A microgrid control system based on multi-module collaboration and its optimized scheduling method

Abstract

The present invention discloses a microgrid control system based on multi-module collaboration and an optimized scheduling method thereof, which relates to the technical field of microgrid scheduling. The scheduling method comprises the following steps: collecting data from various control devices in the microgrid and generating corresponding collaboration records; dividing the devices in any collaboration record into control modules and performing abnormality identification; extracting abnormal features of the abnormal control modules; arbitrarily selecting an abnormal feature to obtain the correlation between the selected abnormal feature and the remaining control modules; performing abnormality assessment on each control module based on the correlation of each abnormal feature; collecting the real-time scheduling process of the microgrid, generating real-time collaboration records and extracting abnormal features; performing real-time assessment on each control module and sending abnormality reminders to the control modules with abnormalities; the method can effectively identify the actual abnormal conditions in each control module and reduce the occurrence of misjudgment and missed judgment.

Description

Technical Field

[0001] The present invention relates to the technical field of microgrid scheduling, and in particular to a microgrid control system based on multi-module collaboration and an optimized scheduling method thereof. Background Art

[0002] A microgrid is a localized power system that can operate independently of the main grid. As a key vehicle for distributed energy integration, its control system must coordinate multiple devices, including photovoltaics, energy storage, and loads. Traditional scheduling methods commonly suffer from the following drawbacks:

[0003] Existing technologies are mostly based on the threshold judgment of single device indicators, and do not consider the coupling between devices. For example, when a device monitoring indicator shows an abnormality, due to the lack of analysis of the collaborative transmission path, the root device of the abnormality cannot be located, causing the fault to be transmitted to the entire system; or the status of each device is only evaluated in isolation, and the correlation between different devices is not quantitatively analyzed, resulting in misjudgment and omission of abnormal identification of each device. Summary of the Invention

[0004] The purpose of the present invention is to provide a microgrid control system based on multi-module collaboration and an optimized scheduling method thereof to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a microgrid optimization scheduling method based on multi-module collaboration, the scheduling method comprising the following steps:

[0006] Step S100: Collect data from each control device in each dispatch process of the microgrid and generate corresponding coordination records; analyze the coordination between each control device and divide the device in any coordination record into control modules;

[0007] Step S200: Conduct multi-dimensional analysis on each control module in any collaborative record and identify anomalies in each control module; for any control module, extract the abnormal features of the abnormal control module based on the differences in abnormal identification in different collaborative records;

[0008] Step S300: arbitrarily select an abnormal feature, analyze the coordination between the control module where the abnormal feature is located and the remaining control modules, and obtain the correlation between the abnormal feature and the remaining control modules; for any control module, perform abnormality assessment on each control module based on the correlation between each abnormal feature;

[0009] Step S400: The real-time scheduling process of the microgrid at the current moment is collected, a real-time collaborative record is generated, and abnormal features of each control module are extracted; based on the extracted abnormal features, each control module is evaluated in real time, and abnormal reminders are sent to control modules with abnormalities.

[0010] Furthermore, step S100 includes the following steps:

[0011] Step S101: Each control device in the microgrid is set as a monitoring node. A monitoring device is installed at each monitoring node to collect all data during the scheduling process, obtain the data source device and target scheduling device of any data on any monitoring node, and obtain the transmission route of any data during the scheduling process;

[0012] Step S102: A monitoring node is randomly selected, and a number of monitoring indicators are preset for the data processing process of the control device corresponding to the selected monitoring node. The indicator values ​​corresponding to each monitoring indicator when the corresponding control device processes any data are obtained, and the average value of each monitoring indicator is obtained by taking the average value; the transmission routes of all data in the scheduling process and the monitoring indicator data of each control device are summarized to generate a coordinated record of the scheduling process; the monitoring indicators of each monitoring node include power indicators such as voltage and current, and equipment status indicators such as operating temperature;

[0013] Step S103: Select the i-th control device from any collaborative record, obtain the data source device and target scheduling device of any data in the i-th control device, and count the number of j-th control devices as data source devices of the i-th control device as m (j,i) and the number of target scheduling devices is m (i,j) ; Reselect a k-th control device and obtain the j-th control device as the number of data source devices m (j,k) and the number of target scheduling devices is m (k,j) , according to the formula:

[0014] ;

[0015] Calculate the difference characteristic value S between the i-th control device and the k-th control device (i,k) ; Preset a difference threshold S th , if S (i,k) <S th , then set a group of feature devices for the i-th control device and the k-th control device; to determine whether two control devices can be divided into the same module, it is necessary to determine whether the data processing processes of the two control devices are similar. First, whether the data source and data transmission target are consistent, and second, whether the operating status is similar, for example, whether the changes in the monitoring data of various monitoring indicators are similar;

[0016] Step S104: If the i-th control device and the k-th control device are a group of characteristic devices, the average indicator values ​​of the i-th control device and the k-th control device on each monitoring indicator are obtained respectively, and the average difference between the two control devices on each monitoring indicator is obtained; an expected difference is preset for each monitoring indicator. If the average difference of each monitoring indicator is less than the preset expected difference, the i-th control device and the k-th control device are divided into the same control module; all control devices in the microgrid are divided to obtain several control modules of the microgrid.

