Charging equipment monitoring, operation and maintenance management system and method based on multi-source data

Abstract

The invention discloses a charging equipment monitoring operation and maintenance management system and method based on multi-source data, and relates to the technical field of equipment monitoring. Comprising a target user determination module, a user classification module, a power utilization stage integration module, a fixed user screening module, a distinguishable feature coefficient analysis module, a charging feature recognition model construction module and an intelligent response adjustment module. According to the method, the user portrait features of other users without fixed charging habits in different power utilization stages are analyzed, and the identification model is constructed to evaluate the use condition of the charging equipment by the users to the greatest extent, so that the user experience is improved on the basis of judging the user data and the charging data. The reasonable charging starting time is responded to the charging equipment, the charging pressure in the peak electricity consumption stage is reduced, and the accuracy and the intelligence range of peak shifting charging adjustment are improved.

Description

Technical Field

[0001] The present invention relates to the field of charging monitoring technology, and in particular to a charging equipment monitoring operation and maintenance management system and method based on multi-source data. Background Art

[0002] As battery vehicles become more and more popular in urban transportation, their charging demand has an increasingly significant impact on the power grid. The rapid growth of battery vehicle ownership has led to a continuous increase in charging load. Under the traditional charging mode, a large number of battery vehicles are charged in the evening after get off work, which overlaps with the peak period of residents' daily electricity consumption, bringing huge pressure to the power grid.

[0003] Traditional battery vehicle charging methods mainly rely on user autonomy and lack effective intelligent management and control mechanisms. Users often connect to the charger at random after returning home and start charging without considering the load on the power grid. This disorderly charging behavior makes it difficult for the power grid to predict and balance electricity demand, further exacerbating the power shortage during peak hours.

[0004] In order to alleviate the impact of battery vehicle charging on the power grid, the industry has made some attempts to stagger charging. Some regions have introduced time-of-use electricity price policies to encourage users to charge during low-price periods. However, this method mainly relies on the self-consciousness of users and lacks effective technical means to enforce constraints and precise guidance. Many users still choose to charge during peak hours because they do not understand the time-of-use electricity price policy or because their travel schedules are limited, which greatly reduces the effectiveness of the policy. At the same time, some existing so-called "smart charging" systems, although they can realize simple timed charging functions, do not perform data analysis based on power grid load data, and have obvious deficiencies in the accuracy and intelligence of staggered charging. Summary of the invention

[0005] The purpose of the present invention is to provide a charging equipment monitoring, operation and maintenance management system and method based on multi-source data to solve the problems raised in the prior art.

[0006] To achieve the above object, the present invention provides the following technical solution: a charging equipment monitoring, operation and maintenance management method based on multi-source data, the method comprising:

[0007] Step S100: extract all logged-in users who respond to charging equipment and have redundant charging time and mark them as target users. The redundant charging time refers to the time from when the user starts charging the charging object to when the charging object is used, which is longer than the time required for the charging object to be fully charged and the difference is greater than the time threshold. The redundant charging time is added as an indicator for user screening because users without redundant charging time cannot achieve device start and stop adjustment in the time dimension during charging events. The target users are classified into non-fixed users and fixed users based on their charging data.

[0008] Step S200: Taking one day as the monitoring unit duration, extract the electricity consumption load data of all users recorded by the charging device within several monitoring unit durations, integrate different electricity consumption stages within the monitoring unit duration; determine the charging time characteristics of fixed users based on different electricity consumption stages; and screen out key fixed users;

[0009] Step S300: Extract the user data of non-fixed users based on the electricity consumption stage, analyze the distinguishable feature coefficients of non-fixed users based on the electricity consumption stage; set the threshold of the distinguishable feature coefficient, and construct a charging feature recognition model for non-fixed users based on the numerical relationship between the distinguishable feature coefficient and the threshold of the distinguishable feature coefficient;

[0010] Step S400: When a new charging device response event occurs, determine whether the user of the responding device is a key fixed user. If so, perform intelligent adjustment based on the real-time charging situation of the user; if not, perform feature recognition and response adjustment based on the charging feature recognition model.

[0011] Furthermore, classifying the target users into non-fixed users and fixed users based on the charging data of the target users includes the following specific processes:

[0012] The charging data records the charging time, extract the charging time t0 of all target users responding to the charging object and the electricity consumption time t1 of using the charging object, and construct a reference time axis with the charging time t0 and the electricity consumption time t1 of any target user;

[0013] Mark the charging data of all unit monitoring durations recorded by the same target user on the reference time axis, set the allowable error thresholds t0±a1 and t1±a1 on the reference time axis, where a1 is the set allowable time error amount;

[0014] When the charging time of each charging event recorded by the same target user all satisfies t0∈[t0 - a1, t0 + a1] and the electricity consumption time all satisfies t1∈[t1 - a1, t1 + a1], mark the target user as a fixed user; otherwise, mark it as a non-fixed user.

