Power load intelligent regulation and control method and system
Through the intelligent power load regulation system, the power load abnormalities are identified and adjusted by using historical databases and real-time data analysis, and a variety of adjustment solutions are provided, which solves the problem of inflexible handling of power load abnormalities in the existing technology, and achieves the stability of the power system and Run efficiently.
Patent Information
- Application Number
- CN202411016089.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-27
- Publication Date
- 2024-11-01
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
When the existing power load regulation system faces abnormal power load, the regulation method is not flexible and efficient enough, making it difficult to effectively deal with sudden and large-scale load abnormalities.
An intelligent power load regulation system was designed, including a historical database module, a collection module, an analysis and judgment module and a processing module. By establishing a historical database, collecting power load data in real time, analyzing and judging power load fluctuations and abnormal data, the abnormal level is determined. , and adjust the power load at the next moment according to the level, provide load reduction notification, start the backup generator or implement cross-regional power allocation and other solutions.
A flexible and efficient power load abnormal handling mechanism is realized, which can detect and deal with power load abnormalities in real time, ensure the stable operation of the power system, reduce the impact on users' normal power use, and improve the adaptability and accuracy of the system through self-learning and optimization. sex.
Smart Images

Figure CN118889404A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power systems, and in particular to a method and system for intelligently controlling power loads. Background Art
[0002] Electricity load, also known as "electricity load". The total amount of electric power drawn from the power system by the electric energy users' electrical equipment at a certain moment is called electricity load. According to the different load characteristics of electricity users, electricity load can be divided into various industrial loads, agricultural loads, transportation loads, and people's daily life loads.
[0003] The total load of the power system is the sum of the total power consumed by all electrical equipment in the system; adding up the power consumed by industry, agriculture, post and telecommunications, transportation, municipal administration, commerce, and urban and rural residents gives the comprehensive power load of the power system; the comprehensive power load plus the power loss of the network is the power that each power plant in the system should supply, which is called the power supply load (power supply) of the power system; the power supply load plus the power consumed by each power plant itself (i.e. plant power consumption) is the power that each generator in the system should generate, which is called the system's power generation load (power generation).
[0004] The existing power load control system is not flexible and efficient enough when facing power load anomalies. Although these control methods can cope with power load fluctuations to a certain extent, their response effect is still poor when facing sudden and large-scale load anomalies.
[0005] Therefore, it is necessary to design an intelligent control method and system for power load to solve the problems existing in current technology. Summary of the invention
[0006] In view of this, the present invention proposes an intelligent power load control method and system, aiming to solve the problem that the existing power load control system in the current technology is not flexible and efficient enough when facing power load abnormality.
[0007] In one aspect, the present invention provides an intelligent control system for electric loads, comprising:
[0008] A historical database module is used to establish a historical database based on the power consumption in the user area, wherein the historical database includes a historical normal power consumption database and a historical abnormal power consumption database, wherein the historical database includes historical residential power consumption, historical commercial power consumption, historical industrial power consumption and historical public utility power consumption, and the historical residential power consumption, historical commercial power consumption, historical industrial power consumption and historical public utility power consumption correspond to historical moments;
[0009] A collection module, used to collect real-time power load in the user area, establish a power load data set according to the power load in the user area at the current moment, the power load data set includes the actual power load in the user area at the current moment and the actual power load in the user area at the previous moment, and obtain the actual power load fluctuation value according to the power load data set;
[0010] An analysis and judgment module is used to compare and screen the actual power load fluctuation value with the power load fluctuation value threshold, and judge whether the screened actual power load fluctuation value is actual power load abnormal data;
[0011] The analysis and judgment module is also used to analyze the correlation between the actual power load abnormality data of each type, compare the correlation with the correlation threshold, and determine the power load abnormality level according to the comparison result;
[0012] The analysis and judgment module is also used to compare the actual power load abnormality data with the historical power load abnormality database data, and adjust the power load abnormality level according to the comparison result;
[0013] The processing module is used to adjust the power load in the user area at the next moment according to the power load abnormality level.
[0014] Furthermore, the analysis and judgment module compares and screens the actual power load fluctuation value with the power load fluctuation value threshold, and the calculation formula of the power load fluctuation threshold is:
[0015] Y = μL + k·σL;
[0016] Among them, Y represents the power load fluctuation value threshold, μL represents the mean of the historical power load fluctuation value, σL represents the standard deviation of the historical power load fluctuation value, and k represents the adjustment factor;
[0017]
[0018] Lt=|X t -X t-1 |;
[0019] Among them, Lt represents the power load fluctuation value, X t represents the actual power load in the user area at the current moment, X t-1 represents the actual power load in the user area at the previous moment, and n represents the number of historical power load fluctuation values.
[0020] Furthermore, when the analysis and judgment module compares and screens the actual power load fluctuation value with the power load fluctuation value threshold, it also includes:
[0021] The actual power load fluctuation value is compared with the power load fluctuation value threshold, and small actual power load fluctuation values are eliminated;
[0022] When the actual power load fluctuation value is greater than the power load fluctuation value threshold, retaining the actual power load fluctuation value;
[0023] When the actual power load fluctuation value is less than or equal to the power load fluctuation value threshold, the actual power load fluctuation value is discarded.
