Micro-grid optimization scheduling method

Abstract

The invention relates to the technical field of power grid dispatching, and discloses a micro-grid optimal dispatching method, which comprises the following steps of: 1, dividing a micro-grid region into a plurality of analysis sub-regions, acquiring power consumption data of each analysis sub-region, and determining an abnormal analysis sub-region according to the power consumption data; 2, historical electricity consumption data of each analysis sub-region in historical data are obtained and evaluated, and analysis sub-regions with large deviation are obtained; according to the method, the power utilization diversity of each analysis sub-region in the micro-grid is analyzed, the historical power utilization data is combined, accurate identification and evaluation of the abnormal analysis sub-region are realized, and then power scheduling is carried out based on the analysis results, so that the diversity of power utilization characteristics in the micro-grid can be effectively handled, and the power utilization efficiency is improved. And the overall operation efficiency and stability of the micro-grid can be improved, dynamic scheduling is carried out, and powerful support is provided for development of the smart grid.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid dispatching, and in particular to a microgrid optimization dispatching method. Background Art

[0002] Micro-Grid, also translated as microgrid, refers to a small power generation and distribution system composed of distributed power sources, energy storage devices, energy conversion devices, loads, monitoring and protection devices, etc. The purpose of microgrid is to realize the flexible and efficient application of distributed power sources and solve the problem of grid connection of a large number of distributed power sources in various forms. The development and extension of microgrid can fully promote the large-scale access of distributed power sources and renewable energy, realize the high-reliability supply of various energy forms to loads, and is an effective way to realize active distribution network, making the transition from traditional power grid to smart grid. However, the power consumption characteristics of each analysis sub-area within the microgrid are different, and there will be a diversity of power consumption patterns. Although we can intuitively identify sub-areas with relatively high or relatively low internal power consumption, there is a lack of in-depth analysis. The supply and demand scheduling strategies implemented based on these intuitive judgment results are also relatively simple and lack flexibility, making it difficult to fully respond to power demand and supply conditions, thereby limiting the overall operation efficiency of the microgrid; In view of this, we propose a microgrid optimal scheduling method. Summary of the invention

[0003] The purpose of the present invention is to provide a microgrid optimization scheduling method to solve the problems in the above background.

[0004] The purpose of the present invention can be achieved through the following technical solutions: A microgrid optimization scheduling method comprises the following steps: step 1: dividing a microgrid area into a plurality of analysis sub-areas, obtaining power consumption data of each analysis sub-area, and determining an abnormal analysis sub-area according to the power consumption data; step 2: obtaining historical power consumption data of each analysis sub-area in historical data, and evaluating to obtain analysis sub-areas with large deviations; step 3: calculating an overlap judgment value based on the abnormal analysis sub-areas and the analysis sub-areas with large deviations generated above, and evaluating the frequency of occurrence of the abnormal analysis sub-areas; step 4: analyzing the abnormal analysis sub-areas based on the result of evaluating the frequency of occurrence of the abnormal analysis sub-areas, and performing power scheduling based on the analysis result.

[0005] As a further solution of the present invention: the acquisition process of the abnormal analysis sub-area: Get the total power consumption deviation value; Compare the total power consumption deviation value with the total power consumption deviation threshold; If the total power consumption deviation value is greater than the total power consumption deviation threshold, it is marked as an abnormal analysis sub-area.

[0006] As a further solution of the present invention: the process of obtaining the total power consumption deviation value is: Preset the analysis cycle, divide the microgrid area into several analysis sub-areas, and obtain the power consumption data of each analysis sub-area; The power consumption of each analysis sub-area within a preset analysis period is summed up to obtain a total power consumption value; The total power consumption values ​​of all analyzed sub-areas are summed up and averaged to obtain the mean power consumption value. The total power consumption values ​​of all analyzed sub-areas are calculated with the mean power consumption value to obtain the absolute value of the difference, which is marked as the total power consumption deviation value.

