CN118014386A - Regional power utilization enterprise data trend analysis system, method and medium - Google Patents
Regional power utilization enterprise data trend analysis system, method and medium Download PDFInfo
- Publication number
- CN118014386A CN118014386A CN202410029627.3A CN202410029627A CN118014386A CN 118014386 A CN118014386 A CN 118014386A CN 202410029627 A CN202410029627 A CN 202410029627A CN 118014386 A CN118014386 A CN 118014386A
- Authority
- CN
- China
- Prior art keywords
- data
- power
- time sequence
- trend
- enterprise
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 89
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000002146 bilateral effect Effects 0.000 claims abstract description 80
- 238000001514 detection method Methods 0.000 claims abstract description 73
- 230000002159 abnormal effect Effects 0.000 claims abstract description 62
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 58
- 238000004364 calculation method Methods 0.000 claims abstract description 17
- 238000006243 chemical reaction Methods 0.000 claims abstract description 17
- 230000005611 electricity Effects 0.000 claims description 48
- 239000011159 matrix material Substances 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 22
- 230000007774 longterm Effects 0.000 claims description 21
- 230000008859 change Effects 0.000 claims description 20
- 238000009499 grossing Methods 0.000 claims description 19
- 238000004422 calculation algorithm Methods 0.000 claims description 18
- 230000000737 periodic effect Effects 0.000 claims description 15
- 230000035772 mutation Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 7
- 238000013139 quantization Methods 0.000 claims description 5
- 239000000654 additive Substances 0.000 claims description 3
- 230000000996 additive effect Effects 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 abstract description 5
- 238000011161 development Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 7
- 230000002776 aggregation Effects 0.000 description 6
- 238000004220 aggregation Methods 0.000 description 6
- 238000010248 power generation Methods 0.000 description 6
- 230000009977 dual effect Effects 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 230000004044 response Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000001932 seasonal effect Effects 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- 238000002759 z-score normalization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the technical field of data analysis and discloses a regional power utilization enterprise data trend analysis system, method and medium, wherein the system comprises a power utilization enterprise time sequence data conversion module, a target power time sequence data generation module, a time sequence decomposition module, a bilateral detection trend calculation module and a power utilization enterprise data trend analysis module, and is used for converting power utilization enterprise enhancement data into power utilization enterprise time sequence data; detecting abnormal power consumption enterprise time sequence data of the power consumption enterprise time sequence data, and generating target power time sequence data according to the abnormal power consumption enterprise time sequence data; performing time sequence decomposition on the target power time sequence data; generating power utilization enterprise time sequence trend data according to the trend component data, and calculating bilateral detection trend of the power utilization enterprise time sequence data through the power utilization enterprise time sequence trend data; and carrying out trend analysis on the power utilization enterprise data by using the trend graph. The invention can improve the accuracy of the trend analysis of the data of the power utilization enterprises.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to a regional power utilization enterprise data trend analysis system, method and medium.
Background
Along with the rapid development of economy and society, the power industry gradually becomes one of key supporting industries for national economy development, the power industry becomes one of the most important basic industries in national economy, the power industry is an indispensable energy supply guarantee for promoting development of various fields such as industry, agriculture, service industry, informatization construction and the like, along with the continuous increase of power demand, the complexity and operation difficulty of a power system are also continuously increased, and therefore, data trend analysis is required to be carried out on the power industry so as to ensure the stable operation of the power industry.
The existing data trend technology in the power industry is mainly used for finding out rules and trends of historical data of power enterprises by analyzing the historical data. In practical application, analysis intelligence is carried out on historical data to analyze and predict known rules and trends, and new modes and trends are difficult to find, so that data trend analysis of an electricity utilization enterprise is too one-sided, and accuracy in the process of carrying out data trend analysis of the electricity utilization enterprise is low.
Disclosure of Invention
The invention provides a regional power utilization enterprise data trend analysis system, method and medium, and mainly aims to solve the problem of accuracy in power utilization enterprise data trend analysis.
