Edge computing based optical storage building integrated energy management system

Abstract

The application relates to the technical field of energy management, and particularly discloses an integrated energy management system for a light storage building based on edge computing, which comprises a data acquisition module, which is used for collecting inverter operation state data, current sensor operation state data and light data in the energy management system in real time through edge computing. The operation state of the inverter can be analyzed by combining the data collected in the data acquisition module, and whether the operation state of the inverter is abnormal can be analyzed. Then, the performance of the inverter can be evaluated in real time by combining the real-time collected energy storage system data, and whether the performance change of the inverter will cause additional energy loss and reduce the power generation efficiency can be further analyzed. Then, whether the inverter optimization operation is needed is decided based on the analysis result, that is, the inverter can be optimized to avoid the occurrence of the condition of reducing energy loss, so that the power generation efficiency is improved and the energy utilization is maximized.

Description

Technical Field

[0001] This invention relates to the field of energy management technology, specifically to a building-integrated energy management system based on edge computing and solar energy storage. Background Technology

[0002] The building-integrated energy management system (BIAS) is a comprehensive solution that deeply integrates photovoltaic power generation, energy storage technology and building energy management. It not only reshapes the way energy is produced and consumed, but also provides an economical and reliable technical path for achieving the dual carbon goals. With technological advancements and policy support, its application prospects will be even broader.

[0003] When in use, the building-integrated photovoltaic (PV) and energy storage (BIPV) energy management system typically configures the energy storage system capacity based on the building's electricity load curve and PV power generation forecasts. This avoids energy waste caused by overcapacity or insufficient capacity. Alternatively, it can use LSTM neural network models to predict the next day's power generation based on historical data and weather forecasts, adjust the energy storage charging and discharging plan in advance, and predict building load demand through user electricity consumption habit analysis. This achieves precise matching of "power generation - energy storage - load," thereby reducing energy loss.

[0004] In existing technologies, in order to reduce energy loss and maximize energy utilization, charging plans or energy storage system capacity are generally dynamically adjusted based on external power generation data and load forecast data to reduce energy loss. However, the impact of inverter performance on energy loss in the building-integrated photovoltaic and energy storage management system is not taken into account, resulting in a certain amount of energy loss and thus failing to achieve maximum energy utilization. Summary of the Invention

[0005] The purpose of this invention is to provide a building-integrated energy management system based on edge computing, which solves the following technical problems: How to reduce energy loss based on inverter performance analysis.

[0006] The objective of this invention can be achieved through the following technical solutions: A building-integrated energy management system based on edge computing and solar energy storage, the system comprising: The data acquisition module is used to collect real-time data on inverter operating status, current sensor operating status, and illumination data in the energy management system through edge computing. The data monitoring module is used to monitor the energy storage system data in the energy management system in real time and to filter and clean the data. The data analysis module is used to analyze the inverter's own operating status by combining real-time collected current sensor data and inverter operating status data. The data evaluation module is used to evaluate the performance of the inverter in real time by combining the analysis results of the inverter's own operating status with the real-time collected data of the energy storage system. The data decision module is used to combine the results of the implementation evaluation of inverter performance to decide whether inverter optimization is needed.

[0007] Furthermore, the data collected by the data acquisition module includes: Inverter operating status data and current sensor operating status data, wherein the inverter operating status data includes inverter input power, operating voltage and conversion efficiency; The current sensor operating status data includes the current sensor's sampling frequency and calibration deviation value; The data monitoring module monitors energy storage system data including remaining battery power, capacity decay rate, and internal resistance.

[0008] Furthermore, the analysis process of the data analysis module includes: S1: By combining real-time collected current sensor operating status data and illumination data, the inverter input power impact index is calculated. S2: By comparing the inverter input power influence index with the preset influence index threshold, and judging whether the collected inverter input power is artificially high based on the comparison result; S3: When it is determined that the collected inverter input power is artificially high, analyze the correlation between the inverter input power influence index and the inverter input power. S4: The inverter's input power is corrected by combining the correlation analysis results of the inverter input power influence index and the inverter input power, and the inverter's own operating status is analyzed by combining the inverter's operating status data.