[0007] As a further solution of the present invention: the acquisition process of the large deviation analysis sub-region is: Get the deviation value of the total historical electricity consumption; Compare the historical total power consumption deviation values ​​with the total power consumption deviation thresholds respectively; If the deviation value of the total historical electricity consumption is greater than the total electricity consumption value deviation threshold, it is marked as a large deviation analysis sub-area.

[0008] As a further solution of the present invention: the process of obtaining the deviation value of the total value of historical power consumption is: Randomly extract multiple analysis periods from historical data; Obtain the historical power consumption data corresponding to each analysis sub-area of ​​the microgrid within a preset period; In each preset period, the power consumption of each analysis sub-area is summed up to obtain the total historical power consumption value; The total historical electricity consumption values ​​of all analyzed sub-areas are summed up and averaged to obtain the historical electricity consumption mean value. The difference between the total historical electricity consumption values ​​of all analyzed sub-areas and the historical electricity consumption mean value is calculated to obtain the absolute value of the difference, which is marked as the historical total electricity consumption deviation value.

[0009] As a further solution of the present invention: the process of evaluating the frequency of occurrence of the abnormal analysis sub-region is as follows: Obtaining a numerical value of the generated synchronization signal, calculating the ratio of the numerical value of the generated synchronization signal to the total number of analysis cycles extracted from the historical data, and obtaining a coincidence judgment value; comparing the coincidence judgment value with the coincidence judgment threshold; If the coincidence judgment value is less than or equal to the coincidence judgment threshold, a low frequency signal is generated; If the coincidence judgment value is greater than the coincidence judgment threshold, a high frequency signal is generated.

[0010] As a further solution of the present invention: the process of generating the synchronization signal is: Get the number of sub-regions marked as abnormal; Obtain the number of identical analysis sub-regions of the marked large deviation analysis region and the marked abnormal sub-region in each analysis period extracted from the historical data, mark them as synchronization number values, perform ratio processing on the synchronization number value and the abnormal sub-region value, and obtain the synchronization number ratio value; Compare the acquired synchronization number ratio values ​​with the synchronization number ratio thresholds respectively; If the synchronization number ratio is greater than or equal to the synchronization number ratio threshold, a synchronization signal is generated.

[0011] As a further solution of the present invention: the process of power dispatching based on the analysis result includes: Obtain the total power consumption deviation value corresponding to the positive sub-area and the total power consumption deviation value corresponding to the negative sub-area; Compare the total value of the deviation of the power consumption corresponding to the positive sub-area with the total value of the deviation of the power consumption corresponding to the negative sub-area; If the total deviation of electricity consumption corresponding to the positive sub-area is greater than the total deviation of electricity consumption corresponding to the negative sub-area, an excess demand signal is generated; If the total value of the power consumption deviation corresponding to the positive sub-area is less than the total value of the power consumption deviation corresponding to the negative sub-area, a demand surplus signal is generated; If the total value of the power consumption deviation corresponding to the positive sub-area is equal to the total value of the power consumption deviation corresponding to the negative sub-area, a demand balance signal is generated; The difference between the total power consumption deviation corresponding to the positive sub-region and the total power consumption deviation corresponding to the negative sub-region is calculated to obtain the regional power dispatch value.

[0012] As a further solution of the present invention: the process of obtaining the total deviation value of the power consumption corresponding to the positive sub-region and the total deviation value of the power consumption corresponding to the negative sub-region is as follows: Obtain the abnormal analysis sub-area, and obtain the real-time total power consumption value and the real-time average power consumption value corresponding to the abnormal analysis sub-area; The analysis sub-regions where the total real-time electricity consumption is higher than the mean total real-time electricity consumption are marked as positive sub-regions, and the analysis sub-regions where the total real-time electricity consumption is lower than the mean total real-time electricity consumption are marked as negative sub-regions; Get the total electricity consumption deviation value corresponding to the abnormal analysis sub-area, sum the total electricity consumption deviation values ​​marked as positive sub-areas to get the total electricity consumption deviation value corresponding to the positive sub-areas, and sum the total electricity consumption deviation values ​​marked as negative sub-areas to get the total electricity consumption deviation value corresponding to the negative sub-areas.

