load monitoring equipment.

3. The intelligent analysis and management method for source-grid-load-storage based on big data as described in claim 1, characterized in that, Define the source-grid-load-storage system in t The initial state at time 0 includes the status of photovoltaic power generation, energy storage capacity, and grid load. The preliminary multi-source heterogeneous data collected includes: Photovoltaic power generation is measured using smart meters and environmental sensors. P pv ( t 0); Monitor the energy storage capacity of the energy storage device through the battery management system. E s ( t 0); Monitor users' grid load through smart meters and load monitoring equipment. P load ( t 0).

4. The intelligent analysis and management method for source-grid-load-storage based on big data as described in claim 3, characterized in that, The initial generating capacity of the power generation system (source-grid-load-storage system) is aggregated into the total generating capacity, which is the initial generating output of the system. The initial generating output represents the power output provided by the system at the initial moment, and the formula for calculating the initial generating output is as follows: （1）； In the formula, P gen ( t 0) indicates that the source-grid-load-storage system is in ( t Total power generation capacity at time 0) P gen,i ( t 0) indicates the first i One resource in ( t Power generation capacity at time 0) n Indicates the quantity of power generation resources. α i Indicates the first i The contribution coefficient of each resource to the total power generation capacity.

5. The intelligent analysis and management method for source-grid-load-storage based on big data as described in claim 1, characterized in that, In step S2, the photovoltaic system update includes adjusting the photovoltaic power generation based on real-time environmental factors. The formula for calculating photovoltaic power generation is as follows: （2）； In the formula, P pv ( t () indicates the current time. t The photovoltaic power generation is the photovoltaic system's output. t Actual power generation at any given time I ( t )and I ( t -1) indicates t Time and t Solar radiation intensity at time -1 β This represents the sensitivity coefficient of a photovoltaic system to changes in radiation intensity. The initial photovoltaic power generation is obtained by multiplying the solar radiation intensity at the initial moment by the efficiency coefficient of the photovoltaic system, and the photovoltaic power generation is optimized in real time through dynamic response to environmental changes.

6. The intelligent analysis and management method for source-grid-load-storage based on big data as described in claim 1, characterized in that, In step S2, the energy storage device update includes the following: the energy storage device's capacity in each time step is determined by the charging power and discharging power. The charging efficiency and discharging efficiency represent the actual energy conversion efficiency of the energy storage device during charging and discharging, respectively. The energy storage device's capacity is updated in each time step based on the current charging and discharging power, simulating the energy storage device's response and regulation capabilities to the grid load. The energy storage capacity update formula is expressed as: （3）； In the formula, E s ( t ) indicates that the energy storage device is in t The battery charge at any given time represents the electrical energy currently stored in the energy storage device, and determines the power capacity provided by the device. η ch and η dis This represents the charge / discharge efficiency coefficient. P ch ( t )and Pdis ( t ) respectively represent t The charging and discharging power of the energy storage system at all times, with the initial energy storage capacity being the battery's maximum capacity.

7. The intelligent analysis and management method for source-grid-load-storage based on big data as described in claim 1, characterized in that, In step S2, the grid load update includes matching the grid load with photovoltaic power generation and total power generation capacity. The grid load update formula is expressed as follows: （4）； In the formula, P load ( t )express t The grid load at a given time represents the total electricity consumption of the grid at that current moment. δ The load change response coefficient represents the sensitivity of the grid load to changes in power generation. The initial grid load is obtained by weighting the base load and the loads of each user group and then adding them together.

8. The intelligent analysis and management method for source-grid-load-storage based on big data as described in claim 1, characterized in that, In S3, the overall state of the source-grid-load-storage system is jointly determined by the current value and change of the photovoltaic system, energy storage equipment and grid load. The state of the source-grid-load-storage system is updated at each moment by the weighted average of the state at the previous moment and the change of each resource.

9. The intelligent analysis and management method for source-grid-load-storage based on big data as described in claim 8, characterized in that, The update formula for the source-grid-load-storage system is expressed as: （5）； In the formula, S state ( t )express t The overall state vector of the source-grid-load-storage system at any given time. ∆P pv ( t ) indicates that photovoltaic power generation is t Changes over time ∆E s ( t ) indicates the amount of energy stored. t Changes over time ∆P load ( t ) indicates that the grid load is t Changes over time γ 1. γ 2. γ 3 represents the influence weight of each resource on the overall state change of the source-grid-load-storage system. The initial state of the source-grid-load-storage system is a vector composed of photovoltaic power generation, energy storage power and grid load at the initial moment.

10. A big data-based intelligent analysis and management system for source-grid-load-storage, used to implement the big data-based intelligent analysis and management method for source-grid-load-storage as described in claims 1-9, characterized in that, include: The data acquisition module acquires real-time data from the photovoltaic system, energy storage equipment, and grid load through smart meters, environmental sensors, battery management systems, and load monitoring equipment, and transmits it to the initial resource aggregation module. The initial resource aggregation module calculates and sets the initial state of the source-grid-load-storage system. By aggregating various resources, it calculates the initial total power generation capacity of the source-grid-load-storage system and transmits it to the resource state update module. The resource status update module is used to update the status of photovoltaic power generation, energy storage capacity and grid load. The photovoltaic power generation is dynamically adjusted according to environmental changes, the energy storage capacity is dynamically updated according to the charging and discharging status, and the grid load is dynamically adjusted according to the balance between power generation and load demand. The updated resource status is transmitted to the system status update module. The system status update module calculates the overall status of the source-grid-load-storage system. By calculating the coordinated control of photovoltaic, energy storage and grid load, it calculates the mutual influence between resources. Based on the status at the previous moment and the changes of each resource, it dynamically adjusts the resource allocation of the source-grid-load-storage system and transmits the updated status of the source-grid-load-storage system to the feedback module. The feedback module provides feedback on the real-time status of the power generation, grid, load, and energy storage system. The system responds promptly to changes in load demand, photovoltaic power generation, and energy storage capacity, and adjusts the output of the power generation, grid, load, and energy storage system in real time.

Images