In order to achieve the above object, the present invention provides a regional power consumption enterprise data trend analysis system, which includes a power consumption enterprise time sequence data conversion module, a target power time sequence data generation module, a time sequence decomposition module, a bilateral detection trend calculation module, and a power consumption enterprise data trend analysis module, wherein,
The power utilization enterprise time sequence data conversion module is used for acquiring power utilization enterprise data of a target area, carrying out data enhancement data on the power utilization enterprise data to obtain power utilization enterprise enhancement data, and converting the power utilization enterprise enhancement data into power utilization enterprise time sequence data;
The target power time sequence data generation module is configured to detect abnormal power consumption time sequence data of the power consumption enterprise time sequence data by using a preset double weight algorithm, and generate target power time sequence data corresponding to the power consumption enterprise time sequence data according to the abnormal power consumption time sequence data, where the method is specifically configured to:
Calculating the power data average value of the time sequence data of the power utilization enterprise; calculating the power weight of each time sequence data in the power utilization enterprise time sequence data according to the power data average value by using the following double weight algorithm:
Wherein, W ni is the power weight of the nth power utilization enterprise index data at the ith moment, x ni is the power value of the nth power utilization enterprise index data at the ith moment, B is the power data average value, k ni is the position serial number of the nth power utilization enterprise index data at the ith moment, a is the position serial number of the nearest time sequence data corresponding to the power data average value, and e is the sequence length of the time sequence data of the power utilization enterprise;
Selecting time sequence data with the power weight smaller than a preset weight threshold as abnormal time sequence data;
Collecting the abnormal time sequence data as abnormal time sequence data of the power utilization enterprise;
the time sequence decomposition module is used for performing time sequence decomposition on the target power time sequence data according to a preset decomposition window to obtain trend component data of the target power time sequence data;
The bilateral detection trend calculation module is used for generating power utilization enterprise time sequence trend data according to the trend component data, generating power data statistics through the power utilization enterprise time sequence trend data, and calculating bilateral detection trend of the power utilization enterprise time sequence data according to the power data statistics;
and the power utilization enterprise data trend analysis module is used for generating a power data trend matrix according to the power time sequence data and the bilateral detection trend, generating a trend chart of the power utilization enterprise data according to the power data trend matrix, and carrying out trend analysis on the power utilization enterprise data by utilizing the trend chart.
Optionally, when the power utilization enterprise time sequence data conversion module performs data enhancement data on the power utilization enterprise data to obtain power utilization enterprise enhancement data, the power utilization enterprise time sequence data conversion module is specifically configured to:
performing numerical quantization processing on the power utilization enterprise data to obtain first power utilization enterprise data;
Performing missing value processing on the first power utilization enterprise data to obtain second power utilization enterprise data;
performing outlier processing on the second electricity utilization enterprise data to obtain third electricity utilization enterprise data;
and carrying out standardized processing on the third electricity enterprise data to obtain electricity enterprise enhancement data.
Optionally, the power utilization enterprise time sequence data conversion module is specifically configured to, when converting the power utilization enterprise enhancement data into power utilization enterprise time sequence data:
the enhanced data of the power utilization enterprises are subjected to time sequence sorting according to a preset time stamp, and an initial power utilization enterprise data sequence is obtained;
the time stamp is in one-to-one correspondence with the power utilization enterprise enhancement data in the initial power utilization enterprise data sequence, so that time sequence corresponding data is obtained;
and generating the time sequence corresponding data into the power utilization enterprise time sequence data according to a preset time granularity.
Optionally, the time sequence decomposition module is specifically configured to, when performing time sequence decomposition on the target power time sequence data according to a preset decomposition window to obtain trend component data of the target power time sequence data:
performing preliminary decomposition on the target power time sequence data by using the following additive decomposition formula to obtain target power time sequence decomposition data:
Yt＝Rt+Qt
Wherein Y t is the power observation value of the target power time sequence data at the time t, R t is the power trend value of the target power time sequence data at the time t, and Q t is the power fluctuation value of the target power time sequence data at the time t;
performing smoothing operation on the target power time sequence data according to a preset decomposition window to obtain target power smoothing time sequence data;
Determining a trend value according to the power observed value of the target power smoothing time sequence data and the power trend value of the target power time sequence decomposition data, wherein the trend value calculation formula is as follows:
wherein R' t is a trend value at time t, Y t is a power observation value of target power time series data at time t, For initial fluctuation value at time t at the f+1st cycle,/>Is a smooth fluctuation value at the time t of the f+1st cycle;
And carrying out numerical fitting on the trend values to obtain trend component data of the target power time sequence data.