[0013] As a further solution of the present invention: the process of performing power dispatch based on the analysis result also includes: Obtain the abnormal sub-area, and within the analysis period, establish a two-dimensional model with time as the X-axis and power consumption as the Y-axis, substitute the acquired real-time power consumption data into the two-dimensional model, and draw a real-time power consumption curve chart; Two parallel lines parallel to the X-axis are established with the peak power consumption threshold and the valley power consumption threshold as the baselines, namely the peak baseline and the valley baseline; The portion of the electricity consumption curve located above the peak baseline is marked as the peak electricity consumption area, and the portion of the historical electricity consumption curve located below the valley baseline is marked as the valley electricity consumption area; Obtain the time period of the peak power consumption area and mark it as the peak time period; obtain the time period of the valley power consumption area and mark it as the valley time period; Specifically, when performing power dispatch, the power consumption in the valley area is dispatched to the peak time period; Extract the maximum value between the peak time period and the trough time period and mark it as the monitoring time period value.

[0014] Beneficial effects of the present invention: The present invention first determines whether the total power consumption in the analysis sub-area is high or low through the total power consumption of multiple analysis sub-areas in the microgrid area within the analysis period. If so, these analysis sub-areas are marked as abnormal analysis sub-areas. Then, multiple analysis periods are randomly extracted from the historical data to determine whether the abnormal analysis sub-areas marked above also have a high or low total power consumption in the historical data. If so, it means that the abnormal analysis sub-area has a high frequency of occurrence, and the power consumption pattern of the analysis sub-area is the same in most cases. If not, it means that the total power consumption in the analysis sub-area is high or low, which may be caused by some temporary factors, so that the analysis sub-areas in the microgrid area can be analyzed to understand the analysis sub-areas with abnormal power consumption. The present invention analyzes the abnormal analysis sub-area through the acquired high-frequency signal, first analyzes all the abnormal analysis sub-areas in the microgrid area, extracts the analysis sub-areas with higher or lower power consumption, marks the positive sub-areas and the negative sub-areas, calculates the total power consumption of the positive sub-areas and the negative sub-areas, obtains the deviation, judges the scheduling based on the deviation, and analyzes the power consumption of each analysis sub-area in the analysis period, obtains the peak power consumption time period and the valley power consumption time period, and schedules the remaining power in the valley power consumption time period to the peak time period. Based on the above power scheduling within the abnormal sub-area and all the abnormal sub-areas within the microgrid area, mutual scheduling is performed, so that the power process, supply and demand within the microgrid can be balanced to a certain extent, and the use effect of power can be increased through dynamic scheduling. At the same time, the monitoring time period value is calculated as a new analysis period, thereby increasing the monitoring effect of power and the accuracy of scheduling; This method analyzes the power consumption diversity of each analysis sub-area within the microgrid and combines it with historical power consumption data to achieve accurate identification and evaluation of abnormal analysis sub-areas, and then performs power dispatch based on these analysis results. It can not only effectively cope with the diversity of power consumption characteristics within the microgrid, but also improve the overall operating efficiency and stability of the microgrid, perform dynamic dispatch, and provide strong support for the development of smart grids. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention will be further described below in conjunction with the accompanying drawings.