[0017] Furthermore, step S200 includes the following steps:

[0018] Step S201: arbitrarily select a collaboration record and arbitrarily select a control module from the selected collaboration record to obtain a number of control devices included in the selected control module; extract each monitoring indicator of the number of control devices and set it as a dimension of the selected control module;

[0019] Step S202: arbitrarily select a dimension, obtain the indicator data of the corresponding monitoring indicator under the selected dimension, use the time point as the horizontal coordinate and the indicator data as the vertical coordinate, establish a two-dimensional rectangular coordinate system to present the changes of each monitoring indicator; set the i-th monitoring indicator, preset an expected value range for the i-th monitoring indicator, set the time point when the indicator data is not within the expected value range as the abnormal time point, obtain each abnormal time point of the i-th monitoring indicator, if there are several abnormal time points that are adjacent and continuous, then an abnormal time interval is obtained, if the time length of the abnormal time interval exceeds the preset abnormal interval length, or the number of abnormal time points exceeds the preset number threshold, then the i-th monitoring indicator is set as an abnormal indicator; setting two judgment methods is to avoid regular fluctuations in the operation of the equipment, so that the identification of abnormal indicators can be more accurate;

[0020] Step S203: Obtain each abnormal indicator in the selected control module, obtain the control device where each abnormal indicator is located, assign each abnormal indicator to the corresponding control device, count the number of abnormal indicators contained in each control device, and set the number of abnormal indicators of the i-th control device to n i , the abnormal index ratio of the i-th control device is η i =n i / b i , where b i For the number of monitoring indicators of the i-th control device, an abnormal proportion threshold η is preset th , if η i ≥η th , then the selected control module is set as the abnormal control module;

[0021] Step S204: arbitrarily select a control module, set the collaborative record of the selected control module as the abnormal control module as the abnormal target record, and the remaining collaborative records as normal target records; arbitrarily extract one abnormal target record and one normal target record, obtain several abnormal indicators of the abnormal target record and several abnormal indicators of the normal target record, compare the abnormal indicators of the two target records, if the abnormal indicator in the normal target record is the same as the abnormal indicator of the abnormal target record, set the compared abnormal indicator as the first abnormal indicator, and set the remaining abnormal indicators in the abnormal target record as the second abnormal indicator; the first abnormal indicator represents a non-essential indicator that causes the device to be abnormal, and the abnormal situation may be caused by the abnormality of the previous device, while the second abnormal indicator represents a necessary indicator, which has nothing to do with the other devices. If there is an abnormality, it is caused by the device itself;

[0022] Step S205: Divide each monitoring indicator in the selected control module into a first abnormal indicator set and a second abnormal indicator set, record each abnormal indicator in the first abnormal indicator set as an abnormal feature of the selected control module, and obtain the abnormal feature set of the selected control module.

[0023] Furthermore, step S300 includes the following steps:

[0024] Step S301: arbitrarily select an abnormal feature from the abnormal feature set of any control module, obtain the control device where the selected abnormal feature is located, and set it as the target control device; obtain the transmission route of any data in the scheduling process, obtain several transmission routes including the target control device, obtain the control device adjacent to the target control device and located after the target control device in any transmission route, obtain the control module where the obtained control device is located, and set it as the target control module;

[0025] Step S302: Acquire several target control modules of the target control device to obtain a target control module set for selecting abnormal features; arbitrarily select a target control module from the target control module set, count the amount of data transmitted from the target control device to the target control module as D, arbitrarily select a data, obtain several abnormal time intervals of the selected data in the target control module, and obtain the total abnormal time length of the selected data as t ex , set the total processing time of the selected data in the target control module to t, and calculate the abnormal proportion of the selected data in the target control module to be τ=t ex / t; the abnormal proportion of the selected data in the target control device is τ ’ , calculate the correlation degree G=1-|τ between the selected data and the target control device and the target control module ’ -τ| / τ’ The correlation between the two devices is reflected by the change in the abnormal proportion of data between the two devices. The smaller the change in the abnormal proportion, the higher the correlation between the two devices.

[0026] Step S303: Set the correlation degree of the cth data in the target control device to G c , according to the formula:

[0027] ;

[0028] Calculate the comprehensive correlation G between the target control device and the target control module ave ; Get the second abnormality indicator number contained in the target control device as p2, and get the correlation value between any abnormal feature and the target control module as Z=G ave / (1+p2); Since the first abnormal indicator reflects a non-essential indicator, considering all first abnormal indicators as a whole and equally dividing the comprehensive correlation with all second abnormal indicators can obtain a more accurate correlation distribution ratio;

[0029] Step S304: Obtain the correlation value between each abnormal feature in any control module and the remaining control modules, arbitrarily select a control module in a collaborative record, obtain each abnormal indicator of any control device in the selected control module, and obtain the deviation amplitude of each abnormal indicator at each time point, calculate the average deviation amplitude of any abnormal indicator, and accumulate the average deviation amplitudes of all abnormal indicators to obtain a comprehensive deviation value of the selected control module;