[0009] Furthermore, the calculation process in S1 includes: Through formula Calculate the inverter input power influence index at the i-th data acquisition time. ; Where i represents a data collection at a fixed interval. This is the actual sampling frequency of the current sensor. With the preset sampling frequency, To define a function, if Then let ,like Then let , This represents the calibration deviation value of the current sensor during the i-th data acquisition. The preset calibration deviation value, This represents the total number of data collections from the start of the energy management system on the day it is used until the i-th data collection. Let be the light intensity during the i-th data acquisition. For all The average value.

[0010] Furthermore, the analysis process in S2 includes: Influence index by the inverter input power during the i-th data acquisition Compared with the preset impact index threshold Perform a comparison; like The system determines that during the i-th data acquisition, the inverter's input power is affected, which may cause the acquired input power to be artificially high compared to the actual input power. like The system determines that during the i-th data acquisition, the inverter's input power was not affected, and the acquired input power was similar to the actual input power.

[0011] Furthermore, the analysis process in S3 includes: Through formula Calculate the correlation coefficient between the inverter input power influence index and the inverter input power at the i-th data acquisition time. ; in, The inverter input power during the i-th data acquisition is... For all The average value, For all The average value.

[0012] Furthermore, the analysis process in S4 includes: Through formula Calculate the influence value of the inverter's operating state at the i-th data acquisition time. ; in, The preset inverter input power, The adjustment coefficient lookup table function has a range of values ​​that are related to... The numerical values ​​correspond one-to-one. The inverter's operating voltage during the i-th data acquisition is... For all The average value, The preset operating voltage for the inverter, Let be the conversion efficiency of the inverter during the i-th data acquisition. This is the preset conversion efficiency.

[0013] Furthermore, the analysis process in S4 also includes: By influencing the inverter's operating state during the i-th data acquisition The threshold value that affects the preset operating status Perform a comparison; like The system determines that the inverter's operating status is abnormal during the i-th data acquisition and optimization is required. like The system determines that the inverter's operating status is not abnormal during the i-th data acquisition and no optimization work is required. Further analysis is then conducted in conjunction with the energy storage system data.

[0014] Furthermore, the evaluation process of the data evaluation module includes: Through formula Calculate the performance impact index of the inverter during the i-th data acquisition. ; Where 'a' represents any single charge / discharge operation of the battery in the energy storage system. The total number of battery charge / discharge cycles from the start of the energy management system on the day of its operation to the i-th data acquisition. Let be the internal resistance of the battery in the energy storage system during the a-th charge-discharge operation. Let be the battery capacity degradation rate at the i-th data acquisition. The preset capacity decay rate, The remaining battery power at the time of the i-th data acquisition. The preset remaining battery power. and These are weighting coefficients, set based on empirical fitting.

[0015] Furthermore, the decision-making process of the data decision module includes: By exponentially controlling the performance impact of the inverter during the i-th data acquisition Compared with the preset performance impact index threshold Perform a comparison; like The system determines that the inverter's performance has degraded during the i-th data acquisition and decides to perform inverter optimization. Conversely, if If the system determines that the inverter's performance does not significantly decrease during the i-th data acquisition, no inverter optimization operation will be performed.

[0016] The beneficial effects of this invention are: (1) This invention analyzes the inverter’s own operating status by combining the data collected in the data acquisition module. It can analyze whether there are any abnormalities in the inverter’s operating status during use. Then, by combining the real-time collected energy storage system data, the inverter’s performance can be evaluated in real time. It can further analyze whether the inverter’s performance changes will lead to additional energy loss and thus reduce power generation efficiency. Then, based on the analysis results, it can decide whether to perform inverter optimization. By optimizing the inverter, the situation of reducing energy loss can be avoided, thereby improving power generation efficiency and maximizing energy utilization.

[0017] (2) This invention obtains the inverter input power influence index by calculating based on diversified data, and compares it with the preset influence index threshold to determine whether the currently collected inverter input power is artificially high. When it is determined that there is artificially high, the inverter input power is corrected by introducing the correlation analysis results between the inverter input power influence index and the inverter input power. This can achieve the cleaning of the inverter input power data, so that the data is closer to the true value, and thus provide reliable data for subsequent analysis of the inverter's own operating status, so as to ensure the accuracy of the analysis results.