[0024] Furthermore, when the analysis and judgment module judges whether the filtered actual power load fluctuation value is power load abnormal data, it includes:
[0025] Fitting an ARIMA model using data from the historical power load normal database;
[0026] Predicting the power load in the user area according to the ARIMA model, using the predicted power load data as the predicted power load in the user area at the current moment, then calculating the difference between the predicted power load in the user area at the current moment and the actual power load in the user area at the previous moment, and recording the difference as the predicted power load fluctuation value;
[0027] Calculating a residual between the predicted power load fluctuation value and the actual power load fluctuation value;
[0028] Presetting a residual threshold, and comparing the residual with the residual threshold;
[0029] When the residual is less than the residual threshold, determining that the actual power load fluctuation value is not power load abnormal data;
[0030] When the residual is greater than or equal to the residual threshold, the actual power load fluctuation value is determined to be the power load abnormality data, and the type of the power load abnormality data is identified, and the power load abnormality data of the same type is stored together.
[0031] Furthermore, when the analysis and judgment module analyzes the correlation between the actual power load abnormal data, it includes:
[0032]
[0033] Wherein, I(X;Y)≥0, which is 0 if and only if X is independent of Y, p(x,y) represents the joint probability distribution, which represents the probability of X=x and Y=y occurring simultaneously, p(x) and p(y) represent the marginal probability distribution, which represent the probabilities of X=x and Y=y respectively, X represents X-type actual power load abnormal data, Y represents Y-type actual power load abnormal data, x represents the xth actual power load abnormal data in the X-type actual power load abnormal data, and y represents the yth actual power load abnormal data in the Y-type actual power load abnormal data.
[0034] Furthermore, the analysis and judgment module is also used to analyze the correlation between the actual power load abnormality data of each type, compare the correlation with the correlation threshold, and determine the power load abnormality level according to the comparison result, including:
[0035] presetting a first preset correlation threshold and a second preset correlation threshold, the first preset correlation threshold being greater than the second preset correlation threshold, comparing the correlation with the first preset correlation threshold and the second preset correlation threshold, and determining the power load abnormality level according to the comparison result;
[0036] When the correlation is less than or equal to the first preset correlation threshold, the analysis and judgment module determines that the power load abnormality level is a first abnormality level;
[0037] When the correlation is greater than the first preset correlation threshold and less than or equal to the second preset correlation threshold, the analysis and judgment module determines that the power load abnormality level is the second abnormality level;
[0038] When the correlation is greater than the second preset correlation threshold, the analysis and judgment module determines that the power load abnormality level is the third abnormality level;
[0039] The first abnormality level is smaller than the second abnormality level, and the second abnormality level is smaller than the third abnormality level.
[0040] Furthermore, the analysis and judgment module is also used to compare the actual power load abnormality data with the historical power load abnormality database data, and to adjust the power load abnormality level according to the comparison result, including:
[0041] When the same data exists in the historical power load anomaly database, the data is updated to the historical power load anomaly database, and the current power load anomaly level is lowered by one level;
[0042] When the same data does not exist in the historical power load abnormality database, the data is updated to the historical power load abnormality database, the current power load abnormality level is increased by one level and an alarm is issued;
[0043] If the current power load abnormality level is the first abnormality level or the third abnormality level, there is no need to adjust the current power load abnormality level.
[0044] Furthermore, when the processing module adjusts the power load in the user area at the next moment according to the power load abnormality level, it includes:
[0045] Presetting a first preset adjustment time interval T1, a second preset adjustment time interval T2, and a third preset adjustment time interval T3;
[0046] When the power load abnormality level is the first abnormality level, selecting the third preset adjustment time interval T3 to adjust the power load in the user area at the next moment;
[0047] When the power load abnormality level is the second abnormality level, selecting the second preset adjustment time interval T2 to adjust the power load in the user area at the next moment;
[0048] When the power load abnormality level is the third abnormality level, selecting the first preset adjustment time interval T1 to adjust the power load in the user area at the next moment;
[0049] The first preset adjustment time interval T1 is smaller than the second preset adjustment time interval T2, and the second preset adjustment time interval T2 is smaller than the third preset adjustment time interval T3.
[0050] Furthermore, when the processing module adjusts the power load in the user area at the next moment according to the power load abnormality level, it also includes:
[0051] After determining the i-th preset adjustment time interval Ti, i=1, 2, 3, presetting the first preset power load adjustment scheme and the second preset power load adjustment scheme;
[0052] When the power load abnormality level is the first abnormality level, selecting the first preset power load adjustment plan;
[0053] When the power load abnormality level is the second abnormality level and / or the second abnormality level, selecting the second preset power load adjustment scheme;
[0054] Among them, the first preset power load adjustment plan is to send a load reduction notice to users, requiring users in the user area to reduce electricity consumption during peak hours; the second preset power load adjustment plan is to start a backup generator or implement cross-regional power allocation.