[0030] Step S305: Obtain the data transmission order between each control device according to the data transmission route of each data, identify the order of each control module, and obtain a control module sequence; obtain the previous control module that is adjacent to the selected control module and is before the selected control module from the control module sequence; extract all abnormal features from the previous control module, assume that there are u abnormal features in the previous control module, and obtain the correlation value between the e-th abnormal feature and the selected control module as Z e ; Set the average deviation of the e-th abnormal feature in the selected collaborative records to f e , according to the formula:

[0031] ;

[0032] Among them, Q comThe comprehensive deviation value of the selected control module is calculated; the abnormal evaluation value Q of the selected control is obtained; a preliminary evaluation is first performed based on the abnormal situation of the control module itself, and then the preliminary evaluation value is corrected based on the impact of the abnormal characteristics of the previous control module on the control module to obtain a more accurate abnormal evaluation value;

[0033] Step S306: Obtain the abnormality evaluation value of each operation module in each collaborative record, summarize the abnormality evaluation values ​​of each abnormal operation module, and select the abnormality evaluation value with the smallest value among all abnormal operation modules as the abnormality evaluation threshold Q for determining whether the operation module is abnormal. th .

[0034] Furthermore, step S400 includes the following steps:

[0035] Step S401: Acquire monitoring data of each control device during the current scheduling process of the microgrid to obtain a real-time coordination record, divide each control device in the real-time coordination record into a number of control modules, and extract each abnormal monitoring indicator in any control module to obtain a number of abnormal features of any control module;

[0036] Step S402: sort the transmission order of each control module in the real-time collaborative record, arbitrarily select two adjacent control modules, extract any abnormal feature from the previous control module, and obtain the correlation value between the extracted abnormal feature and the next control module; obtain the average deviation amplitude of each abnormal monitoring indicator in the next control module, accumulate them to obtain the real-time deviation value of the next control module in the real-time collaborative record, and correct the real-time deviation value of the next control module according to the correlation value of each abnormal feature in the previous control module to obtain the real-time abnormal evaluation value Q of the next control module. now ; Set the abnormal evaluation threshold to Q th , if Q now >Q th , then the latter control module is set as an abnormal control module and an abnormal reminder is sent.

[0037] In order to better implement the above method, a microgrid control system is also proposed. The control system includes a collaborative recording and analysis module, a module abnormality identification module, a module collaborative evaluation module and a real-time abnormality analysis module;

[0038] The collaborative record analysis module is used to collect data from each control device in each dispatch process of the microgrid and generate corresponding collaborative records; analyze the collaboration between each control device and divide the devices in any collaborative record into control modules;

[0039] The module anomaly identification module is used to analyze the coordination between different control modules based on the coordination between various control devices in any coordination record, and identify anomalies in each control module; for any control module, based on the anomaly identification differences in different coordination records, the abnormal features of the abnormal control module are extracted;

[0040] The module collaboration evaluation module is used to arbitrarily select an abnormal feature, analyze the collaboration between the control module where the selected abnormal feature is located and the remaining control modules, and obtain the correlation between the selected abnormal feature and the remaining control modules; for any control module, an abnormality evaluation is performed on each control module based on the correlation between each abnormal feature;

[0041] The real-time anomaly analysis module is used to collect the real-time scheduling process of the microgrid at the current moment, generate real-time collaborative records and extract the abnormal features of each control module; based on the extracted abnormal features, each control module is evaluated in real time and abnormal reminders are sent to the control modules with abnormalities.

[0042] Furthermore, the collaborative record analysis module includes a collaborative record acquisition unit and a control module division unit;

[0043] The collaborative record collection unit is used to collect data from each control device in each scheduling process of the microgrid and generate corresponding collaborative records; the control module division unit is used to analyze the collaborative situation between each control device and divide the control module of the device in any collaborative record.

[0044] Furthermore, the module anomaly identification module includes an abnormal module screening unit and a module feature extraction unit;

[0045] The abnormal module screening unit is used to analyze the coordination between different control modules based on the coordination between various control devices in any coordination record, and to identify abnormalities in each control module; the module feature extraction unit is used to extract abnormal features of abnormal control modules for any control module based on the abnormal identification differences in different coordination records.

[0046] Furthermore, the module collaborative evaluation module includes a feature module association unit and a module evaluation and analysis unit;

[0047] The feature module association unit is used to arbitrarily select an abnormal feature, analyze the coordination between the control module where the selected abnormal feature is located and the remaining control modules, and obtain the association between the selected abnormal feature and the remaining control modules; the module evaluation and analysis unit is used to perform abnormal evaluation on each control module based on the association of each abnormal feature for any control module.