Optionally, the bilateral detection trend calculation module is specifically configured to, when generating the power data statistic from the power consumption enterprise time sequence trend data:
Calculating the sign value of the time sequence trend data of the power utilization enterprise through the following preset sign function:
wherein H is the symbol value, y j is the time sequence data value of the nth power utilization enterprise index data in the power utilization enterprise time sequence data at the j-th moment, and y n(j+1) is the time sequence data value of the nth power utilization enterprise index data in the power utilization enterprise time sequence data at the j+1-th moment;
generating a symbol sequence corresponding to the power utilization enterprise time sequence trend data according to the symbol value;
calculating power data statistics of the power utilization enterprise time sequence trend data according to the symbol sequence:
Wherein S is the power data statistic, H d is the d symbol value in the symbol sequence, and m is the sequence length of the symbol sequence.
Optionally, the bilateral detection trend calculation module is specifically configured to, when calculating the bilateral detection trend of the power consumption enterprise time series data according to the power data statistics:
calculating the power data variance of the power utilization enterprise time sequence trend data according to the symbol sequence;
Calculating a bilateral check value of the power utilization enterprise time sequence data according to the power data statistic and the power data variance:
wherein Z is the bilateral check value, S is the power data statistic, and D is the power data variance;
and determining the bilateral detection trend of the time sequence data of the power utilization enterprise according to the bilateral detection value.
Optionally, the power consumption enterprise data trend analysis module is specifically configured to, when generating a power data trend matrix according to the power time sequence data and the bilateral detection trend:
dividing the power time sequence data into power data types to obtain power time sequence type data;
Extracting a bilateral category detection trend in the bilateral detection trends;
And generating a power data trend matrix according to the power time sequence type data and the bilateral type detection trend.
Optionally, the trend analysis module of the electrical enterprise data is specifically configured to, when performing trend analysis on the electrical enterprise data by using the trend graph:
determining a long-term trend of the electricity enterprise data according to the overall change trend of the trend graph;
Determining a periodic trend of the electricity utilization enterprise data according to peaks and valleys of the trend graph;
Determining the mutation trend of the power utilization enterprise data according to the mutation points of the trend graph;
And determining multidimensional trend changes of the power utilization enterprise data according to the long-term trend, the periodic trend and the abrupt trend.
In order to solve the above problems, the present invention further provides a method for analyzing regional power consumption enterprise data trend, the method comprising:
acquiring power utilization enterprise data of a target area, performing data enhancement data on the power utilization enterprise data to obtain power utilization enterprise enhancement data, and converting the power utilization enterprise enhancement data into power utilization enterprise time sequence data;
Detecting abnormal power consumption enterprise time sequence data of the power consumption enterprise time sequence data by using a preset double weight algorithm, and generating target power time sequence data corresponding to the power consumption enterprise time sequence data according to the abnormal power consumption enterprise time sequence data;
performing time sequence decomposition on the target power time sequence data according to a preset decomposition window to obtain trend component data of the target power time sequence data;
generating power utilization enterprise time sequence trend data according to the trend component data, generating power data statistics through the power utilization enterprise time sequence trend data, and calculating bilateral detection trend of the power utilization enterprise time sequence data according to the power data statistics;
Generating a power data trend matrix according to the power time sequence data and the bilateral detection trend, generating a trend graph of the power enterprise data according to the power data trend matrix, and carrying out trend analysis on the power enterprise data by using the trend graph.
In order to solve the above-mentioned problems, the present invention further provides a computer readable storage medium having at least one computer program stored therein, the at least one computer program being executed by a processor in an electronic device to implement the above-mentioned regional power usage enterprise data trend analysis method.