[0015] Furthermore, step S200 includes the following specific steps:

[0016] Mark the time period when the electricity consumption load data within each monitoring unit duration is greater than or equal to the determined peak load threshold as the peak period, mark the time period less than the low peak load threshold as the low peak period, and mark the remaining time period as the normal period; and generate a time period differentiation horizontal axis with the monitoring unit duration as the axis length;

[0017] Search for the time period differentiation horizontal axes recording several monitoring unit durations within the monitoring period, and align all the time period differentiation horizontal axes by the time start point and the time end point;

[0018] Determine the intersection part of the peak periods in the horizontal axis of each time period division as the peak power consumption stage, the intersection part of the low peak periods as the low peak power consumption stage, and the remaining periods as the normal power consumption stage;

[0019] Extract the charging data of the historical records of fixed users, and match the power consumption stage characteristics corresponding to the charging time of the charging data; when the charging data involves two types of power consumption stages and includes the characteristic that the power consumption stage changes from the peak power consumption stage to the low peak power consumption stage over time, output the corresponding fixed user as a key fixed user; when the charging data involves a single type of power consumption stage, output the corresponding fixed user as a priority fixed user.

[0020] Further, step S300 includes the following specific steps:

[0021] Step S310: Mark the power consumption cycle in which the power consumption stage changes from the peak power consumption stage to other power consumption stages over time as the fluctuating power consumption stage; extract the total number D1 of non-fixed users recorded in the fluctuating power consumption stage within each monitoring unit time length that contains the reference time axis, and use the formula: G = (1 / m) × ∑(D1 / D0) to calculate the distinguishable characteristic coefficient G corresponding to the fluctuating power consumption stage, where D0 represents the total number of users including the target user in the fluctuating power consumption stage, and m represents the total number of records of the monitoring unit time length within the monitoring cycle; similarly, calculate the distinguishable characteristic coefficient G1 corresponding to the peak power consumption stage within the same monitoring cycle;

[0022] Step S320: Set the distinguishable characteristic coefficient threshold G0. If G > G0 and the difference between G and G1 is greater than the difference threshold, mark the starting time point t of the peak power consumption stage 起 , and construct the charging characteristic recognition model as t 实 ≥t 起 ; t 实 represents the moment when the user turns on the device for charging in real time;

[0023] Meeting the above conditions indicates that the charging characteristics of non-fixed users are relatively concentrated during this fluctuating power consumption stage, and all show that the charging device starts using the electrical equipment from the charging start time in the peak power consumption stage to the low peak power consumption stage; therefore, using the time relationship as the recognition model can perform response adjustment quickly and efficiently;

[0024] When the condition of G > G0 and G - G1 is not satisfied, extract the charging device monitoring events recorded by each non-fixed user during the fluctuating power consumption stage and the peak power consumption stage; the charging device monitoring events store the initial remaining charge of the electrical device and the log data of the user device end; calculate the power profile index U of different charging device monitoring events recorded by each non-fixed user during the fluctuating power consumption stage and the peak power consumption stage, U = (W2 - W1) / W1, where W1 represents the remaining charge during the fluctuating power consumption stage and W2 represents the remaining charge during the peak power consumption stage; combine the monitoring events of the same non-fixed user in the two types of power consumption stages to calculate all power profile indexes, calculate the coefficient of variation of each non-fixed user with respect to the power profile index, traverse the coefficient of variation of all non-fixed users to calculate the mean coefficient of variation, and set the coefficient of variation threshold;

[0025] When the mean coefficient of variation is less than the coefficient of variation threshold, mark the initial remaining charge of the electrical device as an effective feature quantity; otherwise, do not mark it; the smaller the coefficient of variation, the smaller the degree of numerical dispersion reflected by the power profile index, which further reflects that there is a certain correlation between the remaining charge of the user's electrical device and the power consumption stage experienced when the final charging event is completed when the non-fixed user executes the charging event during the fluctuating power consumption stage and the peak power consumption stage; therefore, the remaining charge can be used as a basis for judging whether time-adjustable operations can be performed for non-fixed users or new users when responding to charging device events;

[0026] Extract the log data of the user device end before the response of the charging device monitoring events recorded by the same non-fixed user based on the two types of power consumption stages. The log data includes running application programs. Mark the log data before the response of the charging device monitoring events recorded during the fluctuating power consumption stage as the first log, and mark the log data before the response of the charging device monitoring events recorded during the peak power consumption stage as the second log;

[0027] Take the intersection of the first log and the second log recorded by each non-fixed user to obtain the common log. Take the running application programs in the first log after removing the common log as the state-maintaining application programs, and take the running application programs in the second log after removing the common log as the fluctuating application programs;

[0028] Traverse each non-fixed user to obtain the corresponding state-maintaining application programs and fluctuating application programs. Take the intersection of the state-maintaining application programs of all non-fixed users to obtain the first target application program, and take the intersection of the fluctuating application programs of all non-fixed users to obtain the second target application program; construct the charging feature recognition model Y = f1 + f2;

[0029] f1 represents the eigenvalue when the remaining power of the real-time user belongs to the power range corresponding to the effective characteristic quantities of two types of power consumption stages, and the power range is composed of the maximum and minimum values of the remaining power recorded in the historical analysis of the two types of power consumption stages; f1 = {1, 0}, when f1 = 1, it means belonging to the power range of the fluctuating power consumption stage, and when f1 = 0, it means that the effective characteristic quantity is not marked or belonging to the power range of the peak power consumption stage;

[0030] f2 represents the number of running application programs on the user device side that are the same as the first target application program before the real-time user records the monitoring event response of the charging device.