[0048] Furthermore, the real-time anomaly analysis module includes a real-time collaborative analysis unit and a collaborative anomaly judgment unit;

[0049] The real-time collaborative analysis unit is used to collect the real-time scheduling process of the microgrid at the current moment, generate real-time collaborative records and extract abnormal features of each control module; the collaborative abnormality judgment unit is used to perform real-time evaluation of each control module based on the extracted abnormal features and send abnormality reminders to the control modules with abnormalities.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] 1. This invention quantifies the data features and monitoring indicators between different devices, divides and merges devices with similar functions into several control modules, and analyzes the coupling between different devices, fundamentally solving the problem of single-point detection and effectively improving the accuracy of anomaly positioning;

[0052] 2. The present invention analyzes the correlation between abnormal features and downstream modules, and comprehensively analyzes the abnormal transmission between different control modules based on the correlation between the two, providing data support for collaborative optimization;

[0053] 3. The present invention uses historical collaborative records to generate abnormal assessment thresholds, and corrects the current module evaluation results through the abnormal feature association values ​​of the previous module in real-time scheduling. It can effectively identify the actual abnormal conditions in each control module and reduce the occurrence of misjudgments and missed judgments. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic diagram of the steps of a microgrid optimization scheduling method based on multi-module collaboration;

[0055] Figure 2 This is a structural diagram of a microgrid control system based on multi-module collaboration. DETAILED DESCRIPTION

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0057] Example: Figures 1 to 2 As shown, the present invention provides a microgrid optimization scheduling method based on multi-module collaboration, and the scheduling method includes the following steps:

[0058] Step S100: Collect data from each control device in each dispatch process of the microgrid and generate corresponding coordination records; analyze the coordination between each control device and divide the device in any coordination record into control modules;

[0059] Wherein, step S100 includes the following steps:

[0060] Step S101: Each control device in the microgrid is set as a monitoring node. A monitoring device is installed at each monitoring node to collect all data during the scheduling process, obtain the data source device and target scheduling device of any data on any monitoring node, and obtain the transmission route of any data during the scheduling process;

[0061] Step S102: A monitoring node is randomly selected, and a number of monitoring indicators are preset for the data processing process of the control device corresponding to the selected monitoring node. The indicator values ​​corresponding to the monitoring indicators when the corresponding control device processes any data are obtained, and the average values ​​of the monitoring indicators are taken to obtain the average indicator values ​​of the monitoring indicators. The transmission routes of all data in the scheduling process and the monitoring indicator data of each control device are summarized to generate a coordinated record of the scheduling process.

[0062] Step S103: Select the i-th control device from any collaborative record, obtain the data source device and target scheduling device of any data in the i-th control device, and count the number of j-th control devices as data source devices of the i-th control device as m (j,i) and the number of target scheduling devices is m (i,j) ; Reselect a k-th control device and obtain the j-th control device as the number of data source devices m (j,k) and the number of target scheduling devices is m (k,j) , according to the formula:

[0063] ;

[0064] Calculate the difference characteristic value S between the i-th control device and the k-th control device (i,k) ; Preset a difference threshold S th , if S (i,k) <S th , then set a set of characteristic devices for the i-th control device and the k-th control device;

[0065] Example 1: Randomly select a control device cd1 and a control device cd2, and count the number of cd2 as the data source device of cd1 as 10, and the number of cd2 as the target scheduling device of cd1 as 2; similarly, select a control device cd3, and count the number of cd2 as the data source device of cd3 as 10, and the number of cd2 as the target scheduling device of cd1 as 3. The difference characteristic value between cd1 and cd2 is calculated to be S=1 / 20+1 / 5=0.05+0.2=0.25, and set the difference threshold S th =0.5, because 0.25<0.5, so cd1 and cd3 are a set of characteristic devices;

[0066] Step S104: If the i-th control device and the k-th control device are a group of characteristic devices, the average indicator values ​​of the i-th control device and the k-th control device on each monitoring indicator are obtained respectively, and the average difference between the two control devices on each monitoring indicator is obtained; an expected difference is preset for each monitoring indicator. If the average difference of each monitoring indicator is less than the preset expected difference, the i-th control device and the k-th control device are divided into the same control module; all control devices in the microgrid are divided to obtain several control modules of the microgrid.

[0067] Step S200: Conduct multi-dimensional analysis on each control module in any collaborative record and identify anomalies in each control module; for any control module, extract the abnormal features of the abnormal control module based on the differences in abnormal identification in different collaborative records;

[0068] Wherein, step S200 includes the following steps:

[0069] Step S201: arbitrarily select a collaboration record and arbitrarily select a control module from the selected collaboration record to obtain a number of control devices included in the selected control module; extract each monitoring indicator of the number of control devices and set it as a dimension of the selected control module;

[0070] Step S202: arbitrarily select a dimension, obtain the indicator data of the corresponding monitoring indicator under the selected dimension, use the time point as the horizontal coordinate and the indicator data as the vertical coordinate, establish a two-dimensional rectangular coordinate system to present the changes of each monitoring indicator; set the i-th monitoring indicator, preset an expected value range for the i-th monitoring indicator, set the time point when the indicator data is not within the expected value range as the abnormal time point, obtain each abnormal time point of the i-th monitoring indicator, if there are several abnormal time points that are adjacent and continuous, then obtain an abnormal time interval, if the time length of the abnormal time interval exceeds the preset abnormal interval length, or the number of abnormal time points exceeds the preset number threshold, then the i-th monitoring indicator is set as an abnormal indicator;

[0071] Step S203: Obtain each abnormal indicator in the selected control module, obtain the control device where each abnormal indicator is located, assign each abnormal indicator to the corresponding control device, count the number of abnormal indicators contained in each control device, and set the number of abnormal indicators of the i-th control device to n i , the abnormal index ratio of the i-th control device is η i =n i / b i , where b i For the number of monitoring indicators of the i-th control device, an abnormal proportion threshold η is preset th , if η i ≥η th , then the selected control module is set as the abnormal control module;