The embodiment of the invention can timely discover abnormal events or faults in the power system by detecting the abnormal conditions in the time sequence data of the power enterprise; generating target power time sequence data according to the abnormal time sequence data, and analyzing the target power time sequence data to know the basic characteristics and rules of power enterprise data; the target power time sequence data is decomposed into trend component data and other component data through a time sequence decomposition technology, the trend component data reflects the trend of long-term change of the power system, and the trend of the power market and the trend of the load demand are judged; generating time sequence trend data of the power utilization enterprises according to the trend component data, calculating bilateral detection trend of the time sequence data of the power utilization enterprises through statistics, and intuitively displaying important information such as development trend, periodical change and the like of the power utilization enterprises through trend graphs and statistics; and the trend graph is utilized to analyze the trend of the power enterprise data, so that a decision maker can be helped to better understand the development dynamic of the power market, forecast the future power demand and supply condition and optimize the planning and scheduling of the power system. Therefore, the regional power utilization enterprise data trend analysis system, method and medium provided by the invention can solve the problem of lower accuracy in power utilization enterprise data trend analysis.
Drawings
FIG. 1 is a functional block diagram of a trend analysis system for regional power enterprises according to one embodiment of the present invention;
FIG. 2 is a flow chart of a method for operating a regional power utility data trend analysis system according to an embodiment of the present invention.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, the "plurality" generally includes at least two.
The words "if", as used herein, may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrase "if determined" or "if detected (stated condition or event)" may be interpreted as "when determined" or "in response to determination" or "when detected (stated condition or event)" or "in response to detection (stated condition or event), depending on the context.
In addition, the sequence of steps in the method embodiments described below is only an example and is not strictly limited.
In practice, a server device deployed for a regional power utility enterprise data trend analysis system may be comprised of one or more devices. The regional power consumption enterprise data trend analysis system can be realized as follows: service instance, virtual machine, hardware device. For example, the regional power utility data trend analysis system may be implemented as a service instance deployed on one or more devices in a cloud node. Briefly, the regional power consumption enterprise data trend analysis system may be understood as a software deployed on a cloud node, for providing a regional power consumption enterprise data trend analysis system for each user side. Or the regional power utility data trend analysis system may also be implemented as a virtual machine deployed on one or more devices in the cloud node. The virtual machine is provided with application software for managing each user side. Or the regional power consumption enterprise data trend analysis system can be realized as a service end formed by a plurality of hardware devices of the same or different types, and one or more hardware devices are arranged for providing the regional power consumption enterprise data trend analysis system for each user end.
In the implementation form, the regional power utilization enterprise data trend analysis system and the user side are mutually adapted. Namely, aiming at the regional power utilization enterprise data trend analysis system as an application installed on the cloud service platform, the user side is used as a client side for establishing communication connection with the application; or the regional power utilization enterprise data trend analysis system is realized as a website, and the user side is realized as a webpage; and then, the regional power utilization enterprise data trend analysis system is realized as a cloud service platform, and the user side is realized as an applet in the instant messaging application.
Referring to fig. 1, a functional block diagram of a trend analysis system for regional power enterprises according to an embodiment of the present invention is shown.
The regional power consumption enterprise data trend analysis system 100 of the present invention may be disposed in a cloud server, and in implementation form, may be used as one or more service devices, may also be used as an application installed on the cloud (for example, a server of a mobile service operator, a server cluster, etc.), or may also be developed as a website. Depending on the functions implemented, the regional power utility data trend analysis system 100 may include a power utility time series data conversion module 101, a target power time series data generation module 102, a time series decomposition module 103, a bilateral detection trend calculation module 104, and a power utility data trend analysis module 105. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the device, capable of being executed by the processor of the device and of performing a fixed function.
In the embodiment of the invention, in the regional power utilization enterprise data trend analysis system, each module can be independently realized and called with other modules. A call herein is understood to mean that a module may connect to a plurality of modules of another type and provide corresponding services to the plurality of modules to which it is connected. For example, the time sequence decomposition module may call the target power time sequence data generation module to obtain the information collected by the target power time sequence data generation module based on the characteristics, and in the regional power utilization enterprise data trend analysis system provided by the embodiment of the invention, the application range of the regional power utilization enterprise data trend analysis system architecture can be adjusted by adding the module and directly calling the module without modifying the program code, so that the purpose of quickly and flexibly expanding the regional power utilization enterprise data trend analysis system is achieved. In practical applications, the modules may be disposed in the same device or different devices, or may be service instances disposed in virtual devices, for example, in a cloud server.
The following description is directed to various components of the regional power utility data trend analysis system and specific workflows, respectively, in connection with specific embodiments:
The power consumption enterprise time sequence data conversion module 101 is configured to obtain power consumption enterprise data of a target area, perform data enhancement data on the power consumption enterprise data, obtain power consumption enterprise enhancement data, and convert the power consumption enterprise enhancement data into power consumption enterprise time sequence data.