[0018] (3) The present invention influences the index by measuring the inverter input power during the i-th data acquisition. Compared with the preset impact index threshold By comparing the data, we can accurately analyze the impact on the inverter's input power during the i-th data acquisition, and determine whether there is any artificially high input power during the i-th data acquisition. This enables us to monitor the inverter's input power data, ensuring its reliability and accuracy. Consequently, subsequent analyses of the inverter's operating status are based on highly accurate data, guaranteeing the reliability of the analysis results.

[0019] (4) The present invention affects the value of the inverter operating state during the i-th data acquisition. The threshold value that affects the preset operating status By comparing the data, an accurate judgment can be made as to whether there are any abnormalities in the inverter's operating state during the i-th data acquisition. Furthermore, the operating state of the inverter during the i-th data acquisition has an impact on the value... It is obtained based on diversified data correction and fusion, so the reliability of the data is high. On this basis, the accuracy of the judgment results can be improved, thereby timely detection of inverter operation problems and timely optimization, reducing energy loss and improving power generation efficiency.

[0020] (5) The present invention uses the performance influence index of the inverter during the i-th data acquisition. Compared with the preset performance impact index threshold By comparing the data, the system can accurately determine whether the inverter's performance has decreased during the i-th data acquisition. Based on this comparison, since the data is calculated by combining the state data of the batteries in the energy storage system, the data can reflect the inverter's performance under the influence of the external environment. Based on this, the system can promptly identify inverter operation problems and optimize them in a timely manner to ensure good power generation efficiency. Attached Figure Description

[0021] The invention will now be further described with reference to the accompanying drawings.

[0022] Figure 1 This is a schematic block diagram of the building-integrated energy management system based on edge computing for photovoltaics and energy storage in this invention; Figure 2 This is a flowchart of the data analysis module in this invention. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] Please see Figure 1 As shown, in one embodiment, this application provides a building-integrated energy management system based on edge computing, the system comprising: The data acquisition module is used to collect real-time data on inverter operating status, current sensor operating status, and illumination data in the energy management system through edge computing. The data monitoring module is used to monitor the energy storage system data in the energy management system in real time and to filter and clean the data. The data analysis module is used to analyze the inverter's own operating status by combining real-time collected current sensor data and inverter operating status data. The data evaluation module is used to evaluate the performance of the inverter in real time by combining the analysis results of the inverter's own operating status with the real-time collected data of the energy storage system. The data decision module is used to combine the results of the implementation evaluation of inverter performance to decide whether inverter optimization is needed. Through the above technical solution, this example provides a data acquisition module and a data monitoring module. The data acquisition module is used to collect real-time inverter operating status data, current sensor operating status data, and illumination data in the energy management system through edge computing. The data monitoring module is used to monitor the energy storage system data in the energy management system in real-time and filter and clean the data. When the energy management system is in use, the data analysis module combines the real-time collected current sensor and inverter operating status data to analyze the inverter's own operating status. Based on the data evaluation module, the inverter's performance is evaluated in real-time by combining the inverter's own operating status analysis results with the real-time collected energy storage system data. Finally, the data decision module combines the real-time evaluation results of the inverter's performance to decide whether inverter optimization is needed. By combining this setup with data collected from the data acquisition module to analyze the inverter's own operating status, it is possible to analyze whether there are any abnormalities in the inverter's operating status during use. Then, by combining the real-time data collected from the energy storage system, the inverter's performance can be evaluated in real time. This allows for further analysis of whether changes in the inverter's performance will lead to additional energy losses and thus reduce power generation efficiency. Based on the analysis results, a decision can be made as to whether inverter optimization is necessary. By optimizing the inverter, energy losses can be avoided, thereby improving power generation efficiency and maximizing energy utilization.

[0025] The data collected by the data acquisition module includes: Inverter operating status data and current sensor operating status data, wherein the inverter operating status data includes inverter input power, operating voltage and conversion efficiency; The current sensor operating status data includes the current sensor's sampling frequency and calibration deviation value; The data monitoring module monitors energy storage system data including remaining battery power, capacity decay rate, and internal resistance. Through the above technical solution, this example provides data collected by the data acquisition module and data monitored by the data monitoring module. Based on diversified data support, it is possible to accurately analyze the status and performance changes of the inverter during operation, thereby providing reliable data support for deciding whether to optimize the inverter, ensuring the reliability of the decision results, and thus avoiding energy loss reduction.