[0072] Step S204: arbitrarily select a control module, set the collaborative record of the selected control module as the abnormal control module as the abnormal target record, and set the remaining collaborative records as normal target records; arbitrarily extract one abnormal target record and one normal target record, obtain several abnormal indicators of the abnormal target record and several abnormal indicators of the normal target record, compare the abnormal indicators of the two target records, and if an abnormal indicator in the normal target record is the same as the abnormal indicator of the abnormal target record, set the compared abnormal indicator as the first abnormal indicator, and set the remaining abnormal indicators in the abnormal target record as the second abnormal indicator;

[0073] Step S205: Divide each monitoring indicator in the selected control module into a first abnormal indicator set and a second abnormal indicator set, record each abnormal indicator in the first abnormal indicator set as an abnormal feature of the selected control module, and obtain the abnormal feature set of the selected control module.

[0074] Step S300: arbitrarily select an abnormal feature, analyze the coordination between the control module where the abnormal feature is located and the remaining control modules, and obtain the correlation between the abnormal feature and the remaining control modules; for any control module, perform abnormality assessment on each control module based on the correlation between each abnormal feature;

[0075] Wherein, step S300 includes the following steps:

[0076] Step S301: arbitrarily select an abnormal feature from the abnormal feature set of any control module, obtain the control device where the selected abnormal feature is located, and set it as the target control device; obtain the transmission route of any data in the scheduling process, obtain several transmission routes including the target control device, obtain the control device adjacent to the target control device and located after the target control device in any transmission route, obtain the control module where the obtained control device is located, and set it as the target control module;

[0077] Step S302: Acquire several target control modules of the target control device to obtain a target control module set for selecting abnormal features; arbitrarily select a target control module from the target control module set, count the amount of data transmitted from the target control device to the target control module as D, arbitrarily select a data, obtain several abnormal time intervals of the selected data in the target control module, and obtain the total abnormal time length of the selected data as t ex , set the total processing time of the selected data in the target control module to t, and calculate the abnormal proportion of the selected data in the target control module to be τ=t ex / t; the abnormal proportion of the selected data in the target control device is τ ’ , calculate the correlation degree G=1-|τ between the selected data and the target control device and the target control module ’ -τ| / τ ’ ;

[0078] Step S303: Set the correlation degree of the cth data in the target control device to G c , according to the formula:

[0079] ;

[0080] Calculate the comprehensive correlation G between the target control device and the target control module ave ; Get the second abnormality indicator number contained in the target control device as p2, and get the correlation value between any abnormal feature and the target control module as Z=G ave / (1+p2);

[0081] Example 2: Setting and calculating the comprehensive correlation G between a control device and a control module ave =0.5, assuming that the control device contains 3 first abnormality indicators and 4 second abnormality indicators, the 3 first abnormality indicators are taken as a whole, which is equivalent to 1 second abnormality indicator, which is equivalent to evenly dividing the comprehensive correlation degree by 5 second abnormality indicators, and the correlation value of each second abnormality indicator is 0.5 / 5=0.1;

[0082] Step S304: Obtain the correlation value between each abnormal feature in any control module and the remaining control modules, arbitrarily select a control module in a collaborative record, obtain each abnormal indicator of any control device in the selected control module, and obtain the deviation amplitude of each abnormal indicator at each time point, calculate the average deviation amplitude of any abnormal indicator, and accumulate the average deviation amplitudes of all abnormal indicators to obtain a comprehensive deviation value of the selected control module;

[0083] Step S305: Obtain the data transmission order between each control device according to the data transmission route of each data, identify the order of each control module, and obtain a control module sequence; obtain the previous control module that is adjacent to the selected control module and is before the selected control module from the control module sequence; extract all abnormal features from the previous control module, assume that there are u abnormal features in the previous control module, and obtain the correlation value between the e-th abnormal feature and the selected control module as Z e ; Set the average deviation of the e-th abnormal feature in the selected collaborative records to f e , according to the formula:

[0084] ;

[0085] Among them, Q com is the comprehensive deviation value of the selected control module; the abnormal evaluation value Q of the selected control is calculated;

[0086] Step S306: Obtain the abnormality evaluation value of each operation module in each collaborative record, summarize the abnormality evaluation values ​​of each abnormal operation module, and select the abnormality evaluation value with the smallest value among all abnormal operation modules as the abnormality evaluation threshold Q for determining whether the operation module is abnormal. th .

[0087] Step S400: The real-time scheduling process of the microgrid at the current moment is collected, a real-time collaborative record is generated, and abnormal features of each control module are extracted; based on the extracted abnormal features, each control module is evaluated in real time, and abnormal reminders are sent to control modules with abnormalities;

[0088] Step S400 includes the following steps:

[0089] Step S401: Acquire monitoring data of each control device during the current scheduling process of the microgrid to obtain a real-time coordination record, divide each control device in the real-time coordination record into a number of control modules, and extract each abnormal monitoring indicator in any control module to obtain a number of abnormal features of any control module;

[0090] Step S402: sort the transmission order of each control module in the real-time collaborative record, arbitrarily select two adjacent control modules, extract any abnormal feature from the previous control module, and obtain the correlation value between the extracted abnormal feature and the next control module; obtain the average deviation amplitude of each abnormal monitoring indicator in the next control module, accumulate them to obtain the real-time deviation value of the next control module in the real-time collaborative record, and correct the real-time deviation value of the next control module according to the correlation value of each abnormal feature in the previous control module to obtain the real-time abnormal evaluation value Q of the next control module. now ; Set the abnormal evaluation threshold to Q th , if Q now >Q th , then the latter control module is set as an abnormal control module and an abnormal reminder is sent.