[0031] Furthermore, step S400 includes the following steps:

[0032] When the user of the real-time response device is a key fixed user and in the fluctuating power consumption stage, obtain the estimated charging duration, and based on the real-time charging moment, adjust the actual start charging moment according to the principle of maximizing the coverage of the low peak stage or the normal stage;

[0033] When the user of the real-time response device is a priority fixed user and in the peak power consumption stage, turn on the device charging in real time;

[0034] When the user of the real-time response device is a non-fixed user, and the constructed charging feature recognition model is t 实 ≥t 起 , obtain the charging device response moment, and when t 实 ≥t 起 , adjust the actual start charging moment according to the principle of maximizing the coverage of the low peak stage or the normal stage; if not satisfied, turn on the device charging in real time;

[0035] When the user of the real-time response device is a non-fixed user, and the constructed charging feature recognition model is Y = f1 + f2, extract the remaining charging power of the non-fixed user and the log data of the user device side, bring them into the calculation to output the charging feature recognition value, calculate the charging feature recognition values of each device in the charging process in real time, calculate the average value, and when the real-time charging feature recognition value is greater than the average value, adjust the actual start charging moment according to the principle of maximizing the coverage of the low peak stage or the normal stage; otherwise, turn on the device charging in real time.

[0036] The charging device monitoring and operation and maintenance management system based on multi-source data, the system includes a target user determination module, a user classification module, a power consumption stage integration module, a fixed user screening module, a distinguishable feature coefficient analysis module, a charging feature recognition model construction module and an intelligent response adjustment module;

[0037] The target user determination module is used to extract all logged-in users who respond to the charging device and have a charging redundancy duration and mark them as target users,

[0038] The user classification module is used to classify the target user into a non-fixed user and a fixed user based on the charging data of the target user;

[0039] The electricity consumption stage integration module is used to integrate different electricity consumption stages within the monitored unit time;

[0040] The fixed user screening module is used to determine the charging time characteristics of fixed users based on different electricity consumption stages; and screen out key fixed users;

[0041] The distinguishable feature coefficient analysis module is used to analyze the distinguishable feature coefficient of non-fixed users based on the electricity consumption stage;

[0042] The charging feature recognition model construction module is used to construct a charging feature recognition model for non-fixed users;

[0043] The intelligent response adjustment module is used to adjust the intelligent response charging time when a new charging device response event occurs.

[0044] Furthermore, the distinguishable feature coefficient analysis module includes a fluctuating electricity consumption stage determination unit and a distinguishable feature coefficient calculation unit;

[0045] The fluctuating electricity consumption stage determination unit is used to mark the electricity consumption cycle in which the electricity consumption stage advances from the peak electricity consumption stage to other electricity consumption stages over time as the fluctuating electricity consumption stage;

[0046] The distinguishable feature coefficient calculation unit is used to extract the total number of non-fixed users recorded in the fluctuating electricity consumption stage within each monitored unit time that includes the reference time axis, and calculate the distinguishable feature coefficient corresponding to the fluctuating electricity consumption stage.

[0047] Furthermore, the charging feature recognition model construction module includes a first-class recognition model construction unit and a second-class recognition model construction unit;

[0048] The first-class recognition model construction unit is used to construct a charging feature recognition model based on the starting time point when the distinguishable feature coefficient is greater than the distinguishable feature coefficient threshold and the difference between the distinguishable feature coefficient corresponding to the fluctuating electricity consumption stage and the peak electricity consumption node is greater than the difference threshold;

[0049] The second-class recognition model construction unit is used to calculate the electricity consumption portrait index of different charging device monitoring events recorded in the fluctuating electricity consumption stage and the peak electricity consumption stage where each non-fixed user is located when the construction conditions of the first-class recognition model are not met, calculate the dispersion coefficient of each non-fixed user with respect to the electricity consumption portrait index, traverse the dispersion coefficients of all non-fixed users to calculate the average dispersion coefficient, set the dispersion coefficient threshold, and mark the effective feature quantities based on the size relationship between the dispersion coefficient and the threshold; thereby constructing a second-class recognition model.

[0050] Further, the intelligent response adjustment module includes a real-time user determination unit, a data substitution unit and a maximum coverage principle response unit;

[0051] The real-time user determination unit is used to determine the real-time user type;

[0052] The data substitution unit is used to substitute the user data acquired in real time into the recognition model;

[0053] The maximum coverage principle response unit is used to respond to the charging device to adjust the actual charging start time according to the maximum coverage low-peak stage or normal stage principle.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] 1. The present invention screens target users and determines the user group that can find out the rules based on the user charging data in a large amount of user data to realize the charging peak adjustment from the time dimension, thereby saving the system's overall analysis computing power requirements for numerous and complex user data;

[0056] 2. The present invention divides target users according to their charging habits, and prioritizes the electricity consumption of some users with fixed charging habits when they meet the electricity consumption stage with adjustable charging time, so that the optimization adjustment of electricity load sharing can be quickly realized based on a simple analysis algorithm;