[0055] Compared with the prior art, the beneficial effect of the present invention is that the power load intelligent control system provided by the present application has a flexible and efficient power load abnormality processing mechanism. The system can detect the power load abnormality in the user area in real time, and automatically adjust the power load at the next moment according to the abnormal level to balance the power demand and supply and ensure the stable operation of the power system. When handling power load abnormal events, the system not only considers the abnormal level, but also combines the information of the historical power load abnormality database to formulate a more accurate adjustment plan. At the same time, the system also provides a variety of power load adjustment schemes, including load reduction notifications, starting standby generators, and implementing cross-regional power allocation, etc., to deal with abnormal events of different levels and types. These measures are intended to quickly respond to and handle abnormal events, reduce the impact on users' normal electricity consumption, and ensure the safety and stability of the power system. In addition, the system also has the ability of self-learning and optimization, can continuously update the historical power load abnormality database, and adjust the processing strategy according to new abnormal events to improve the adaptability and accuracy of the system. In short, the power load intelligent control system provided in this embodiment provides strong support and guarantee for users and power system managers, can effectively deal with a variety of power load abnormal events, and ensure the stable operation of the power system and the reliability of power supply.
[0056] In another aspect, the present invention also proposes a method for intelligently controlling power loads, comprising the following steps:
[0057] S100. Establish a historical database based on the power consumption in the user area, wherein the historical database includes a normal historical power consumption database and an abnormal historical power consumption database, wherein the historical database includes historical residential power consumption, historical commercial power consumption, historical industrial power consumption, and historical public utility power consumption, and the historical residential power consumption, historical commercial power consumption, historical industrial power consumption, and historical public utility power consumption correspond to historical moments;
[0058] S200. Collect the real-time power load in the user area, establish a power load data set according to the power load in the user area at the current moment, the power load data set includes the actual power load in the user area at the current moment and the actual power load in the user area at the previous moment, and obtain the actual power load fluctuation value according to the power load data set;
[0059] S300. Compare and screen the actual power load fluctuation value with the power load fluctuation value threshold, and determine whether the screened actual power load fluctuation value is actual power load abnormal data;
[0060] S400. Analyze the correlation between the actual power load abnormality data of each type, compare the correlation with the correlation threshold, and determine the power load abnormality level according to the comparison result;
[0061] S500. Compare the actual power load abnormality data with the historical power load abnormality database data, and adjust the power load abnormality level according to the comparison result;
[0062] S600. Adjust the power load in the user area at the next moment according to the power load abnormality level.
[0063] It is understandable that the above-mentioned intelligent control method and system of power load have the same beneficial effects, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0064] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:
[0065] Figure 1 A structural block diagram of the power load intelligent control system provided by an embodiment of the present invention;
[0066] Figure 2 A flow chart of a method for intelligently controlling electric loads provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0067] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0068] See also Figure 1 As shown, in some embodiments of the present application, this embodiment provides an intelligent control system for power loads, including:
[0069] A historical database module is used to establish a historical database based on the power consumption in the user area, wherein the historical database includes a historical normal power consumption database and a historical abnormal power consumption database, wherein the historical database includes historical residential power consumption, historical commercial power consumption, historical industrial power consumption and historical public utility power consumption, and the historical residential power consumption, historical commercial power consumption, historical industrial power consumption and historical public utility power consumption correspond to historical moments;
[0070] A collection module, used to collect real-time power load in the user area, establish a power load data set according to the power load in the user area at the current moment, the power load data set includes the actual power load in the user area at the current moment and the actual power load in the user area at the previous moment, and obtain the actual power load fluctuation value according to the power load data set;
[0071] An analysis and judgment module is used to compare and screen the actual power load fluctuation value with the power load fluctuation value threshold, and judge whether the screened actual power load fluctuation value is actual power load abnormal data;
[0072] The analysis and judgment module is also used to analyze the correlation between the actual power load abnormality data of each type, compare the correlation with the correlation threshold, and determine the power load abnormality level according to the comparison result;
[0073] The analysis and judgment module is also used to compare the actual power load abnormality data with the historical power load abnormality database data, and adjust the power load abnormality level according to the comparison result;
[0074] The processing module is used to adjust the power load in the user area at the next moment according to the power load abnormality level.
[0075] It can be seen that the historical database module is used to store historical electricity consumption data in the user area, providing a data basis for subsequent electricity consumption analysis; the acquisition module is used to capture the power load conditions in the user area in real time to ensure the real-time and accuracy of the data; the analysis and judgment module is used to conduct in-depth analysis and judgment on the collected real-time power load data, identify possible abnormal conditions, and classify and evaluate these abnormal conditions; the analysis and judgment module preliminarily judges whether the power load is abnormal by comparing the actual power load fluctuation value with the preset fluctuation value threshold. Once abnormal data is found, the analysis and judgment module will further analyze the correlation between these abnormal data to determine the level of power load abnormality; the processing module is used to make targeted adjustments to the power load in the user area at the next moment according to the determined power load abnormality level.