[0091] A microgrid control system includes a collaborative recording and analysis module, a module anomaly identification module, a module collaborative evaluation module and a real-time anomaly analysis module;

[0092] The collaborative record analysis module is used to collect data from each control device in each dispatch process of the microgrid and generate corresponding collaborative records; analyze the collaboration between each control device and divide the devices in any collaborative record into control modules;

[0093] The module anomaly identification module is used to analyze the coordination between different control modules based on the coordination between various control devices in any coordination record, and identify anomalies in each control module; for any control module, based on the anomaly identification differences in different coordination records, the abnormal features of the abnormal control module are extracted;

[0094] The module collaboration evaluation module is used to arbitrarily select an abnormal feature, analyze the collaboration between the control module where the selected abnormal feature is located and the remaining control modules, and obtain the correlation between the selected abnormal feature and the remaining control modules; for any control module, an abnormality evaluation is performed on each control module based on the correlation between each abnormal feature;

[0095] The real-time anomaly analysis module is used to collect the real-time scheduling process of the microgrid at the current moment, generate real-time collaborative records and extract the abnormal features of each control module; based on the extracted abnormal features, each control module is evaluated in real time and abnormal reminders are sent to the control modules with abnormalities.

[0096] Among them, the collaborative record analysis module includes a collaborative record acquisition unit and a control module division unit;

[0097] The collaborative record collection unit is used to collect data from each control device in each scheduling process of the microgrid and generate corresponding collaborative records; the control module division unit is used to analyze the collaborative situation between each control device and divide the control module of the device in any collaborative record.

[0098] Among them, the module abnormality identification module includes an abnormal module screening unit and a module feature extraction unit;

[0099] The abnormal module screening unit is used to analyze the coordination between different control modules based on the coordination between various control devices in any coordination record, and to identify abnormalities in each control module; the module feature extraction unit is used to extract abnormal features of abnormal control modules for any control module based on the abnormal identification differences in different coordination records.

[0100] Among them, the module collaborative evaluation module includes a feature module association unit and a module evaluation and analysis unit;

[0101] The feature module association unit is used to arbitrarily select an abnormal feature, analyze the coordination between the control module where the selected abnormal feature is located and the remaining control modules, and obtain the association between the selected abnormal feature and the remaining control modules; the module evaluation and analysis unit is used to perform abnormal evaluation on each control module based on the association of each abnormal feature for any control module.

[0102] Among them, the real-time anomaly analysis module includes a real-time collaborative analysis unit and a collaborative anomaly judgment unit;

[0103] The real-time collaborative analysis unit is used to collect the real-time scheduling process of the microgrid at the current moment, generate real-time collaborative records and extract abnormal features of each control module; the collaborative abnormality judgment unit is used to perform real-time evaluation of each control module based on the extracted abnormal features and send abnormality reminders to the control modules with abnormalities.

[0104] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A microgrid optimization scheduling method based on multi-module collaboration, characterized by: The scheduling method comprises the following steps: Step S100: Collect data from each control device in each dispatch process of the microgrid and generate corresponding coordination records; analyze the coordination between each control device and divide the device in any coordination record into control modules; Step S200: Conduct multi-dimensional analysis on each control module in any collaborative record and identify anomalies in each control module; for any control module, extract the abnormal features of the abnormal control module based on the differences in abnormal identification in different collaborative records; Step S300: arbitrarily select an abnormal feature, analyze the coordination between the control module where the abnormal feature is located and the remaining control modules, and obtain the correlation between the abnormal feature and the remaining control modules; for any control module, perform abnormality assessment on each control module based on the correlation between each abnormal feature; Step S400: The real-time scheduling process of the microgrid at the current moment is collected, a real-time collaborative record is generated, and abnormal features of each control module are extracted; based on the extracted abnormal features, each control module is evaluated in real time, and abnormal reminders are sent to control modules with abnormalities.