[0057] The present invention analyzes the user portrait characteristics of other users who do not have fixed charging habits at different power usage stages, and constructs a recognition model to evaluate the user's usage of the charging device to the greatest extent, so as to achieve a reasonable charging start time for the charging device based on the judgment of user data and charging data, reduce the charging pressure in the peak power usage stage, and improve the accuracy and intelligence of off-peak charging regulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a structural schematic diagram of the charging equipment monitoring, operation and maintenance management method based on multi-source data of the present invention. DETAILED DESCRIPTION

[0059] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0060] Example: Figure 1 As shown, the present invention provides a charging equipment monitoring, operation and maintenance management method based on multi-source data, the method comprising:

[0061] Step S100: Extract all logged-in users who respond to the charging device and have a charging redundancy duration. The charging redundancy duration refers to the interval duration from the start charging moment of the user to the charging object to the moment of using the charging object, which is greater than the duration required for the charging object to complete charging and the difference is greater than the duration threshold. Adding the charging redundancy duration as an indicator for user screening is because users without charging redundancy duration cannot achieve start-stop adjustment of the device in the time dimension during the charging event. Classify the target users into non-fixed users and fixed users based on the charging data of the target users.

[0062] Step S200: Taking one day as a monitoring unit duration, extract the electricity load data of all users recorded by the charging device within several monitoring unit durations, and integrate different electricity consumption stages within the monitoring unit duration. Determine the charging time characteristics of fixed users based on different electricity consumption stages, and screen out key fixed users.

[0063] Step S300: Extract the user data of non-fixed users based on the electricity consumption stage, and analyze the distinguishable feature coefficients of non-fixed users based on the electricity consumption stage. Set the distinguishable feature coefficient threshold, and construct a charging feature recognition model for non-fixed users based on the numerical relationship between the distinguishable feature coefficient and the distinguishable feature coefficient threshold.

[0064] Step S400: When a new charging device response event occurs, determine whether the user of the responding device is a key fixed user. If so, perform intelligent adjustment based on the real-time charging situation of the user. If not, perform feature recognition and response adjustment based on the charging feature recognition model.

[0065] Classifying the target users into non-fixed users and fixed users based on the charging data of the target users includes the following specific processes:

[0066] The charging data records the charging moment. Extract the charging moment t0 of all target users responding to the charging object and the electricity consumption moment t1 of using the charging object, and construct a reference time axis with the charging moment t0 and the electricity consumption moment t1 of any target user.

[0067] Mark the charging data of all unit monitoring durations recorded by the same target user on the reference time axis, and set the allowable error thresholds t0±a1 and t1±a1 on the reference time axis, where a1 is the set allowable time error amount.

[0068] When the charging moments of each charging event recorded by the same target user all satisfy t0∈[t0 - a1, t0 + a1] and the electricity consumption moments all satisfy t1∈[t1 - a1, t1 + a1], mark the target user as a fixed user; otherwise, mark it as a non-fixed user.

[0069] Step S200 includes the following specific steps:

[0070] Mark the time periods within each monitoring unit duration when the electricity load data is greater than or equal to the peak load threshold as peak periods, the time periods less than the off-peak load threshold as off-peak periods, and the remaining time periods as normal periods; and generate a time period differentiation horizontal axis with the monitoring unit duration as the axis length.

[0071] Search for the time period differentiation horizontal axes that record several monitoring unit durations within the monitoring period, and align all the time period differentiation horizontal axes based on the start time point and end time point of time.

[0072] Determine the intersection part of the peak periods in each time period differentiation horizontal axis as the peak electricity consumption stage, the intersection part of the off-peak periods as the off-peak electricity consumption stage, and the remaining time periods as the normal electricity consumption stage.

[0073] Extract the charging data of the fixed user's historical records, and match the characteristics of the electricity consumption stage corresponding to the charging time of the charging data; when the charging data involves two types of electricity consumption stages and includes the characteristic that the electricity consumption stage changes from the peak electricity consumption stage to the off-peak electricity consumption stage over time, output the corresponding fixed user as a key fixed user; when the charging data involves a single type of electricity consumption stage, output the corresponding fixed user as a priority fixed user.

[0074] Step S300 includes the following specific steps:

[0075] Step S310: Mark the electricity consumption cycle in which the electricity consumption stage changes from the peak electricity consumption stage to other electricity consumption stages over time as the fluctuating electricity consumption stage; extract the total number D1 of non-fixed users recorded in the fluctuating electricity consumption stage within each monitoring unit duration that contains the reference time axis, and use the formula: G = (1 / m) × ∑(D1 / D0) to calculate the distinguishable characteristic coefficient G corresponding to the fluctuating electricity consumption stage, where D0 represents the total number of users containing the target user in the fluctuating electricity consumption stage, and m represents the total number of records of the monitoring unit duration within the monitoring period; similarly, calculate the distinguishable characteristic coefficient G1 corresponding to the peak electricity consumption stage in the same monitoring period.

[0076] Step S320: Set the distinguishable characteristic coefficient threshold G0. If G > G0 and the difference between G and G1 is greater than the difference threshold, mark the start time point t of the peak electricity consumption stage 起 , and construct the charging characteristic recognition model as t 实 ≥t 起 ; t 实 represents the moment when the user turns on the device for charging in real time.