[0076] Specifically, the analysis and judgment module compares and screens the actual power load fluctuation value with the power load fluctuation value threshold, and the calculation formula of the power load fluctuation threshold is:
[0077] Y = μL + k·σL;
[0078] Among them, Y represents the power load fluctuation value threshold, μL represents the mean of the historical power load fluctuation value, σL represents the standard deviation of the historical power load fluctuation value, and k represents the adjustment factor;
[0079]
[0080] Lt=|X t -X t-1 |;
[0081] Among them, Lt represents the power load fluctuation value, X t represents the actual power load in the user area at the current moment, X t-1 represents the actual power load in the user area at the previous moment, and n represents the number of historical power load fluctuation values.
[0082] It can be seen that the calculation of the power load fluctuation threshold is based on the statistical characteristics of the historical power load fluctuation data. By calculating the mean (μL) and standard deviation (σL) of the historical power load fluctuation values and introducing the adjustment factor (k), we can obtain a dynamic threshold (Y) that can reflect the historical power load fluctuation trend. This threshold not only takes into account the average level of historical power load, but also its fluctuation, so it can more accurately reflect the actual power load in the user area. In this embodiment, the introduction of the adjustment factor (k) is to increase the flexibility and adaptability of the system. By adjusting the value of k, we can change the tightness of the threshold according to actual needs.
[0083] It is understandable that this embodiment also takes into account that different types of power load data (such as residential power load, commercial power load, industrial power load and public utility power load) may have different fluctuation characteristics. Therefore, in practical applications, we can calculate the power load fluctuation threshold for different power load types to achieve more accurate and effective power load anomaly detection.
[0084] Specifically, when the analysis and judgment module compares and screens the actual power load fluctuation value with the power load fluctuation value threshold, it also includes:
[0085] The actual power load fluctuation value is compared with the power load fluctuation value threshold, and small actual power load fluctuation values are eliminated;
[0086] When the actual power load fluctuation value is greater than the power load fluctuation value threshold, retaining the actual power load fluctuation value;
[0087] When the actual power load fluctuation value is less than or equal to the power load fluctuation value threshold, the actual power load fluctuation value is discarded.
[0088] It can be seen that by comparing and screening the actual power load fluctuation value with the power load fluctuation value threshold, those small fluctuation values that do not affect the stability of power consumption can be effectively removed, while those actual power load fluctuation values that exceed the threshold and may cause power consumption anomalies are retained. This can greatly reduce the work pressure of the subsequent analysis and judgment module and improve the operating efficiency of the entire system.
[0089] Specifically, when the analysis and judgment module determines whether the filtered actual power load fluctuation value is power load abnormal data, it includes:
[0090] Fitting an ARIMA model using data from the historical power load normal database;
[0091] Predicting the power load in the user area according to the ARIMA model, using the predicted power load data as the predicted power load in the user area at the current moment, then calculating the difference between the predicted power load in the user area at the current moment and the actual power load in the user area at the previous moment, and recording the difference as the predicted power load fluctuation value;
[0092] Calculating a residual between the predicted power load fluctuation value and the actual power load fluctuation value;
[0093] Presetting a residual threshold, and comparing the residual with the residual threshold;
[0094] When the residual is less than the residual threshold, determining that the actual power load fluctuation value is not power load abnormal data;
[0095] When the residual is greater than or equal to the residual threshold, the actual power load fluctuation value is determined to be the power load abnormality data, and the type of the power load abnormality data is identified, and the power load abnormality data of the same type is stored together.
[0096] It can be seen that in the process of identifying and processing abnormal power load data, this embodiment uses the ARIMA model (autoregressive integrated moving average model) to predict the power load in the user area. The ARIMA model is a statistical model widely used in time series data analysis. It can find the inherent laws between data by analyzing historical data and predict future data accordingly.
[0097] In this embodiment, the ARIMA model is fitted by using the data in the historical power load normal database, and then the power load at the next moment is predicted using the model; the residual between the predicted power load and the actual power load (i.e., the predicted power load fluctuation value) is calculated and compared with the actual power load fluctuation value, and the residual between the two can be obtained. This residual reflects the degree of difference between the actual power load and the predicted power load. If the difference is too large (i.e., the residual exceeds the preset threshold), then it can be determined that the actual power load fluctuation value at the current moment is an abnormal power load data.
[0098] Specifically, when the analysis and judgment module analyzes the correlation between the actual power load abnormal data, it includes:
[0099]
[0100] Wherein, I(X;Y)≥0, which is 0 if and only if X is independent of Y, p(x,y) represents the joint probability distribution, which represents the probability of X=x and Y=y occurring simultaneously, p(x) and p(y) represent the marginal probability distribution, which represent the probabilities of X=x and Y=y respectively, X represents X-type actual power load abnormal data, Y represents Y-type actual power load abnormal data, x represents the xth actual power load abnormal data in the X-type actual power load abnormal data, and y represents the yth actual power load abnormal data in the Y-type actual power load abnormal data.