In the embodiment of the present invention, the electricity consumption enterprise data refers to data related to regional electricity consumption enterprises, including information on electricity generation capacity, electricity consumption, electricity price, market scale, voltage, grid frequency, etc., where the electricity consumption enterprise data of the target area may be obtained from a pre-stored storage area through a computer sentence (such as a Java sentence, a Python sentence, etc.) with a data grabbing function, where the storage area includes, but is not limited to, a database and a blockchain.
Further, in order to obtain reliable power data for trend analysis of power utility data, data cleansing and processing of the power utility data is required.
In the embodiment of the invention, the power utilization enterprise enhancement data is power utilization enterprise data obtained by carrying out data preprocessing on the power utilization enterprise data which are originally collected so as to ensure the integrity of the power utilization enterprise data.
In the embodiment of the present invention, when the power consumption enterprise time sequence data conversion module 101 performs data enhancement data on the power consumption enterprise data to obtain power consumption enterprise enhancement data, the power consumption enterprise time sequence data conversion module is specifically configured to:
performing numerical quantization processing on the power utilization enterprise data to obtain first power utilization enterprise data;
Performing missing value processing on the first power utilization enterprise data to obtain second power utilization enterprise data;
performing outlier processing on the second electricity utilization enterprise data to obtain third electricity utilization enterprise data;
and carrying out standardized processing on the third electricity enterprise data to obtain electricity enterprise enhancement data.
In detail, firstly, the data which is not represented by the numerical value in the electric enterprise data is quantized into the electric enterprise data which is represented by the numerical value, if the market scale in the electric enterprise data is not represented by the numerical value, the market scale is required to be converted into the data which is represented by the numerical value, the market scale is large and can be represented by the numerical value 1, the market scale is small and can be represented by the numerical value-1, compared with the data which is already represented by the numerical value in the electric enterprise data, the numerical value quantization processing is not required, and the electric enterprise data after the numerical value quantization processing is further used as the first electric enterprise data, so that the missing value, the abnormal value and the standardization processing are carried out on the first electric enterprise data.
Specifically, the mode of the missing data is identified through a statistical method or a visualization tool (such as a heat map), if the proportion of the missing data is small, the missing samples or characteristics can be considered to be deleted directly, and for the numerical data, namely the first electrical enterprise data can fill in the missing values through interpolation methods (such as a mean value, a median value, linear interpolation and the like); after the missing value processing is carried out on the first power enterprise data, abnormal value processing is needed, namely abnormal values are detected on the second power enterprise data by using a statistical method, a box diagram and the like, abnormal values exceeding a certain range are truncated or processed by a conversion method, so that the influence of the abnormal values on a model is relieved, and the median can be used for the data of the unbalanced distribution to replace the mean value, so that the influence of the abnormal values is reduced; in addition, the repeated records in the data set can be searched and removed by using a repeated value detection method, one of the repeated records with the same identification characteristics and different other characteristics can be reserved, and other repeated records are deleted; finally, the third electrical enterprise data is normalized, that is, for the numerical type feature, the data is converted into a standard normal distribution with a mean value of 0 and a standard deviation of 1 by using normalization (Z-score normalization), and the feature value is scaled to a fixed range, usually [0,1], which is very useful for an algorithm (such as KNN) that needs to consider the weight between the features, so as to obtain the electrical enterprise enhancement data.
Further, after the power utilization enterprise data is subjected to data preprocessing, in order to better find the change trend of the power utilization enterprise data, the power utilization enterprise data needs to be time-sequenced, the time sequence data can better reflect the change trend in the power system, and the change rule, trend and periodicity in the power utilization enterprise can be better understood through time sequence data analysis, so that prediction and decision can be better carried out.
In the embodiment of the invention, the time sequence data of the power utilization enterprise refers to recording data related to power according to time sequence in a period of time.