2. A microgrid optimization scheduling method based on multi-module collaboration according to claim 1, characterized in that: The step S100 includes the following steps: Step S101: Each control device in the microgrid is set as a monitoring node. A monitoring device is installed at each monitoring node to collect all data during the scheduling process, obtain the data source device and target scheduling device of any data on any monitoring node, and obtain the transmission route of any data during the scheduling process; Step S102: A monitoring node is randomly selected, and a number of monitoring indicators are preset for the data processing process of the control device corresponding to the selected monitoring node. The indicator values ​​corresponding to the monitoring indicators when the corresponding control device processes any data are obtained, and the average values ​​of the monitoring indicators are taken to obtain the average indicator values ​​of the monitoring indicators. The transmission routes of all data in the scheduling process and the monitoring indicator data of each control device are summarized to generate a coordinated record of the scheduling process. Step S103: Select the i-th control device from any collaborative record, obtain the data source device and target scheduling device of any data in the i-th control device, and count the number of j-th control devices as data source devices of the i-th control device as m (j,i) and the number of target scheduling devices is m (i,j) ; Reselect a k-th control device and obtain the j-th control device as the number of data source devices m (j,k) and the number of target scheduling devices is m (k,j) , according to the formula: ； Calculate the difference characteristic value S between the i-th control device and the k-th control device (i,k) ; Preset a difference threshold S th , if S (i,k) <S th , then set a set of characteristic devices for the i-th control device and the k-th control device; Step S104: If the i-th control device and the k-th control device are a group of characteristic devices, the average indicator values ​​of the i-th control device and the k-th control device on each monitoring indicator are obtained respectively, and the average difference between the two control devices on each monitoring indicator is obtained; an expected difference is preset for each monitoring indicator. If the average difference of each monitoring indicator is less than the preset expected difference, the i-th control device and the k-th control device are divided into the same control module; all control devices in the microgrid are divided to obtain several control modules of the microgrid.

3. The microgrid optimization scheduling method based on multi-module collaboration according to claim 2 is characterized in that: The step S200 includes the following steps: Step S201: arbitrarily select a collaboration record and arbitrarily select a control module from the selected collaboration record to obtain a number of control devices included in the selected control module; extract each monitoring indicator of the number of control devices and set it as a dimension of the selected control module; Step S202: arbitrarily select a dimension, obtain the indicator data of the corresponding monitoring indicator under the selected dimension, use the time point as the horizontal coordinate and the indicator data as the vertical coordinate, establish a two-dimensional rectangular coordinate system to present the changes of each monitoring indicator; set the i-th monitoring indicator, preset an expected value range for the i-th monitoring indicator, set the time point when the indicator data is not within the expected value range as the abnormal time point, obtain each abnormal time point of the i-th monitoring indicator, if there are several abnormal time points that are adjacent and continuous, then obtain an abnormal time interval, if the time length of the abnormal time interval exceeds the preset abnormal interval length, or the number of abnormal time points exceeds the preset number threshold, then the i-th monitoring indicator is set as an abnormal indicator; Step S203: Obtain each abnormal indicator in the selected control module, obtain the control device where each abnormal indicator is located, assign each abnormal indicator to the corresponding control device, count the number of abnormal indicators contained in each control device, and set the number of abnormal indicators of the i-th control device to n i , the abnormal index ratio of the i-th control device is η i =n i / b i , where b i For the number of monitoring indicators of the i-th control device, an abnormal proportion threshold η is preset th , if η i ≥η th , then the selected control module is set as the abnormal control module; Step S204: arbitrarily select a control module, set the collaborative record of the selected control module as the abnormal control module as the abnormal target record, and set the remaining collaborative records as normal target records; arbitrarily extract one abnormal target record and one normal target record, obtain several abnormal indicators of the abnormal target record and several abnormal indicators of the normal target record, compare the abnormal indicators of the two target records, and if an abnormal indicator in the normal target record is the same as the abnormal indicator of the abnormal target record, set the compared abnormal indicator as the first abnormal indicator, and set the remaining abnormal indicators in the abnormal target record as the second abnormal indicator; Step S205: Divide each monitoring indicator in the selected control module into a first abnormal indicator set and a second abnormal indicator set, record each abnormal indicator in the first abnormal indicator set as an abnormal feature of the selected control module, and obtain the abnormal feature set of the selected control module.

4. The microgrid optimization scheduling method based on multi-module collaboration according to claim 3 is characterized by: The step S300 includes the following steps: Step S301: arbitrarily select an abnormal feature from the abnormal feature set of any control module, obtain the control device where the selected abnormal feature is located, and set it as the target control device; obtain the transmission route of any data in the scheduling process, obtain several transmission routes including the target control device, obtain the control device adjacent to the target control device and located after the target control device in any transmission route, obtain the control module where the obtained control device is located, and set it as the target control module; Step S302: Acquire several target control modules of the target control device to obtain a target control module set for selecting abnormal features; arbitrarily select a target control module from the target control module set, count the amount of data transmitted from the target control device to the target control module as D, arbitrarily select a data, obtain several abnormal time intervals of the selected data in the target control module, and obtain the total abnormal time length of the selected data as t ex , set the total processing time of the selected data in the target control module to t, and calculate the abnormal proportion of the selected data in the target control module to be τ=t ex / t; the abnormal proportion of the selected data in the target control device is τ ’ , calculate the correlation degree G=1-|τ between the selected data and the target control device and the target control module ’ -τ| / τ ’ ; Step S303: Set the correlation degree of the cth data in the target control device to G c , according to the formula: ； Calculate the comprehensive correlation G between the target control device and the target control module ave ; Get the second abnormality indicator number contained in the target control device as p2, and get the correlation value between any abnormal feature and the target control module as Z=G ave / (1+p2); Step S304: Obtain the correlation value between each abnormal feature in any control module and the remaining control modules, arbitrarily select a control module in a collaborative record, obtain each abnormal indicator of any control device in the selected control module, and obtain the deviation amplitude of each abnormal indicator at each time point, calculate the average deviation amplitude of any abnormal indicator, and accumulate the average deviation amplitudes of all abnormal indicators to obtain a comprehensive deviation value of the selected control module; Step S305: Obtain the data transmission order between each control device according to the data transmission route of each data, identify the order of each control module, and obtain a control module sequence; obtain the previous control module that is adjacent to the selected control module and is before the selected control module from the control module sequence; extract all abnormal features from the previous control module, assume that there are u abnormal features in the previous control module, and obtain the correlation value between the e-th abnormal feature and the selected control module as Z e ; Set the average deviation of the e-th abnormal feature in the selected collaborative records to f e , according to the formula: ； Among them, Q com is the comprehensive deviation value of the selected control module; the abnormal evaluation value Q of the selected control is calculated; Step S306: Obtain the abnormality evaluation value of each operation module in each collaborative record, summarize the abnormality evaluation values ​​of each abnormal operation module, and select the abnormality evaluation value with the smallest value among all abnormal operation modules as the abnormality evaluation threshold Q for determining whether the operation module is abnormal. th .