[0026] Please see Figure 2 As shown, the analysis process of the data analysis module includes: S1: By combining real-time collected current sensor operating status data and illumination data, the inverter input power impact index is calculated. S2: By comparing the inverter input power influence index with the preset influence index threshold, and judging whether the collected inverter input power is artificially high based on the comparison result; S3: When it is determined that the collected inverter input power is artificially high, analyze the correlation between the inverter input power influence index and the inverter input power. S4: The inverter's input power is corrected by combining the correlation analysis results of the inverter input power influence index and the inverter input power, and the inverter's own operating status is analyzed by combining the inverter's operating status data. Through the above technical solution, this example provides the analysis process of the data analysis module. First, by combining the real-time collected current sensor operating status data and illumination data, the inverter input power influence index is calculated. Then, the inverter input power influence index is compared with the preset influence index threshold, and the comparison result is used to determine whether the collected inverter input power is artificially high. When it is determined that the operating status of the current sensor will cause the collected inverter input power to be artificially high, the correlation between the inverter input power influence index and the inverter input power is analyzed. Finally, the inverter input power is corrected by combining the correlation analysis results between the inverter input power influence index and the inverter input power, and the inverter's own operating status is analyzed by combining the inverter's operating status data. By setting it up in this way, the inverter input power influence index is obtained through calculation based on diversified data. By comparing it with the preset influence index threshold, it can be determined whether the currently collected inverter input power is artificially inflated. When artificially inflated data is found, the inverter input power is corrected by introducing the correlation analysis results between the inverter input power influence index and the inverter input power. This cleans the inverter input power data, making it closer to the true value. This provides reliable data for subsequent analysis of the inverter's own operating status, ensuring the accuracy of the analysis results.

[0027] The calculation process in S1 includes: Through formula Calculate the inverter input power influence index at the i-th data acquisition time. ; Where i represents a data collection at a fixed interval. This is the actual sampling frequency of the current sensor. With the preset sampling frequency, To define a function, if Then let ,like Then let , This represents the calibration deviation value of the current sensor during the i-th data acquisition. The preset calibration deviation value, This represents the total number of data collections from the start of the energy management system on the day it is used until the i-th data collection. Let be the light intensity during the i-th data acquisition. For all The average value; Through the above technical solution, this paper provides the inverter input power influence index at the i-th data acquisition time. It can be done through the formula The calculation yields the result, where the formula is... The fluctuation value of light intensity during the period from the start of use of the energy management system to the i-th data acquisition can be calculated. Clearly, the larger the fluctuation value of light intensity and the calibration deviation value of the current sensor during the period from the start of use of the energy management system to the i-th data acquisition, and the larger the actual sampling frequency of the current sensor is compared to the preset sampling frequency, the greater the influence index of the inverter input power at the i-th data acquisition. The higher the value of the light intensity fluctuation and the calibration deviation of the current sensor during the i-th data acquisition, the higher the inverter input power data at that time. Conversely, the lower the value of the light intensity fluctuation and the calibration deviation of the current sensor during the i-th data acquisition process from the start of the energy management system's operation that day, and the higher the actual sampling frequency of the current sensor is than the preset sampling frequency, the lower the inverter input power influence index at the i-th data acquisition time. The lower the value, the less likely the inverter's input power data is to be artificially high during the data acquisition. Therefore, based on this calculation process, we can make an accurate analysis for subsequent analysis of whether the inverter's input power is artificially high, and provide reliable data support for subsequent correction of the inverter's input power, ensuring the reliability of the correction results. Specifically, when the calibration deviation of the current sensor is large, zero-point drift or range error of the current sensor will cause the measured value to be higher than the actual value, resulting in an inflated power calculation. Furthermore, the higher the light intensity fluctuation value during the data acquisition process from the start of the day to the i-th data acquisition, the more rapid the light changes that day, which may cause the MPPT algorithm to make a brief misjudgment, treating voltage or current fluctuations as valid power input. Finally, when the actual sampling frequency of the current sensor is lower than the preset sampling frequency, since the preset sampling frequency is generally set according to the signal change frequency, when the actual sampling frequency of the current sensor is lower than the preset sampling frequency, it means that the actual sampling frequency of the current sensor is lower than the signal change frequency, which will cause the power calculation value to be distorted.