[0016] Figure 1 It is a schematic diagram of a flow chart of a microgrid optimization scheduling method of the present invention; Figure 2 It is a flow chart of step 1 in a microgrid optimization scheduling method of the present invention; Figure 3 It is a schematic diagram of a process for obtaining a coincidence judgment value in a microgrid optimization scheduling method of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example 1

[0018] See also Figure 1 - Figure 3 As shown, the present invention is a microgrid optimization scheduling method, comprising the following steps: Step 1: Divide the microgrid area into several analysis sub-areas, obtain the power consumption data of each analysis sub-area, and determine the abnormal analysis sub-area based on the power consumption data; Exemplarily, a residential area is taken as the analysis object of the microgrid area; In some embodiments, a preset analysis period (the preset analysis period is set to one day) is used to divide the microgrid area into a number of analysis sub-areas, and the power consumption data of each analysis sub-area is obtained; The power consumption of each analysis sub-area within a preset analysis period is summed up to obtain a total power consumption value; The total power consumption of each analysis sub-area obtained in the microgrid area is summed up and averaged to obtain the average power consumption, and the difference between the total power consumption of all analysis sub-areas and the average power consumption is calculated to obtain the absolute value of the difference, which is marked as the total power consumption deviation value; Compare the total power consumption deviation value with the total power consumption deviation threshold value (the total power consumption deviation threshold value is set by technicians in this field based on historical experimental data); If the total power consumption deviation value is less than or equal to the total power consumption deviation threshold, the total power consumption value of the analysis sub-area is less different from the average power consumption value, and is marked as a normal analysis sub-area; If the total power consumption deviation value is greater than the total power consumption deviation threshold, the total power consumption value of the analysis sub-area is significantly different from the average power consumption value, and is marked as an abnormal analysis sub-area; Thus, through the above comparison process, it is possible to identify whether each analysis sub-area in the microgrid area has a high or low total power consumption, and mark these analysis sub-areas for further analysis, thereby facilitating understanding of the power consumption of the corresponding analysis sub-areas; Step 2: Obtain the historical electricity consumption data of each analysis sub-area in the historical data, and evaluate it to obtain the analysis sub-area with large deviation; In some embodiments, a plurality of analysis periods are randomly extracted from the historical data; Obtain the historical power consumption data corresponding to each analysis sub-area of ​​the microgrid within a preset period; In each preset period, the power consumption of each analysis sub-area is summed up to obtain the total historical power consumption value; The total historical electricity consumption values ​​of all analyzed sub-areas are summed up and averaged to obtain the historical electricity consumption mean value. The difference between the total historical electricity consumption values ​​of all analyzed sub-areas and the historical electricity consumption mean value is calculated to obtain the absolute value of the difference, which is marked as the historical total electricity consumption deviation value; Compare the historical total power consumption deviation values ​​with the total power consumption deviation thresholds respectively; If the deviation value of the total value of historical electricity consumption is less than or equal to the total value of electricity consumption deviation threshold, the total value of historical electricity consumption of the analysis sub-area is less different from the historical electricity consumption mean value, and is marked as a small deviation