[0101] It can be seen that in the analysis of actual power load abnormal data, the correlation between different types of abnormal data is evaluated by calculating the mutual information between them. Mutual information is a measure of the correlation between two random variables, which represents the amount of information contained in one random variable about another random variable. In this embodiment, after the analysis and judgment module identifies the power load abnormal data, it will further analyze the correlation between these abnormal data. By analyzing the mutual information between different types of actual power load abnormal data (such as type X and type Y), we can understand the degree of correlation between them. If the mutual information value is high, it means that there is a strong correlation between the two types of abnormal data, and it may be necessary to process the two anomalies at the same time to solve the fundamental problem. If the mutual information value is low, it means that the correlation between them is weak, and they may need to be processed separately.
[0102] Specifically, the analysis and judgment module is further used to analyze the correlation between the actual power load abnormality data of each type, compare the correlation with the correlation threshold, and determine the power load abnormality level according to the comparison result, including:
[0103] presetting a first preset correlation threshold and a second preset correlation threshold, the first preset correlation threshold being greater than the second preset correlation threshold, comparing the correlation with the first preset correlation threshold and the second preset correlation threshold, and determining the power load abnormality level according to the comparison result;
[0104] When the correlation is less than or equal to the first preset correlation threshold, the analysis and judgment module determines that the power load abnormality level is a first abnormality level;
[0105] When the correlation is greater than the first preset correlation threshold and less than or equal to the second preset correlation threshold, the analysis and judgment module determines that the power load abnormality level is the second abnormality level;
[0106] When the correlation is greater than the second preset correlation threshold, the analysis and judgment module determines that the power load abnormality level is the third abnormality level;
[0107] The first abnormality level is smaller than the second abnormality level, and the second abnormality level is smaller than the third abnormality level.
[0108] It can be seen that when the correlation between abnormal data is less than or equal to the first preset correlation threshold, it means that the correlation between these abnormal data is weak, and they may belong to independent or occasional abnormal events, so they are judged as the first abnormal level, which usually indicates some smaller or less serious abnormalities; when the correlation is greater than the first preset correlation threshold and less than or equal to the second preset correlation threshold, it means that there is a certain degree of correlation between these abnormal data, and they may belong to the same type of problems or abnormal events that affect each other, so they are judged as the second abnormal level, which usually indicates some medium-severity abnormalities; and when the correlation is greater than the second preset correlation threshold, it means that the correlation between these abnormal data is very strong, and they may belong to serious systemic problems or urgent abnormal events, so they are judged as the third abnormal level, which usually indicates some serious or urgent abnormalities that need to be handled immediately.
[0109] Specifically, the analysis and judgment module is further used to compare the actual power load abnormality data with the historical power load abnormality database data, and to adjust the power load abnormality level according to the comparison result, including:
[0110] When the same data exists in the historical power load anomaly database, the data is updated to the historical power load anomaly database, and the current power load anomaly level is lowered by one level;
[0111] When the same data does not exist in the historical power load abnormality database, the data is updated to the historical power load abnormality database, the current power load abnormality level is increased by one level and an alarm is issued;
[0112] If the current power load abnormality level is the first abnormality level or the third abnormality level, there is no need to adjust the current power load abnormality level.
[0113] It can be seen that when there is data identical to the current actual power load abnormality data in the historical power load abnormality database, this means that this abnormality may be a recurring problem or an abnormality that has had similar processing experience. In this case, the analysis and judgment module will update the relevant data to the historical power load abnormality database and lower the current power load abnormality level by one level. This is because for known or recurring problems, we may already have a relatively mature processing solution, so its urgency and severity will be relatively low. On the contrary, if there is no data identical to the current actual power load abnormality data in the historical power load abnormality database, then this may be a completely new and unknown problem. In this case, the analysis and judgment module will update the relevant data to the historical power load abnormality database, raise the current power load abnormality level by one level and issue an alarm. This is to remind relevant personnel to pay attention to this new abnormal situation and take measures to deal with it as soon as possible to prevent the problem from further deteriorating or spreading.
[0114] Specifically, when the processing module adjusts the power load in the user area at the next moment according to the power load abnormality level, it includes:
[0115] Presetting a first preset adjustment time interval T1, a second preset adjustment time interval T2, and a third preset adjustment time interval T3;
[0116] When the power load abnormality level is the first abnormality level, selecting the third preset adjustment time interval T3 to adjust the power load in the user area at the next moment;
[0117] When the power load abnormality level is the second abnormality level, selecting the second preset adjustment time interval T2 to adjust the power load in the user area at the next moment;
[0118] When the power load abnormality level is the third abnormality level, selecting the first preset adjustment time interval T1 to adjust the power load in the user area at the next moment;
[0119] The first preset adjustment time interval T1 is smaller than the second preset adjustment time interval T2, and the second preset adjustment time interval T2 is smaller than the third preset adjustment time interval T3.