[0028] The analysis process in S2 includes: Influence index by the inverter input power during the i-th data acquisition Compared with the preset impact index threshold Perform a comparison; like The system determines that during the i-th data acquisition, the inverter's input power is affected, which may cause the acquired input power to be artificially high compared to the actual input power. like The system determines that during the i-th data acquisition, the inverter's input power was not affected, and the acquired input power was similar to the actual input power. Through the above technical solution, this embodiment influences the inverter input power during the i-th data acquisition by indexing. Compared with the preset impact index threshold By comparing the data, we can accurately analyze the impact on the inverter's input power during the i-th data acquisition, and determine whether there is any artificially high input power during the i-th data acquisition. This enables us to monitor the inverter's input power data, ensuring its reliability and accuracy. Consequently, subsequent analyses of the inverter's operating status are based on highly accurate data, guaranteeing the reliability of the analysis results.

[0029] The analysis process in S3 includes: Through formula Calculate the correlation coefficient between the inverter input power influence index and the inverter input power at the i-th data acquisition time. ; in, The inverter input power during the i-th data acquisition is... For all The average value, For all The average value; Through the above technical solution, this example provides the correlation coefficient between the inverter input power influence index and the inverter input power during the i-th data acquisition. It can be done through the formula The calculation method yields data that quantifies the synchronicity of the linear change between the inverter input power influence index and the inverter input power. In other words, it determines whether the inverter input power changes in a predictable manner when the inverter input power influence index changes. Based on this data, additional data support can be provided for subsequent corrections to the inverter input power, ensuring the reliability of the correction results and guaranteeing that subsequent analyses of the inverter's operating status are based on highly accurate data.

[0030] The analysis process in S4 includes: Through formula Calculate the influence value of the inverter's operating state at the i-th data acquisition time. ; in, The preset inverter input power, The adjustment coefficient lookup table function has a range of values ​​that are related to... The numerical values ​​correspond one-to-one. It should be noted that the values ​​of the adjustment coefficient lookup table function can be based on empirical data. The impact of the range of numerical values ​​on the inverter input power is based on test results. The inverter's operating voltage during the i-th data acquisition is... For all The average value, The preset operating voltage for the inverter, Let be the conversion efficiency of the inverter during the i-th data acquisition. The preset conversion efficiency; Through the above technical solution, this example provides the inverter operating status impact value at the i-th data acquisition time. It can be done through the formula The calculation yields the result, where the formula is... The corrected inverter input power at the i-th data acquisition can be calculated using the formula. The inverter operating voltage fluctuation value from the start of the energy management system's operation on the current day to the i-th data acquisition process can be calculated. Clearly, the lower the corrected inverter input power and inverter conversion efficiency at the i-th data acquisition time, and the higher the inverter operating voltage fluctuation value from the start of the energy management system's operation on the current day to the i-th data acquisition time, and the higher the voltage value at the i-th data acquisition time, the greater the impact of the inverter operating state at the i-th data acquisition time. The higher the value, the greater the impact on the inverter's operating state during the i-th data acquisition. Conversely, the higher the corrected inverter input power and conversion efficiency during the i-th data acquisition, and the lower the inverter operating voltage fluctuation value from the start of the energy management system's operation to the i-th data acquisition, compared to the voltage value at the time of the i-th data acquisition, the lower the impact on the inverter's operating state during the i-th data acquisition. The lower the value, the less the inverter's operating state is affected during the i-th data acquisition. Specifically, the lower the corrected inverter input power and inverter conversion efficiency during the i-th data acquisition, the higher the inverter's operating load. In this case, there will be significant energy loss. Conversely, the higher the inverter operating voltage fluctuation value from the start of the energy management system to the i-th data acquisition process and the higher the voltage value during the i-th data acquisition, the more likely the inverter has a connection fault. This will also increase the inverter's load, increase energy loss, and thus affect power generation efficiency.