[0077] Meeting the above conditions indicates that the charging characteristics of non-fixed users are relatively concentrated within this fluctuating electricity consumption stage, and all show that the charging device starts using the device only from the moment of starting charging in the peak electricity consumption stage to the off-peak electricity consumption stage; therefore, using the time relationship as the recognition model can quickly and efficiently perform response adjustment.

[0078] When the condition of G > G0 and G - G1 is not satisfied, extract the charging device monitoring events recorded by each non-fixed user during the fluctuating power consumption stage and the peak power consumption stage; the charging device monitoring events store the initial remaining charge of the electrical device and the log data of the user device end; calculate the power profile index U of different charging device monitoring events recorded by each non-fixed user during the fluctuating power consumption stage and the peak power consumption stage, U = (W2 - W1) / W1, where W1 represents the remaining charge during the fluctuating power consumption stage and W2 represents the remaining charge during the peak power consumption stage; combine the monitoring events of the same non-fixed user in the two types of power consumption stages to calculate all the power profile indexes, calculate the coefficient of variation of each non-fixed user with respect to the power profile index, traverse the coefficients of variation of all non-fixed users to calculate the mean coefficient of variation, and set the coefficient of variation threshold;

[0079] When the mean coefficient of variation is less than the coefficient of variation threshold, mark the initial remaining charge of the electrical device as an effective feature quantity; otherwise, do not mark; the smaller the coefficient of variation, the smaller the degree of numerical dispersion reflected by the power profile index, which further reflects that when the non-fixed user executes the charging event during the fluctuating power consumption stage and the peak power consumption stage, there is a certain correlation between the remaining charge of the user's electrical device and the power consumption stage experienced until the final charging event is completed; therefore, the remaining charge can be used as a basis for judging whether time-adjustable operations can be performed for non-fixed users or new users when responding to charging device events;

[0080] Extract the log data of the user device end before the response of the charging device monitoring events recorded by the same non-fixed user based on the two types of power consumption stages. The log data includes running application programs. Mark the log data before the response of the charging device monitoring events recorded during the fluctuating power consumption stage as the first log, and mark the log data before the response of the charging device monitoring events recorded during the peak power consumption stage as the second log;

[0081] Take the intersection of the first log and the second log recorded by each non-fixed user to obtain the common log. Take the running application programs in the first log after removing the common log as the state-maintaining application programs, and take the running application programs in the second log after removing the common log as the fluctuating application programs;

[0082] Traverse each non-fixed user to obtain the corresponding state-maintaining application programs and fluctuating application programs. Take the intersection of the state-maintaining application programs of all non-fixed users to obtain the first target application program, and take the intersection of the fluctuating application programs of all non-fixed users to obtain the second target application program; construct the charging feature recognition model Y = f1 + f2;

[0083] f1 represents the eigenvalue when the remaining power of the real-time user belongs to the power range corresponding to the effective characteristic quantities of two types of power consumption stages. The power range is composed of the maximum and minimum values of the remaining power recorded in the historical analysis of the two types of power consumption stages; f1 = {1, 0}. When f1 = 1, it indicates that it belongs to the power range of the fluctuating power consumption stage. When f1 = 0, it indicates that no effective characteristic quantity is marked or it belongs to the power range of the peak power consumption stage.

[0084] f2 represents the number of running application programs on the user device end that are the same as the first target application program before the real-time user records the monitoring event response of the charging device.

[0085] As shown in the embodiment: The application program run by the user before charging is the takeaway program, and the power consumption stage after subsequent response to charging is the fluctuating power consumption stage, that is, spanning from the peak power consumption stage to the low peak power consumption stage or spanning from the peak power consumption stage to the normal power consumption stage.

[0086] And in the analysis of the application programs of all non-fixed users, if the takeaway program is still retained after taking the intersection, it can be determined that the takeaway program is a user portrait feature that non-fixed users may record cross-stage power consumption. When there is more user data that conforms to this user portrait feature, it means that the possibility that the charging time of this user is much farther from the startup time of the electrical device than the time required to complete charging is greater, and the space for adjusting the charging time will be larger. The adjustable space for this type of user based on the needs of the electrical device is larger.

[0087] Step S400 includes the following steps:

[0088] When the user of the real-time response device is a key fixed user and is in the fluctuating power consumption stage, obtain the estimated charging duration, and based on the real-time charging moment, adjust the actual start charging moment according to the principle of maximizing the coverage of the low peak stage or the normal stage;

[0089] As shown in the embodiment: If the moment when the user responds to the charging device is 19:00 and is in the fluctuating power consumption period at this time, the fluctuating power consumption period here is determined based on the user, that is, the charging period habitually used by the user covers the peak power consumption stage and the low peak power consumption stage; and the end point of the user's reference time axis is 9:00; with a front and back error of 1h;

[0090] The period from 22:00 to 7:00 the next day belongs to the low peak power consumption stage. At this time, the estimated charging duration is 6h. The principle of maximizing the coverage means that the charging moment when the user responds at 19:00 can be postponed to start as early as 22:00 at the earliest and end charging as late as 8:00 the next day; rather than charging in the interval from 19:00 to 22:00 and occupying the peak power consumption load;

[0091] When the user of the real-time response device is a priority fixed user and is in the peak power consumption stage, turn on the device charging in real time;