In the embodiment of the present invention, when the power utilization enterprise time sequence data conversion module 101 converts the power utilization enterprise enhancement data into power utilization enterprise time sequence data, the power utilization enterprise time sequence data conversion module is specifically configured to:
the enhanced data of the power utilization enterprises are subjected to time sequence sorting according to a preset time stamp, and an initial power utilization enterprise data sequence is obtained;
the time stamp is in one-to-one correspondence with the power utilization enterprise enhancement data in the initial power utilization enterprise data sequence, so that time sequence corresponding data is obtained;
and generating the time sequence corresponding data into the power utilization enterprise time sequence data according to a preset time granularity.
In detail, the time stamp refers to a field for representing time in the determination data, and may be a specific time stamp, for example, a combination of date and time, or may be an indicator of a time interval, such as every hour, every day, etc.; the data are ordered according to the time stamps, the data are ensured to be arranged according to the time sequence, the data are converted into a time sequence form, each time point corresponds to one row of data, and each time point is ensured to have a corresponding observation value, so that an initial power utilization enterprise data sequence is obtained; the sequenced time stamps are in one-to-one correspondence with the corresponding power utilization enterprise enhancement data to form time sequence corresponding data, so that each time point can be ensured to have the corresponding power utilization enterprise enhancement data.
Specifically, according to preset time granularity (such as every hour, every day and every month), the corresponding time sequence data is aggregated or interpolated, so as to generate the time sequence data of the power utilization enterprise, the original time sequence corresponding data can be converted into more regular and easy-to-analyze time sequence data, and subsequent modeling and analysis are facilitated, wherein the aggregation treatment refers to that if the preset time granularity is larger than that of the original data, a plurality of data points can be combined into one data point in an aggregation mode, so that the data volume is reduced, the influence of data noise is reduced, and the aggregation method comprises, but is not limited to, average value aggregation, maximum value aggregation and minimum value aggregation, for example, if the time granularity of the original data is once every minute and the preset time granularity is once every hour, every 60 data points can be aggregated into one data point, and the average value, the maximum value or the minimum value of the 60 data points can be calculated as data of one hour; the interpolation processing means that if the preset time granularity is smaller than the time granularity of the original data, new data points can be generated according to the existing data points in an interpolation mode, so that the data density is increased, the accuracy and the reliability of the data are improved, and the interpolation method comprises but is not limited to linear interpolation, spline interpolation and polynomial interpolation. For example, if the time granularity of the raw data is once per hour and the preset time granularity is once per minute, 60 data points can be interpolated per hour in a linear interpolation manner, resulting in higher data density and more accuracy.
For example, when the electricity enterprise data collected at the time point t 1 is { a, B, C }, the time sequence corresponding data is t 1 - { a, B, C }, where a may be an electricity consumption amount, B may be an electricity generation amount, C may be a voltage, if the timestamp and the electricity enterprise enhancement data do not completely correspond, interpolation or other processing methods need to be performed to supplement, so as to generate electricity enterprise time sequence data, and finally, the generated electricity enterprise time sequence data is stored according to a fixed format, so as to facilitate subsequent analysis and processing.
Further, abnormal data in the generated power utilization enterprise time sequence data is required to be subjected to abnormal value detection processing, so that the data false alarm rate of the power utilization enterprise data is reduced, and unnecessary interference and loss are reduced.
The target power time sequence data generating module 102 is configured to detect abnormal power consumption time sequence data of the power consumption enterprise time sequence data by using a preset dual weight algorithm, and generate target power time sequence data corresponding to the power consumption enterprise time sequence data according to the abnormal power consumption time sequence data.
In the embodiment of the invention, the abnormal time sequence data of the voltage industry refers to abnormal power data, such as abnormal data of power consumption and abnormal data of power generation, in the time sequence data of the power utilization enterprise generated in real time.
In the embodiment of the present invention, when the target power time-series data generating module 102 detects abnormal time-series data of the power-consumption enterprise time-series data by using a preset dual weight algorithm, the method is specifically configured to:
calculating the power data average value of the time sequence data of the power utilization enterprise;
Calculating the power weight of each time sequence data in the power utilization enterprise time sequence data according to the power data average value by using the following double weight algorithm:
Wherein, W ni is the power weight of the nth power utilization enterprise index data at the ith moment, x ni is the power value of the nth power utilization enterprise index data at the ith moment, B is the power data average value, k ni is the position serial number of the nth power utilization enterprise index data at the ith moment, a is the position serial number of the nearest time sequence data corresponding to the power data average value, and e is the sequence length of the time sequence data of the power utilization enterprise;
Selecting time sequence data with the power weight smaller than a preset weight threshold as abnormal time sequence data;
And collecting the abnormal time sequence data as the abnormal time sequence data of the power utilization enterprise.