[0031] The analysis process in S4 also includes: By influencing the inverter's operating state during the i-th data acquisition The threshold value that affects the preset operating status Perform a comparison; like The system determines that the inverter's operating status is abnormal during the i-th data acquisition and optimization is required. like The system determines that the inverter's operating status is not abnormal during the i-th data acquisition and no optimization work is required. Further analysis is then conducted in conjunction with the energy storage system data. Through the above technical solution, this embodiment uses the inverter operating state influence value during the i-th data acquisition. The threshold value that affects the preset operating status By comparing the data, an accurate judgment can be made as to whether there are any abnormalities in the inverter's operating state during the i-th data acquisition. Furthermore, the operating state of the inverter during the i-th data acquisition has an impact on the value... It is obtained based on diversified data correction and fusion, so the reliability of the data is high. On this basis, the accuracy of the judgment results can be improved, thereby timely detection of inverter operation problems and timely optimization, reducing energy loss and improving power generation efficiency.

[0032] The evaluation process of the data evaluation module includes: Through formula Calculate the performance impact index of the inverter during the i-th data acquisition. ; Where 'a' represents any single charge / discharge operation of the battery in the energy storage system. The total number of battery charge / discharge cycles from the start of the energy management system on the day of its operation to the i-th data acquisition. Let be the internal resistance of the battery in the energy storage system during the a-th charge-discharge operation. Let be the battery capacity degradation rate at the i-th data acquisition. The preset capacity decay rate, The remaining battery power at the time of the i-th data acquisition. The preset remaining battery power. and These are weighting coefficients, set based on empirical fitting. Using the above technical solution, this example provides the performance impact index of the inverter during the i-th data acquisition. It can be done through the formula The calculation yields the result, where the formula is... The internal resistance fluctuation value of the battery during each charge and discharge cycle from the start of the energy management system's operation to the i-th data acquisition can be calculated. Clearly, the larger the internal resistance fluctuation value of the battery during each charge and discharge cycle from the start of the energy management system's operation to the i-th data acquisition, and the higher the battery capacity decay rate and the lower the remaining battery capacity at the i-th data acquisition, the greater the performance impact index of the inverter at the i-th data acquisition. The higher the internal resistance fluctuation value of the battery during each charge and discharge cycle from the start of the energy management system to the first data acquisition, the higher the battery capacity decay rate at the first data acquisition. This indicates a poorer battery health. Furthermore, prolonged use will lead to increased battery heat generation, further reducing charge and discharge efficiency and affecting the overall performance of the inverter. Conversely, the lower the remaining battery charge at the first data acquisition, the lower the upper limit of the inverter's output voltage, resulting in limited maximum output power. Therefore, by combining this calculation method with the battery status data in the energy storage system at the first data acquisition, the performance of the inverter can be further analyzed.

[0033] The decision-making process of the data decision module includes: By exponentially controlling the performance impact of the inverter during the i-th data acquisition Compared with the preset performance impact index threshold Perform a comparison; like The system determines that the inverter's performance has degraded during the i-th data acquisition and decides to perform inverter optimization. Conversely, if If the system determines that the inverter's performance does not significantly decrease during the i-th data acquisition, no inverter optimization operation will be performed. Using the above technical solution, this example demonstrates the impact of inverter performance on the i-th data acquisition. Compared with the preset performance impact index threshold By comparing the data, the system can accurately determine whether the inverter's performance has decreased during the i-th data acquisition. Based on this comparison, since the data is calculated by combining the state data of the batteries in the energy storage system, the data can reflect the inverter's performance under the influence of the external environment. Based on this, the system can promptly identify inverter operation problems and optimize them in a timely manner to ensure good power generation efficiency.