[0092] When the user of the real-time response device is a non-fixed user and the constructed charging feature recognition model is t 实 ≥t 起 , obtain the charging device response time, and adjust the actual start charging time according to the principle of maximum coverage of the low peak stage or the normal stage when t 实 ≥t 起 ; if not satisfied, turn on the device charging in real time;

[0093] When the user of the real-time response device is a non-fixed user and the constructed charging feature recognition model is Y = f1 + f2, extract the remaining charge of the non-fixed user and the log data of the user device end, substitute them into the calculation to output the charging feature recognition value, calculate the charging feature recognition values of each device in the charging process in real time, calculate the average value, and when the real-time charging feature recognition value is greater than the average value, adjust the actual start charging time according to the principle of maximum coverage of the low peak stage or the normal stage; otherwise, turn on the device charging in real time.

[0094] A charging device monitoring, operation and maintenance management system based on multi-source data, the system includes a target user determination module, a user classification module, a power consumption stage integration module, a fixed user screening module, a distinguishable feature coefficient analysis module, a charging feature recognition model construction module and an intelligent response adjustment module;

[0095] The target user determination module is used to extract all logged-in users who respond to the charging device and have a charging redundancy duration and mark them as target users,

[0096] The user classification module is used to classify the target users into non-fixed users and fixed users based on the charging data of the target users;

[0097] The power consumption stage integration module is used to integrate different power consumption stages within the monitored unit duration;

[0098] The fixed user screening module is used to determine the charging time characteristics of fixed users based on different power consumption stages; and screen out key fixed users;

[0099] The distinguishable feature coefficient analysis module is used to analyze the distinguishable feature coefficients of non-fixed users based on the power consumption stage;

[0100] The charging feature recognition model construction module is used to construct a charging feature recognition model for non-fixed users;

[0101] The intelligent response adjustment module is used to adjust the intelligent response charging time when a new charging device response event occurs.

[0102] The distinguishable feature coefficient analysis module includes a fluctuating power consumption stage determination unit and a distinguishable feature coefficient calculation unit;

[0103] The fluctuating power consumption stage determination unit is used to mark the power consumption cycle in which the power consumption stage advances from the peak power consumption stage to other power consumption stages over time as the fluctuating power consumption stage;

[0104] The distinguishable feature coefficient calculation unit is used to extract the total number of non-fixed users recorded in the fluctuating power consumption stage within each monitored unit time length, which includes the reference time axis, and calculate the distinguishable feature coefficient corresponding to the fluctuating power consumption stage.

[0105] The charging feature recognition model construction module includes a first-class recognition model construction unit and a second-class recognition model construction unit;

[0106] The first-class recognition model construction unit is used to construct a charging feature recognition model based on the starting time point when the distinguishable feature coefficient is greater than the distinguishable feature coefficient threshold and the difference between the distinguishable feature coefficient corresponding to the fluctuating power consumption stage and the peak power consumption node is greater than the difference threshold;

[0107] The second-class recognition model construction unit is used when the construction conditions of the first-class recognition model are not met. It calculates the power profile indicators of different charging device monitoring events recorded in the fluctuating power consumption stage and the peak power consumption stage for each non-fixed user, calculates the coefficient of variation of each non-fixed user with respect to the power profile indicators, traverses the coefficients of variation of all non-fixed users to calculate the mean coefficient of variation, sets the coefficient of variation threshold, and marks the effective feature quantities based on the magnitude relationship between the coefficient of variation and the threshold; thereby constructing a second-class recognition model.

[0108] The intelligent response adjustment module includes a real-time user determination unit, a data substitution unit, and a maximum coverage principle response unit;

[0109] The real-time user determination unit is used to determine the type of real-time users;

[0110] The data substitution unit is used to substitute the real-time obtained user data into the recognition model;

[0111] The maximum coverage principle response unit is used to adjust the actual start charging time by responding to the charging device according to the principle of maximum coverage of the low peak stage or the normal stage.

[0112] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A charging equipment monitoring, operation and maintenance management method based on multi-source data, characterized in that: The method comprises: Step S100: extracting all logged-in users who respond to charging equipment and have redundant charging time as target users, wherein the redundant charging time refers to the time interval from the time when the user starts charging the charging object to the time when the charging object is used is greater than the time required for the charging object to be fully charged and the difference is greater than the time threshold; classifying the target users into non-fixed users and fixed users based on their charging data; Step S200: Taking one day as a monitoring unit, extracting the power load data of all users recorded by the charging equipment within a certain monitoring unit, integrating different power consumption stages within the monitoring unit; determining the charging time characteristics of fixed users based on different power consumption stages; and screening out key fixed users; Step S300: extracting user data of non-fixed users based on the electricity usage stage, analyzing the distinguishable characteristic coefficients of the non-fixed users based on the electricity usage stage; setting a distinguishable characteristic coefficient threshold, and constructing a charging feature recognition model for non-fixed users based on the numerical relationship between the distinguishable characteristic coefficient and the distinguishable characteristic coefficient threshold; Step S400: When a new charging device responds to an event, determine whether the user of the responding device is a key fixed user. If so, perform intelligent adjustment based on the real-time user's charging status; if not, perform feature recognition and response adjustment based on the charging feature recognition model.