analysis sub-area; If the deviation value of the total value of historical electricity consumption is greater than the total value of electricity consumption deviation threshold, the total value of historical electricity consumption of the analysis sub-area is significantly different from the average value of historical electricity consumption, and is marked as a large deviation analysis sub-area; Step 3: Based on the abnormal analysis sub-region and the large deviation analysis sub-region generated above, the overlap judgment value is calculated to evaluate the frequency of occurrence of the abnormal analysis sub-region; In some embodiments, obtaining a value of the number of sub-regions marked as abnormal; Obtain the number of identical analysis sub-regions of the marked large deviation analysis region and the marked abnormal sub-region in each analysis period extracted from the historical data, mark them as synchronization number values, perform ratio processing on the synchronization number value and the abnormal sub-region value, and obtain the synchronization number ratio value; Compare the obtained synchronization number ratio values ​​with the synchronization number ratio thresholds (the synchronization number ratio thresholds are summarized and set by those skilled in the art based on multiple experimental data); If the synchronous number ratio value is less than the synchronous number ratio threshold value, it means that the overlap between the large deviation analysis sub-region and the abnormal analysis sub-region obtained in the corresponding preset period is low, and an asynchronous signal is generated; If the synchronous number ratio is greater than or equal to the synchronous number ratio threshold, it means that the overlap between the large deviation analysis sub-region and the abnormal analysis sub-region obtained in the corresponding preset period is high, and a synchronous signal is generated; Obtaining a numerical value of the generated synchronization signal, calculating the ratio of the numerical value of the generated synchronization signal to the total number of analysis cycles extracted from the historical data, and obtaining a coincidence judgment value; Compare the overlap judgment value with the overlap judgment threshold (the overlap judgment threshold is set by a person skilled in the art based on historical experimental data); If the coincidence judgment value is less than or equal to the coincidence judgment threshold, a low frequency signal is generated; If the coincidence judgment value is greater than the coincidence judgment threshold, a high frequency signal is generated; It should be explained that: when a low-frequency signal is generated, it means that although power consumption anomalies (i.e., the total power consumption is higher or lower) exist, their frequency of occurrence is relatively low, which may be due to some temporary factors causing the change in power consumption. When a high-frequency signal is generated, it means that the frequency of power consumption anomalies is relatively high, and the sub-area corresponding to the high-frequency signal has power consumption anomalies most of the time. The core technical solution of this embodiment is: first, according to the total electricity consumption of multiple analysis sub-areas in the microgrid area within the analysis period, it is judged whether the total electricity consumption in the sub-area is high or low. If so, these analysis sub-areas are marked as abnormal analysis sub-areas, and then multiple analysis periods are randomly extracted from the historical data to judge whether the abnormal analysis sub-areas marked above also have a high or low total electricity consumption in the historical data. If so, it means that the abnormal analysis sub-area appears frequently, and the electricity consumption pattern of the analysis sub-area is the same in most cases. If not, it means that the analysis sub-area has a high or low total electricity consumption, which may be caused by some temporary factors. This makes it easy to analyze the analysis sub-areas in the microgrid area and determine the analysis sub-areas where abnormal electricity consumption (i.e., high or low total electricity consumption) occurs. Example 2