In detail, firstly, calculating the power data average value of the power utilization enterprise time sequence data, wherein the time sequence data corresponding to the power utilization index data in the power utilization enterprise time sequence data is (x 11,x12,…,x1i,…,x1t), x 1i is the power utilization at the ith moment, and x 1t is the power utilization at the t moment; the time sequence data corresponding to the power generation amount index in the time sequence data of the power utilization enterprise is (x 21,x22,…,x2i,…,x2t), wherein x 2i is the power generation amount at the ith moment, and x 2t is the power generation amount at the t moment; the time sequence data of the power utilization enterprise is (x n1,xn2,…,xni,…,xnt), wherein x ni is the nth power utilization enterprise index data at the ith moment, so that the power data average value corresponding to each time sequence data in the time sequence data of the power utilization enterprise is calculated, and the power weight of each time sequence data is calculated according to the power data average value.
Specifically, the dual weight algorithm combines the information of time weight and distance weight, can more comprehensively consider the abnormal situation of time sequence data, reduces the influence of the size of a time window on an abnormal detection result, and can improve the detection accuracy, wherein the former represents the robustness weight, calculates the difference value between the power value of the nth power utilization enterprise index data at the ith moment and the average value of the time sequence data, the latter represents the distance value between the nth power utilization enterprise index data at the ith moment and the position serial number corresponding to the nearest time sequence data close to the average value of the power utilization enterprise index data, represents the weight by distance, further calculates the power weight of each time sequence data, selects the data with the power weight smaller than the weight threshold as the abnormal time sequence data, and gathers all the abnormal time sequence data as the abnormal time sequence data of the power utilization enterprise.
For example, if the time series data corresponding to the power consumption index data in the time series data of the power consumption enterprise is (x 11,x12,…,x1i,…,x1t), the power data average value of the power consumption index data is calculated to be B 1, in the dual weighting algorithm, when n=1 in x ni, the power consumption index data is represented, so that the robustness weight of each time series data is calculated according to the former in the dual weighting algorithm, then the distance weight is calculated according to the latter, for example, the value of the power data average value B 1 is closest to the x 1i data in the time series data, if the distance weight of x 11 is calculated, k ni represents the position number of x 11, namely, the position number of k 11 is 1, and the position number of x 1i represents a, so that the distance between x 11 and x 1i is calculated, so as to obtain the distance weight, and finally, the power weight corresponding to x 11 is obtained as W 11.
Further, target power time sequence data corresponding to the power utilization enterprise time sequence data are generated according to the power utilization enterprise abnormal time sequence data, namely the power utilization enterprise abnormal time sequence data are screened out from the power utilization enterprise time sequence data, the power utilization enterprise data screened by the abnormal data are used as the target power time sequence data, no abnormal data in the target power time sequence data can be ensured, and accurate analysis of subsequent power utilization enterprise data is ensured.
Furthermore, through analyzing trend components of the target power time sequence data, the long-term trend of the data can be better known, so that the future development trend can be more accurately predicted.
The time sequence decomposition module 103 is configured to perform time sequence decomposition on the target power time sequence data according to a preset decomposition window, so as to obtain trend component data of the target power time sequence data.
In the embodiment of the invention, the trend component data refers to a part extracted from the target power time sequence data by a time sequence decomposition method, and represents the long-term trend in the data, and represents the change of the data on a longer time scale.
In the embodiment of the present invention, when the time-series decomposition module 103 performs time-series decomposition on the target power time-series data according to a preset decomposition window to obtain trend component data of the target power time-series data, the time-series decomposition module is specifically configured to:
performing preliminary decomposition on the target power time sequence data by using the following additive decomposition formula to obtain target power time sequence decomposition data:
Yt＝Rt+Qt
Wherein Y t is the power observation value of the target power time sequence data at the time t, R t is the power trend value of the target power time sequence data at the time t, and Q t is the power fluctuation value of the target power time sequence data at the time t;
performing smoothing operation on the target power time sequence data according to a preset decomposition window to obtain target power smoothing time sequence data;
Determining a trend value according to the power observed value of the target power smoothing time sequence data and the power trend value of the target power time sequence decomposition data, wherein the trend value calculation formula is as follows:
wherein R' t is a trend value at time t, Y t is a power observation value of target power time series data at time t, For initial fluctuation value at time t at the f+1st cycle,/>Is a smooth fluctuation value at the time t of the f+1st cycle;
And carrying out numerical fitting on the trend values to obtain trend component data of the target power time sequence data.