[0120] It can be seen that when the power load abnormality level is the first abnormality level, since the correlation between these abnormal data is weak, they may belong to independent or occasional abnormal events, so a longer third preset adjustment time interval T3 is selected for adjustment to ensure the stable operation of the system and avoid excessive adjustment; when the power load abnormality level is the second abnormality level, there is a certain correlation between these abnormal data, which may belong to the same type of problems or abnormal events that affect each other, so they need to be responded and processed more quickly, so a shorter second preset adjustment time interval T2 is selected for adjustment; and when the power load abnormality level is the third abnormality level, the correlation between these abnormal data is very strong, which may belong to serious systemic problems or urgent abnormal events, and immediate measures need to be taken to deal with them, so the shortest first preset adjustment time interval T1 is selected for adjustment to ensure the safety and stability of the system.
[0121] It is understandable that when the same data exists in the historical power load anomaly database, it means that this abnormal event has occurred before and the system already has a certain processing capability. Therefore, after updating the database, the current power load anomaly level is lowered by one level to reduce unnecessary tension and processing costs. When the same data does not exist in the historical power load anomaly database, it means that this is a new abnormal event that needs to be handled more carefully. Therefore, after updating the database, the current power load anomaly level is raised by one level and an alarm is issued to remind relevant personnel to pay attention and take measures to deal with it as soon as possible.
[0122] Specifically, when the processing module adjusts the power load in the user area at the next moment according to the power load abnormality level, it also includes:
[0123] After determining the i-th preset adjustment time interval Ti, i=1, 2, 3, presetting the first preset power load adjustment scheme and the second preset power load adjustment scheme;
[0124] When the power load abnormality level is the first abnormality level, selecting the first preset power load adjustment plan;
[0125] When the power load abnormality level is the second abnormality level and / or the second abnormality level, selecting the second preset power load adjustment scheme;
[0126] Among them, the first preset power load adjustment plan is to send a load reduction notice to users, requiring users in the user area to reduce electricity consumption during peak hours; the second preset power load adjustment plan is to start a backup generator or implement cross-regional power allocation.
[0127] It can be seen that when dealing with power load abnormal events, in addition to selecting an appropriate adjustment time interval according to the abnormal level, it is also necessary to formulate and implement corresponding power load adjustment plans according to specific circumstances. These adjustment plans are intended to balance user needs, system safety and the stability of power supply. For the first abnormal level, due to its relatively low abnormality and weak correlation between abnormal data, we tend to adopt a milder adjustment plan. Specifically, when the power load abnormality level is the first abnormal level, the processing module will select the first preset power load adjustment plan, that is, send a load reduction notification to the user. This plan aims to reduce the burden on the power system by guiding users to reduce electricity consumption during peak hours while avoiding excessive impact on users. In this way, while ensuring the stable operation of the system, the impact on the normal power consumption of users can be minimized. However, for the second and third abnormal levels, due to their high abnormality and strong correlation between abnormal data, we need to adopt a more active adjustment plan. Specifically, when the power load abnormality level is the second abnormal level or the third abnormal level, the processing module will select the second preset power load adjustment plan. This plan includes measures such as starting a backup generator or implementing cross-regional power allocation. The startup of backup generators can quickly increase power supply to cope with sudden increases in power demand, while cross-regional power allocation can make full use of power resources between regions to achieve optimal configuration of power supply. These measures are aimed at quickly responding to and handling abnormal events to ensure the safety and stability of the power system.
[0128] In summary, the power load intelligent control system provided in this embodiment has a flexible and efficient power load abnormality processing mechanism. The system can detect power load anomalies in the user area in real time, and automatically adjust the power load at the next moment according to the abnormal level to balance power demand and supply and ensure the stable operation of the power system. When handling power load abnormal events, the system not only considers the abnormal level, but also combines the information of the historical power load abnormal database to formulate a more accurate adjustment plan. At the same time, the system also provides a variety of power load adjustment schemes, including load reduction notifications, starting standby generators, and implementing cross-regional power allocation, etc., to deal with abnormal events of different levels and types. These measures are intended to quickly respond to and handle abnormal events, reduce the impact on users' normal electricity consumption, and ensure the safety and stability of the power system. In addition, the system also has the ability of self-learning and optimization, can continuously update the historical power load abnormal database, and adjust the processing strategy according to new abnormal events to improve the adaptability and accuracy of the system. In short, the power load intelligent control system provided in this embodiment provides strong support and guarantee for users and power system managers, and can effectively deal with a variety of power load abnormal events to ensure the stable operation of the power system and the reliability of power supply.
[0129] See also Figure 2 As shown, in some embodiments of the present application, this embodiment provides a method for intelligently controlling power loads, comprising the following steps:
[0130] S100. Establish a historical database based on the power consumption in the user area, wherein the historical database includes a normal historical power consumption database and an abnormal historical power consumption database, wherein the historical database includes historical residential power consumption, historical commercial power consumption, historical industrial power consumption, and historical public utility power consumption, and the historical residential power consumption, historical commercial power consumption, historical industrial power consumption, and historical public utility power consumption correspond to historical moments;
[0131] S200. Collect the real-time power load in the user area, establish a power load data set according to the power load in the user area at the current moment, the power load data set includes the actual power load in the user area at the current moment and the actual power load in the user area at the previous moment, and obtain the actual power load fluctuation value according to the power load data set;
[0132] S300. Compare and screen the actual power load fluctuation value with the power load fluctuation value threshold, and determine whether the screened actual power load fluctuation value is actual power load abnormal data;
[0133] S400. Analyze the correlation between the actual power load abnormality data of each type, compare the correlation with the correlation threshold, and determine the power load abnormality level according to the comparison result;
[0134] S500. Compare the actual power load abnormality data with the historical power load abnormality database data, and adjust the power load abnormality level according to the comparison result;
[0135] S600. Adjust the power load in the user area at the next moment according to the power load abnormality level.