[0034] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A building-integrated energy management system based on edge computing and solar energy storage, characterized in that, The system includes: The data acquisition module is used to collect real-time data on inverter operating status, current sensor operating status, and illumination data in the energy management system through edge computing. The data monitoring module is used to monitor the energy storage system data in the energy management system in real time and to filter and clean the data. The data analysis module is used to analyze the inverter's own operating status by combining real-time collected current sensor data and inverter operating status data. The data evaluation module is used to evaluate the performance of the inverter in real time by combining the analysis results of the inverter's own operating status with the real-time collected data of the energy storage system. The data decision module is used to combine the results of the implementation evaluation of inverter performance to decide whether inverter optimization is needed. The data collected by the data acquisition module includes: Inverter operating status data and current sensor operating status data, wherein the inverter operating status data includes inverter input power, operating voltage and conversion efficiency; The current sensor operating status data includes the current sensor's sampling frequency and calibration deviation value; The data monitoring module monitors energy storage system data including remaining battery power, capacity decay rate, and internal resistance. The analysis process of the data analysis module includes: S1: By combining real-time collected current sensor operating status data and illumination data, the inverter input power impact index is calculated. S2: By comparing the inverter input power influence index with the preset influence index threshold, and judging whether the collected inverter input power is artificially high based on the comparison result; S3: When it is determined that the collected inverter input power is artificially high, analyze the correlation between the inverter input power influence index and the inverter input power. S4: The inverter's input power is corrected by combining the correlation analysis results of the inverter input power influence index and the inverter input power, and the inverter's own operating status is analyzed by combining the inverter's operating status data. The calculation process in S1 includes: Through formula Calculate the inverter input power influence index at the i-th data acquisition time. ; Where i represents a single data collection at a fixed interval. This is the actual sampling frequency of the current sensor. The preset sampling frequency, To define a function, if Then let ,like Then let , This represents the calibration deviation value of the current sensor during the i-th data acquisition. The preset calibration deviation value, This represents the total number of data collections from the start of the energy management system on the day it is used until the i-th data collection. Let be the light intensity during the i-th data acquisition. For all The average value.

2. The building-integrated energy management system based on edge computing for photovoltaics and energy storage as described in claim 1, characterized in that, The analysis process in S2 includes: Influence index by the inverter input power during the i-th data acquisition Compared with the preset impact index threshold Perform a comparison; like The system determines that during the i-th data acquisition, the inverter's input power is affected, which may cause the acquired input power to be artificially high compared to the actual input power. like The system determines that during the i-th data acquisition, the inverter's input power was not affected, and the acquired input power was similar to the actual input power.

3. The building-integrated energy management system based on edge computing for photovoltaics and energy storage as described in claim 2, characterized in that, The analysis process in S3 includes: Through formula Calculate the correlation coefficient between the inverter input power influence index and the inverter input power at the i-th data acquisition time. ; in, The inverter input power during the i-th data acquisition is... For all The average value, For all The average value.

4. The building-integrated energy management system based on edge computing for photovoltaics and energy storage as described in claim 3, characterized in that, The analysis process in S4 includes: Through formula Calculate the influence value of the inverter's operating state at the i-th data acquisition time. ; in, The preset inverter input power, The adjustment coefficient lookup table function has a range of values ​​that are related to... The numerical values ​​correspond one-to-one. The inverter's operating voltage during the i-th data acquisition is... For all The average value, The preset operating voltage for the inverter, Let be the conversion efficiency of the inverter during the i-th data acquisition. This is the preset conversion efficiency.

5. The building-integrated energy management system based on edge computing for photovoltaics and energy storage as described in claim 4, characterized in that, The analysis process in S4 also includes: By influencing the inverter's operating state during the i-th data acquisition The threshold value that affects the preset operating status Perform a comparison; like The system determines that the inverter's operating status is abnormal during the i-th data acquisition and optimization is required. like The system determines that the inverter's operating status is not abnormal during the i-th data acquisition and no optimization work is required. Further analysis is then conducted in conjunction with the energy storage system data.

6. The building-integrated energy management system based on edge computing for photovoltaics and energy storage as described in claim 5, characterized in that, The evaluation process of the data evaluation module includes: Through formula Calculate the performance impact index of the inverter during the i-th data acquisition. ; Where 'a' represents any single charge / discharge operation of the battery in the energy storage system. The total number of battery charge / discharge cycles from the start of the energy management system on the day of its operation to the i-th data acquisition. Let be the internal resistance of the battery in the energy storage system during the a-th charge-discharge operation. For all The average value, Let be the battery capacity degradation rate at the i-th data acquisition. The preset capacity decay rate, The remaining battery power at the time of the i-th data acquisition is... The preset remaining battery power. and These are weighting coefficients, set based on empirical fitting.

7. The building-integrated energy management system based on edge computing for photovoltaics and energy storage as described in claim 6, characterized in that, The decision-making process of the data decision module includes: By exponentially controlling the performance impact of the inverter during the i-th data acquisition Compared with the preset performance impact index threshold Perform a comparison; like The system determines that the inverter's performance has degraded during the i-th data acquisition and decides to perform inverter optimization. Conversely, if If the system determines that the inverter's performance does not significantly decrease during the i-th data acquisition, no inverter optimization operation will be performed.

Images