5. The microgrid optimization scheduling method based on multi-module collaboration according to claim 4 is characterized in that: The step S400 includes the following steps: Step S401: Acquire monitoring data of each control device during the current scheduling process of the microgrid to obtain a real-time coordination record, divide each control device in the real-time coordination record into a number of control modules, and extract each abnormal monitoring indicator in any control module to obtain a number of abnormal features of any control module; Step S402: sort the transmission order of each control module in the real-time collaborative record, arbitrarily select two adjacent control modules, extract any abnormal feature from the previous control module, and obtain the correlation value between the extracted abnormal feature and the next control module; obtain the average deviation amplitude of each abnormal monitoring indicator in the next control module, accumulate them to obtain the real-time deviation value of the next control module in the real-time collaborative record, and correct the real-time deviation value of the next control module according to the correlation value of each abnormal feature in the previous control module to obtain the real-time abnormal evaluation value Q of the next control module. now ; Set the abnormal evaluation threshold to Q th , if Q now >Q th , then the latter control module is set as an abnormal control module and an abnormal reminder is sent.

6. A microgrid control system for executing a microgrid optimization scheduling method based on multi-module collaboration according to any one of claims 1 to 5, characterized in that: The control system includes a collaborative recording and analysis module, a module anomaly identification module, a module collaborative evaluation module and a real-time anomaly analysis module; The collaborative record analysis module is used to collect data from each control device in each dispatch process of the microgrid and generate corresponding collaborative records; analyze the collaborative situation between each control device and divide the device in any collaborative record into control modules; The module anomaly identification module is used to analyze the coordination between different control modules based on the coordination between various control devices in any coordination record, and identify anomalies in each control module; for any control module, based on the anomaly identification differences in different coordination records, the abnormal features of the abnormal control module are extracted; The module collaboration evaluation module is used to arbitrarily select an abnormal feature, analyze the collaboration between the control module where the selected abnormal feature is located and the remaining control modules, and obtain the correlation between the selected abnormal feature and the remaining control modules; for any control module, an abnormality evaluation is performed on each control module based on the correlation between each abnormal feature; The real-time anomaly analysis module is used to collect the real-time scheduling process of the microgrid at the current moment, generate real-time collaborative records and extract the abnormal features of each control module; based on the extracted abnormal features, each control module is evaluated in real time and an abnormality reminder is sent to the control module with an abnormality.

7. A microgrid control system according to claim 6, characterized in that: The collaborative record analysis module includes a collaborative record acquisition unit and a control module division unit; The collaborative record collection unit is used to collect data from each control device in each scheduling process of the microgrid and generate corresponding collaborative records; the control module division unit is used to analyze the collaborative situation between each control device and divide the device in any collaborative record into control modules.

8. A microgrid control system according to claim 6, characterized in that: The module abnormality identification module includes an abnormal module screening unit and a module feature extraction unit; The abnormal module screening unit is used to analyze the coordination situation between different control modules based on the coordination situation between each control device in any coordination record, and identify abnormalities in each control module; the module feature extraction unit is used to extract abnormal features of the abnormal control module for any control module based on the abnormal identification differences in different coordination records.

9. A microgrid control system according to claim 6, characterized in that: The module collaborative evaluation module includes a feature module association unit and a module evaluation and analysis unit; The feature module association unit is used to arbitrarily select an abnormal feature, analyze the coordination between the control module where the selected abnormal feature is located and the remaining control modules, and obtain the association between the selected abnormal feature and the remaining control modules; the module evaluation and analysis unit is used to perform abnormality evaluation on each control module based on the association of each abnormal feature for any control module.

10. A microgrid control system according to claim 6, characterized in that: The real-time anomaly analysis module includes a real-time collaborative analysis unit and a collaborative anomaly judgment unit; The real-time collaborative analysis unit is used to collect the real-time scheduling process of the microgrid at the current moment, generate real-time collaborative records and extract abnormal features of each control module; The collaborative abnormality judgment unit is used to perform real-time evaluation on each control module based on the extracted abnormal features, and send abnormality reminders to the control modules with abnormalities.

Images