2. The charging equipment monitoring, operation and maintenance management method based on multi-source data according to claim 1 is characterized by: The method of classifying the target user into a non-fixed user and a fixed user based on the charging data of the target user includes the following specific processes: The charging data records the charging time, extracts the charging time t0 of all target users responding to the charging object and the electricity consumption time t1 of the charging object, and constructs a reference time axis with the charging time t0 and electricity consumption time t1 of any target user; Mark the charging data of all unit monitoring time recorded by the same target user on the reference time axis, set the allowable error thresholds t0±a1 and t1±a1 on the reference time axis, where a1 is the set allowable time error; When the charging time of each charging event recorded by the same target user satisfies t0∈[t0-a1,t0+a1] and the power consumption time satisfies t1∈[t1-a1,t1+a1], the target user is marked as a fixed user; otherwise, it is marked as a non-fixed user.

3. The charging equipment monitoring, operation and maintenance management method based on multi-source data according to claim 2 is characterized in that: The step S200 includes the following specific steps: The time period in which the power load data within each monitoring unit time is greater than or equal to the peak load threshold is marked as the peak time period, the time period less than the low-peak load threshold is marked as the low-peak time period, and the remaining time periods are marked as the normal time period; and a time period-differentiated horizontal axis with the monitoring unit time as the axis length is generated; Find the time period-dividing horizontal axis that records the duration of several monitoring units within the monitoring period, and align all time period-dividing horizontal axes with the time start point and time end point; Determine the intersection of the peak time periods in the horizontal axis of each time period as the peak power consumption stage, the intersection of the off-peak time periods as the off-peak power consumption stage, and the remaining time periods as the normal power consumption stage; Extract the charging data of the historical records of fixed users, and match the characteristics of the power consumption stage at the time of charging corresponding to the charging data; when the charging data involves two types of power consumption stages and contains the characteristics that the power consumption stage changes from the peak power consumption stage to the low-peak power consumption stage over time, output the corresponding fixed user as the key fixed user; when the charging data involves a unique power consumption stage type, output the corresponding fixed user as the priority fixed user.

4. The charging equipment monitoring, operation and maintenance management method based on multi-source data according to claim 3 is characterized by: The step S300 includes the following specific steps: Step S310: Mark the electricity consumption period in which the electricity consumption stage progresses from the peak electricity consumption stage to other electricity consumption stages over time as the fluctuating electricity consumption stage; extract the total number of non-fixed users D1 recorded in the fluctuating electricity consumption stage containing the reference time axis within each monitoring unit time, and use the formula: G = (1 / m) × ∑ (D1 / D0) to calculate the distinguishable characteristic coefficient G corresponding to the fluctuating electricity consumption stage, where D0 represents the total number of target users included in the fluctuating electricity consumption stage, and m represents the total number of records of the monitoring unit time within the monitoring period; similarly calculate the distinguishable characteristic coefficient G1 corresponding to the peak electricity consumption stage within the same monitoring period; Step S320: Set the distinguishable characteristic coefficient threshold G0. If G>G0 and the difference between G and G1 is greater than the difference threshold, mark the starting time point t of the peak power consumption phase. 起 , construct the charging feature recognition model as t 实 ≥t 起 ;t 实 Indicates the moment when the user starts charging the device in real time; If the condition G>G0 and G-G1 is not met, the charging equipment monitoring events recorded by each non-fixed user during the fluctuating power consumption stage and the peak power consumption stage are extracted; the charging equipment monitoring events store the initial charging remaining power of the power-consuming equipment and the log data of the user's device end; Calculate the power profile index U of different charging equipment monitoring events recorded in the fluctuating power consumption stage and the peak power consumption stage for each non-fixed user, U = (W2-W1) / W1, W1 represents the remaining power in the fluctuating power consumption stage, and W2 represents the remaining power in the peak power consumption stage; combine the monitoring events of the same non-fixed user in the two types of power consumption stages to calculate all power profile indicators, calculate the discrete coefficient of each non-fixed user with respect to the power profile index, traverse the discrete coefficients of all non-fixed users to calculate the mean of the discrete coefficients, and set the discrete coefficient threshold; When the mean value of the dispersion coefficient is less than the dispersion coefficient threshold, the initial charging remaining power of the electrical equipment is marked as a valid characteristic quantity; Otherwise, no marking will be done; Extract the log data of the user device before the response to the charging device monitoring event based on two types of power consumption stages for the same non-fixed user, wherein the log data includes running the application, marking the log data before the response to the charging device monitoring event in the fluctuating power consumption stage as the first log, and marking the log data before the response to the charging device monitoring event in the peak power consumption stage as the second log; The intersection of the first log and the second log of each non-fixed user record is obtained by obtaining a common log, and the running application programs in the first log except the common log are regarded as state-maintaining applications, and the running application programs in the second log except the common log are regarded as fluctuating applications; Traverse each non-fixed user to obtain the corresponding state-maintaining application and fluctuating application, take the intersection of all the state-maintaining applications of non-fixed users to obtain the first target application, and take the intersection of all the fluctuating applications of non-fixed users to obtain the second target application; construct a charging feature recognition model Y=f1+f2; f1 represents the characteristic value when the real-time user remaining power belongs to the power interval of the valid characteristic quantity corresponding to the two types of power consumption stages, and the power interval is composed of the maximum and minimum values ​​of the remaining power recorded in the two types of power consumption stages in the historical analysis; f1 = {1, 0}, when f1 = 1, it means the power interval belongs to the fluctuating power consumption stage, and when f1 = 0, it means that the valid characteristic quantity is not marked or the power interval belongs to the peak power consumption stage; f2 represents the number of running applications on the user's device that are identical to the first target application before the real-time user records the charging device monitoring event response.