[0019] Based on the above embodiments, the present invention is a microgrid optimization scheduling method, which also includes the following steps: Step 4: Based on the above-mentioned abnormal frequency high signal, analyze the abnormal analysis sub-area, and perform power dispatch based on the analysis result; In some embodiments, an abnormal analysis sub-region is obtained, and a real-time total power consumption value and a real-time average power consumption value corresponding to the abnormal analysis sub-region are obtained; The analysis sub-regions where the total real-time electricity consumption is higher than the mean total real-time electricity consumption are marked as positive sub-regions, and the analysis sub-regions where the total real-time electricity consumption is lower than the mean total real-time electricity consumption are marked as negative sub-regions; Obtain the total power consumption deviation value corresponding to the abnormal analysis sub-area, sum the total power consumption deviation values ​​marked as positive sub-areas to obtain the total power consumption deviation value corresponding to the positive sub-areas, and sum the total power consumption deviation values ​​marked as negative sub-areas to obtain the total power consumption deviation value corresponding to the negative sub-areas; Compare the total value of the deviation of the power consumption corresponding to the positive sub-area with the total value of the deviation of the power consumption corresponding to the negative sub-area; If the total deviation of the power consumption corresponding to the positive sub-region is greater than the total deviation of the power consumption corresponding to the negative sub-region, it means that there is an excess demand for power consumption in the microgrid area, and an excess demand signal is generated; If the total deviation value of the power consumption corresponding to the positive sub-area is less than the total deviation value of the power consumption corresponding to the negative sub-area, it means that there is a shortage of power consumption in the microgrid area, and a demand surplus signal is generated; If the total value of the power consumption deviation corresponding to the positive sub-area is equal to the total value of the power consumption deviation corresponding to the negative sub-area, a demand balance signal is generated; The difference between the total power consumption deviation corresponding to the positive sub-region and the total power consumption deviation corresponding to the negative sub-region is calculated to obtain the regional power dispatch value; Based on the above process, when the excess demand signal is generated, after the remaining electricity in the negative area is dispatched to the positive sub-area, the positive sub-area still needs to be dispatched. Specifically, the regional electricity dispatch value calculated above is used. When the excess demand signal is generated, the remaining electricity in the negative area is dispatched to the positive sub-area, and then the remaining electricity is stored. It should be noted that, taking the preset analysis period as one day as an example, the scheduling result obtained in the above process is specifically implemented on the next day, that is, the power value of the negative sub-area on the first day is scheduled to the positive sub-area on the second day, thereby increasing the accuracy and timeliness of scheduling; In some embodiments, an abnormal sub-region is obtained, and within an analysis period, a two-dimensional model is established with time as the X-axis and power consumption as the Y-axis, and the obtained real-time power consumption data is substituted into the two-dimensional model to draw a real-time power consumption curve graph; Two parallel lines parallel to the X-axis are established with the peak power consumption threshold and the valley power consumption threshold as the baselines, namely the peak baseline and the valley baseline; Exemplarily, the process of obtaining the peak power consumption threshold and the valley power consumption threshold is as follows: summing and averaging all the acquired power consumption data to obtain the average power consumption value, which is marked as LY. Then the peak power consumption threshold is LY (1+X%), and the valley power consumption threshold is LY (1-X%), where X% is set by those skilled in the art based on their work experience; The portion of the electricity consumption curve located above the peak baseline is marked as the peak electricity consumption area, and the portion of the historical electricity consumption curve located below the valley baseline is marked as the valley electricity consumption area; Obtain the time period of the peak power consumption area and mark it as the peak time period; obtain the time period of the valley power consumption area and mark it as the valley time period; Specifically, when performing power dispatch, for the abnormal sub-area, the power consumption in the valley area is dispatched to the peak time period; Extract the maximum value between the peak time period and the trough time period and mark it as the monitoring time period value; It should be noted that the detection period value is set as a new analysis period, and the power consumption of the abnormal sub-area is monitored with the new analysis period, so as to increase the accuracy of power consumption monitoring and scheduling, and shorten the time of the analysis period, so as to increase the timely scheduling of power consumption; It should be explained that the above calculation and scheduling process is based on an ideal state where the power transmission effect is 100%, and the actual amount of electricity transmitted to the target area is lower than the calculated amount; The core technology of this embodiment is: analyzing the abnormal analysis sub-area through the acquired high-frequency signal, first analyzing all the abnormal analysis sub-areas in the microgrid area, extracting the analysis sub-areas with higher or lower power consumption, marking the positive sub-areas and the negative sub-areas, calculating the total power consumption of the positive sub-areas and the negative sub-areas, obtaining the deviation, judging the scheduling based on the deviation, and analyzing the power consumption of each analysis sub-area in the analysis period, obtaining the peak power consumption time period and the valley power consumption time period, and scheduling the remaining power in the valley power consumption time period to the peak time period, based on the above-mentioned power scheduling within the abnormal sub-area and all the abnormal sub-areas within the microgrid area, mutually scheduling, so as to balance the power process, supply and demand within the microgrid to a certain extent, and increase the power usage effect through dynamic scheduling, and at the same time calculate the monitoring time period value as the new analysis period, thereby increasing the power monitoring effect and scheduling accuracy. Example 3