[0136] It can be seen that, through the above steps, the intelligent control method of electric load provided in this embodiment realizes comprehensive monitoring and intelligent adjustment of the power consumption in the user area. First, by establishing a historical database, including a historical normal power consumption database and a historical abnormal power consumption database, a data basis is provided for subsequent abnormal judgment and adjustment of power consumption. Secondly, by real-time acquisition of the power load in the user area, establishing a power load data set, and calculating the actual power load fluctuation value, the abnormal power load situation can be discovered in time. Then, by analyzing the correlation between the actual power load abnormal data and comparing it with the correlation threshold, the abnormal power load level can be determined, which provides a basis for subsequent adjustments. Then, by comparing the actual power load abnormal data with the historical power load abnormal database data, the abnormal power load level can be adjusted to more accurately reflect the current abnormal power load situation. Finally, the power load in the user area at the next moment is adjusted according to the abnormal power load level to ensure the safety and stability of the power system.
[0137] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0138] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0139] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0140] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0141] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.
Claims
1. An intelligent control system for electric loads, characterized in that: include: A historical database module is used to establish a historical database based on the power consumption in the user area, wherein the historical database includes a historical normal power consumption database and a historical abnormal power consumption database, wherein the historical database includes historical residential power consumption, historical commercial power consumption, historical industrial power consumption and historical public utility power consumption, and the historical residential power consumption, historical commercial power consumption, historical industrial power consumption and historical public utility power consumption correspond to historical moments; A collection module, used to collect real-time power load in the user area, establish a power load data set according to the power load in the user area at the current moment, the power load data set includes the actual power load in the user area at the current moment and the actual power load in the user area at the previous moment, and obtain the actual power load fluctuation value according to the power load data set; An analysis and judgment module is used to compare and screen the actual power load fluctuation value with the power load fluctuation value threshold, and judge whether the screened actual power load fluctuation value is actual power load abnormal data; The analysis and judgment module is also used to analyze the correlation between the actual power load abnormality data of each type, compare the correlation with the correlation threshold, and determine the power load abnormality level according to the comparison result; The analysis and judgment module is also used to compare the actual power load abnormality data with the historical power load abnormality database data, and adjust the power load abnormality level according to the comparison result; The processing module is used to adjust the power load in the user area at the next moment according to the power load abnormality level.
2. The intelligent control system for electric load according to claim 1 is characterized in that: The analysis and judgment module compares and screens the actual power load fluctuation value with the power load fluctuation value threshold, and the calculation formula of the power load fluctuation threshold is: Y = μL + k·σL; Among them, Y represents the power load fluctuation value threshold, μL represents the mean of the historical power load fluctuation value, σL represents the standard deviation of the historical power load fluctuation value, and k represents the adjustment factor; Lt=|X t -X t-1 |; Among them, Lt represents the power load fluctuation value, X t represents the actual power load in the user area at the current moment, X t-1 represents the actual power load in the user area at the previous moment, and n represents the number of historical power load fluctuation values.
3. The intelligent control system for electric load according to claim 2 is characterized in that: When the analysis and judgment module compares and screens the actual power load fluctuation value with the power load fluctuation value threshold, it also includes: The actual power load fluctuation value is compared with the power load fluctuation value threshold, and small actual power load fluctuation values are eliminated; When the actual power load fluctuation value is greater than the power load fluctuation value threshold, retaining the actual power load fluctuation value; When the actual power load fluctuation value is less than or equal to the power load fluctuation value threshold, the actual power load fluctuation value is discarded.
4. The intelligent control system for electric load according to claim 3 is characterized in that: When the analysis and judgment module judges whether the filtered actual power load fluctuation value is power load abnormal data, it includes: Fitting an ARIMA model using data from the historical power load normal database; Predicting the power load in the user area according to the ARIMA model, using the predicted power load data as the predicted power load in the user area at the current moment, then calculating the difference between the predicted power load in the user area at the current moment and the actual power load in the user area at the previous moment, and recording the difference as the predicted power load fluctuation value; Calculating a residual between the predicted power load fluctuation value and the actual power load fluctuation value; Presetting a residual threshold, and comparing the residual with the residual threshold; When the residual is less than the residual threshold, determining that the actual power load fluctuation value is not power load abnormal data; When the residual is greater than or equal to the residual threshold, the actual power load fluctuation value is determined to be the power load abnormality data, and the type of the power load abnormality data is identified, and the power load abnormality data of the same type is stored together.