5. The charging equipment monitoring, operation and maintenance management method based on multi-source data according to claim 4 is characterized in that: The step S400 includes the following steps: When the user of the real-time response device is a key fixed user and is in a fluctuating electricity consumption stage, the estimated charging time is obtained, and based on the real-time charging time, the actual charging start time is adjusted in accordance with the principle of maximizing coverage of the off-peak stage or the normal stage; When the user of the real-time response device is a priority fixed user and is in the peak power consumption period, the device charging is started in real time; When the user of the real-time response device is a non-fixed user, and the charging feature recognition model is constructed as t 实 ≥t 起 At t, obtain the charging device response time. 实 ≥t 起 The actual charging start time is adjusted based on the principle of maximum coverage of the low-peak phase or the normal phase; if it is not met, the device charging is started in real time; When the user of the real-time response device is a non-fixed user and the charging feature recognition model is constructed as Y=f1+f2, the remaining charging power of the non-fixed user and the log data of the user device are extracted and brought into the calculation output charging feature recognition value, the charging feature recognition value of each device that is charging in real time is calculated, and the average value is calculated. When the real-time charging feature recognition value is greater than the average value, the actual charging start time is adjusted based on the principle of maximum coverage of the low-peak stage or the normal stage; otherwise, the device charging is started in real time.

6. A charging equipment monitoring, operation and maintenance management system based on multi-source data, such as using the charging equipment monitoring, operation and maintenance management method based on multi-source data according to any one of claims 1 to 5, characterized in that: The system includes a target user determination module, a user classification module, a power consumption stage integration module, a fixed user screening module, a distinguishable characteristic coefficient analysis module, a charging characteristic recognition model construction module and an intelligent response adjustment module; The target user determination module is used to extract all logged-in users who respond to the charging device and have redundant charging time and mark them as target users. The user classification module is used to classify the target user into a non-fixed user and a fixed user based on the charging data of the target user; The power consumption stage integration module is used to integrate different power consumption stages within the monitoring unit time; The fixed user screening module is used to determine the charging time characteristics of fixed users based on different power consumption stages; And screen out key fixed users; The distinguishable characteristic coefficient analysis module is used to analyze the distinguishable characteristic coefficients of non-fixed users based on the electricity consumption stage; The charging feature recognition model building module is used to build a charging feature recognition model for non-fixed users; The intelligent response adjustment module is used to adjust the intelligent response charging time when a new charging device responds to an event.

7. The charging equipment monitoring, operation and maintenance management system based on multi-source data according to claim 6, characterized in that: The distinguishable characteristic coefficient analysis module includes a fluctuating power consumption stage determination unit and a distinguishable characteristic coefficient calculation unit; The fluctuating power consumption stage determination unit is used to mark the power consumption cycle in which the power consumption stage progresses from the peak power consumption stage to other power consumption stages over time as a fluctuating power consumption stage; The distinguishable characteristic coefficient calculation unit is used to extract the total number of non-fixed users recorded in the fluctuating power consumption stage within each monitoring unit time and including the reference time axis, and calculate the distinguishable characteristic coefficient corresponding to the fluctuating power consumption stage.

8. The charging equipment monitoring, operation and maintenance management system based on multi-source data according to claim 6, characterized in that: The charging feature recognition model construction module includes a first-class recognition model construction unit and a second-class recognition model construction unit; The first type of recognition model construction unit is used to construct a charging feature recognition model based on the starting time point when the distinguishable feature coefficient is greater than the distinguishable feature coefficient threshold and the difference between the distinguishable feature coefficients of the corresponding fluctuating power consumption stage and the peak power consumption node is greater than the difference threshold; The second-class identification model construction unit is used to calculate the power portrait index of each non-fixed user in the fluctuating power consumption stage and the peak power consumption stage to record different charging equipment monitoring events when the construction conditions of the first-class identification model are not met, calculate the discrete coefficient of each non-fixed user with respect to the power portrait index, traverse the discrete coefficients of all non-fixed users to calculate the mean of the discrete coefficients, set the discrete coefficient threshold, and mark the effective feature quantity based on the size relationship between the discrete coefficient and the threshold; Thus a two-class recognition model is constructed.

9. The charging equipment monitoring, operation and maintenance management system based on multi-source data according to claim 6, characterized in that: The intelligent response adjustment module includes a real-time user determination unit, a data substitution unit and a maximum coverage principle response unit; The real-time user determination unit is used to determine the real-time user type; The data substitution unit is used to substitute the user data acquired in real time into the recognition model; The maximum coverage principle response unit is used to respond to the charging device adjusting the actual charging start time according to the maximum coverage low-peak stage or normal stage principle.

Images