[0020] Based on the above embodiments, the present invention is a microgrid optimization dispatching system, which specifically includes: Data acquisition and evaluation module: the microgrid area is divided into several analysis sub-areas, the power consumption data of each analysis sub-area is obtained, and the data is evaluated to obtain the abnormal analysis sub-areas; Historical data acquisition and analysis module: obtains historical electricity consumption data of each analysis sub-area in the historical data, evaluates it, and obtains the analysis sub-area with large deviation; Overlap judgment module: based on the abnormal analysis sub-region and large deviation analysis sub-region generated above, calculate the overlap judgment value and evaluate the frequency of occurrence of the abnormal analysis sub-region; If the coincidence judgment value is greater than the coincidence judgment threshold, a high frequency signal is generated, otherwise, a low frequency signal is generated; Scheduling analysis module: Based on the above-mentioned generation of abnormal high frequency signals, analyze the abnormal analysis sub-area and perform power scheduling based on the analysis results.

[0021] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A microgrid optimization scheduling method, characterized in that: The following steps are involved: Step 1: Divide the microgrid area into several analysis sub-areas, obtain the power consumption data of each analysis sub-area, and determine the abnormal analysis sub-area according to the power consumption data; Step 2: Obtain the historical electricity consumption data of each analysis sub-area in the historical data, and evaluate it to obtain the analysis sub-area with large deviation; Step 3: Based on the abnormal analysis sub-region and the large deviation analysis sub-region generated above, the overlap judgment value is calculated to evaluate the frequency of occurrence of the abnormal analysis sub-region; Step 4: Based on the results of evaluating the frequency of occurrence of the abnormal analysis sub-area, analyze the abnormal analysis sub-area and perform power dispatch based on the analysis results.

2. A microgrid optimization scheduling method according to claim 1, characterized in that: The process of obtaining the abnormal analysis sub-area: Get the total power consumption deviation value; Compare the total power consumption deviation value with the total power consumption deviation threshold; If the total power consumption deviation value is greater than the total power consumption deviation threshold, it is marked as an abnormal analysis sub-area.

3. A microgrid optimization scheduling method according to claim 2, characterized in that: The process of obtaining the total power consumption deviation value is as follows: Preset the analysis cycle, divide the microgrid area into several analysis sub-areas, and obtain the power consumption data of each analysis sub-area; The power consumption of each analysis sub-area within a preset analysis period is summed up to obtain a total power consumption value; The total power consumption values ​​of all analyzed sub-areas are summed up and averaged to obtain the mean power consumption value. The total power consumption values ​​of all analyzed sub-areas are calculated with the mean power consumption value to obtain the absolute value of the difference, which is marked as the total power consumption deviation value.

4. A microgrid optimization scheduling method according to claim 1, characterized in that: The process of obtaining the large deviation analysis sub-area is as follows: Get the total deviation value of historical electricity consumption; Compare the historical total power consumption deviation values ​​with the total power consumption deviation thresholds respectively; If the deviation value of the total historical electricity consumption is greater than the total electricity consumption value deviation threshold, it is marked as a large deviation analysis sub-area.

5. A microgrid optimization scheduling method according to claim 4, characterized in that: The process of obtaining the deviation value of the total historical electricity consumption is as follows: Randomly extract multiple analysis periods from historical data; Obtain the historical power consumption data corresponding to each analysis sub-area of ​​the microgrid within a preset period; In each preset period, the power consumption of each analysis sub-area is summed up to obtain the total historical power consumption value; The total historical electricity consumption values ​​of all analyzed sub-areas are summed up and averaged to obtain the historical electricity consumption mean value. The difference between the total historical electricity consumption values ​​of all analyzed sub-areas and the historical electricity consumption mean value is calculated to obtain the absolute value of the difference, which is marked as the historical total electricity consumption deviation value.

6. A microgrid optimization scheduling method according to claim 1, characterized in that: The process of evaluating the frequency of occurrence of the anomaly analysis sub-area is as follows: Obtaining a numerical value of the generated synchronization signal, calculating the ratio of the numerical value of the generated synchronization signal to the total number of analysis cycles extracted from the historical data, and obtaining a coincidence judgment value; comparing the coincidence judgment value with the coincidence judgment threshold; If the coincidence judgment value is less than or equal to the coincidence judgment threshold, a low frequency signal is generated; If the coincidence judgment value is greater than the coincidence judgment threshold, a high frequency signal is generated.