5. The intelligent control system for electric load according to claim 4 is characterized in that: When the analysis and judgment module analyzes the correlation between the actual power load abnormal data, it includes: Wherein, I(X;Y)≥0, which is 0 if and only if X is independent of Y, p(x,y) represents the joint probability distribution, which represents the probability of X=x and Y=y occurring simultaneously, p(x) and p(y) represent the marginal probability distribution, which represent the probabilities of X=x and Y=y respectively, X represents X-type actual power load abnormal data, Y represents Y-type actual power load abnormal data, x represents the xth actual power load abnormal data in the X-type actual power load abnormal data, and y represents the yth actual power load abnormal data in the Y-type actual power load abnormal data.
6. The intelligent control system for electric load according to claim 5 is characterized in that: The analysis and judgment module is also used to analyze the correlation between the actual power load abnormality data of each type, compare the correlation with the correlation threshold, and determine the power load abnormality level according to the comparison result, including: presetting a first preset correlation threshold and a second preset correlation threshold, the first preset correlation threshold being greater than the second preset correlation threshold, comparing the correlation with the first preset correlation threshold and the second preset correlation threshold, and determining the power load abnormality level according to the comparison result; When the correlation is less than or equal to the first preset correlation threshold, the analysis and judgment module determines that the power load abnormality level is a first abnormality level; When the correlation is greater than the first preset correlation threshold and less than or equal to the second preset correlation threshold, the analysis and judgment module determines that the power load abnormality level is the second abnormality level; When the correlation is greater than the second preset correlation threshold, the analysis and judgment module determines that the power load abnormality level is the third abnormality level; The first abnormality level is smaller than the second abnormality level, and the second abnormality level is smaller than the third abnormality level.
7. The intelligent control system for electric load according to claim 6 is characterized in that: The analysis and judgment module is also used to compare the actual power load abnormality data with the historical power load abnormality database data, and adjust the power load abnormality level according to the comparison result, including: When the same data exists in the historical power load anomaly database, the data is updated to the historical power load anomaly database, and the current power load anomaly level is lowered by one level; When the same data does not exist in the historical power load abnormality database, the data is updated to the historical power load abnormality database, the current power load abnormality level is increased by one level and an alarm is issued; If the current power load abnormality level is the first abnormality level or the third abnormality level, there is no need to adjust the current power load abnormality level.
8. The intelligent control system for electric load according to claim 7 is characterized in that: When the processing module adjusts the power load in the user area at the next moment according to the power load abnormality level, it includes: Presetting a first preset adjustment time interval T1, a second preset adjustment time interval T2, and a third preset adjustment time interval T3; When the power load abnormality level is the first abnormality level, selecting the third preset adjustment time interval T3 to adjust the power load in the user area at the next moment; When the power load abnormality level is the second abnormality level, selecting the second preset adjustment time interval T2 to adjust the power load in the user area at the next moment; When the power load abnormality level is the third abnormality level, selecting the first preset adjustment time interval T1 to adjust the power load in the user area at the next moment; The first preset adjustment time interval T1 is smaller than the second preset adjustment time interval T2, and the second preset adjustment time interval T2 is smaller than the third preset adjustment time interval T3.
9. The intelligent control system for electric load according to claim 8, characterized in that: When the processing module adjusts the power load in the user area at the next moment according to the power load abnormality level, it also includes: After determining the i-th preset adjustment time interval Ti, i=1, 2, 3, presetting the first preset power load adjustment scheme and the second preset power load adjustment scheme; When the power load abnormality level is the first abnormality level, selecting the first preset power load adjustment plan; When the power load abnormality level is the second abnormality level and / or the second abnormality level, selecting the second preset power load adjustment scheme; Among them, the first preset power load adjustment plan is to send a load reduction notice to users, requiring users in the user area to reduce electricity consumption during peak hours; the second preset power load adjustment plan is to start a backup generator or implement cross-regional power allocation.
10. An intelligent control method for electric loads, applied to the intelligent control system for electric loads as claimed in any one of claims 1 to 9, characterized in that: include: Establish a historical database based on the power consumption in the user area, wherein the historical database includes a historical normal power consumption database and a historical abnormal power consumption database, wherein the historical database includes historical residential power consumption, historical commercial power consumption, historical industrial power consumption and historical public utility power consumption, and the historical residential power consumption, historical commercial power consumption, historical industrial power consumption and historical public utility power consumption correspond to historical moments; Collecting real-time power load in the user area, establishing a power load data set according to the power load in the user area at the current moment, the power load data set including the actual power load in the user area at the current moment and the actual power load in the user area at the previous moment, and obtaining the actual power load fluctuation value according to the power load data set; Compare and screen the actual power load fluctuation value with the power load fluctuation value threshold, and determine whether the screened actual power load fluctuation value is actual power load abnormal data; Analyze the correlation between the actual power load abnormality data of each type, compare the correlation with the correlation threshold, and determine the power load abnormality level according to the comparison result; Comparing the actual power load abnormality data with the historical power load abnormality database data, and adjusting the power load abnormality level according to the comparison result; The power load in the user area at the next moment is adjusted according to the power load abnormality level.