7. A microgrid optimization scheduling method according to claim 6, characterized in that: The process of generating synchronization signal is as follows: Get the number of sub-regions marked as abnormal; Obtain the number of identical analysis sub-regions of the marked large deviation analysis region and the marked abnormal sub-region in each analysis period extracted from the historical data, mark them as synchronization number values, perform ratio processing on the synchronization number value and the abnormal sub-region value, and obtain the synchronization number ratio value; Compare the acquired synchronization number ratio values ​​with the synchronization number ratio thresholds respectively; If the synchronization number ratio is greater than or equal to the synchronization number ratio threshold, a synchronization signal is generated.

8. A microgrid optimization scheduling method according to claim 1, characterized in that: The process of power dispatch based on the analysis results includes: Obtain the total power consumption deviation value corresponding to the positive sub-area and the total power consumption deviation value corresponding to the negative sub-area; Compare the total value of the deviation of the power consumption corresponding to the positive sub-area with the total value of the deviation of the power consumption corresponding to the negative sub-area; If the total deviation of electricity consumption corresponding to the positive sub-area is greater than the total deviation of electricity consumption corresponding to the negative sub-area, an excess demand signal is generated; If the total value of the power consumption deviation corresponding to the positive sub-area is less than the total value of the power consumption deviation corresponding to the negative sub-area, a demand surplus signal is generated; If the total value of the power consumption deviation corresponding to the positive sub-area is equal to the total value of the power consumption deviation corresponding to the negative sub-area, a demand balance signal is generated; The difference between the total power consumption deviation corresponding to the positive sub-region and the total power consumption deviation corresponding to the negative sub-region is calculated to obtain the regional power dispatch value.

9. A microgrid optimization scheduling method according to claim 8, characterized in that: The process of obtaining the total deviation value of power consumption corresponding to the positive sub-area and the total deviation value of power consumption corresponding to the negative sub-area is as follows: Obtain the abnormal analysis sub-area, and obtain the real-time total power consumption value and the real-time average power consumption value corresponding to the abnormal analysis sub-area; The analysis sub-regions where the total real-time electricity consumption is higher than the mean total real-time electricity consumption are marked as positive sub-regions, and the analysis sub-regions where the total real-time electricity consumption is lower than the mean total real-time electricity consumption are marked as negative sub-regions; Get the total electricity consumption deviation value corresponding to the abnormal analysis sub-area, sum the total electricity consumption deviation values ​​marked as positive sub-areas to get the total electricity consumption deviation value corresponding to the positive sub-areas, and sum the total electricity consumption deviation values ​​marked as negative sub-areas to get the total electricity consumption deviation value corresponding to the negative sub-areas.

10. A microgrid optimization scheduling method according to claim 1, characterized in that: The process of power dispatch based on the analysis results also includes: Obtain the abnormal sub-area, and within the analysis period, establish a two-dimensional model with time as the X-axis and power consumption as the Y-axis, substitute the acquired real-time power consumption data into the two-dimensional model, and draw a real-time power consumption curve chart; Two parallel lines parallel to the X-axis are established with the peak power consumption threshold and the valley power consumption threshold as the baselines, namely the peak baseline and the valley baseline; The portion of the electricity consumption curve located above the peak baseline is marked as the peak electricity consumption area, and the portion of the historical electricity consumption curve located below the valley baseline is marked as the valley electricity consumption area; Obtain the time period of the peak power consumption area and mark it as the peak time period; obtain the time period of the valley power consumption area and mark it as the valley time period; Specifically, when performing power dispatch, the power consumption in the valley area is dispatched to the peak time period; Extract the maximum value between the peak time period and the trough time period and mark it as the monitoring time period value.

Images