In detail, the target power time sequence data is firstly expressed as a trend component and a fluctuation component, so that the long-term trend change condition of the power enterprise data can be obtained, then the trend component is completely separated from the target power time sequence and the fluctuation component, so as to obtain trend component data, the target power time sequence data is firstly decomposed into a trend component R t and a fluctuation component Q t through a wig decomposition formula, wherein the power trend component R t represents the long-term trend change condition, the fluctuation component Q t reveals the fluctuation condition in a short term, Y t reflects the actual power consumption or generation condition, the long-term change trend of the power system can be determined through analyzing the power trend value, the stability and the reliability of the power system can be evaluated through analyzing the power fluctuation value, and meanwhile, the complexity and the dynamics of the power time sequence data can be better understood.
Specifically, according to a preset decomposition window, smoothing operation can be performed on the target power time sequence data to obtain the target power smoothing time sequence data, short-term fluctuation and noise can be removed through the smoothing operation, so that the data is smoother and more stable, long-term trends can be captured better, and a moving average method, an exponential smoothing method and the like can be adopted as the smoothing method. The moving average method is a common smoothing method, it realizes smoothing by calculating the mean value of data in a certain time window, assuming the preset decomposition window size is n, selecting a proper initial point as a starting point, calculating the mean value of data from t-n to t for each time t, as the target power smoothing time sequence data of t time, repeating the above steps until all times are processed, through such smoothing operation, the smoothed target power time sequence data can be obtained to better understand the long-term trend and characteristics of the power system, the smoothed data is generally more stable, the influence of noise and abnormal value is reduced, and the reliability and the interpretation of the data are improved.
Further, the trend value can be determined by the power observed value of the target power smoothing time sequence data and the power fluctuation value of the target power time sequence decomposition data, then the power fluctuation value at each moment is removed from the target power time sequence data, and the smoothed fluctuation value is added, so that the trend characteristic in the data can be better highlighted by adding the smoothed fluctuation value. The smoothed fluctuation values usually retain trend components, and highlight long-term variation trend and periodic characteristics of the data, so that the trends are more obvious and observable, namely, trend values at all moments can be obtained from the preliminarily decomposed power fluctuation values through continuous cyclic operation, and then numerical fitting is carried out on the decomposed trend values to obtain trend component data of target power time sequence data, for example, a time sequence corresponding to each moment t is calculated according to the trend value R' t, for example, from t=1 to t=N, the time sequence is fitted through a polynomial fitting method and an exponential fitting method, after numerical fitting is carried out, a fitting curve can be obtained, and then data corresponding to each moment in the fitting curve are determined to be trend component data.
Furthermore, the trend component data based on the decomposition can be expressed in time series, and trend prediction can be performed, namely, the development trend of the future power utilization enterprises can be presumed.
The bilateral detection trend calculation module 104 is configured to generate power consumption enterprise time sequence trend data according to the trend component data, generate power data statistics according to the power consumption enterprise time sequence trend data, and calculate the bilateral detection trend of the power consumption enterprise time sequence data according to the power data statistics.
In the embodiment of the invention, the trend component data is generated into the power consumption enterprise time sequence trend data according to the sequence of the time stamps, and the trend component data decomposed by each target power time sequence data is generated into the power consumption enterprise time sequence data, namely, the trend component data are recombined into the trend component data according to the time sequence, so that the power consumption enterprise time sequence trend data is obtained.
Furthermore, the data statistics is carried out according to the time sequence trend data of the power utilization enterprises, a large amount of data can be integrated into a plurality of simple statistics, such as average values, standard deviations and the like, which is beneficial to improving the readability and the understandability of the data, and meanwhile, the data comparison and analysis are convenient, such as the increase trend and the fluctuation range of the future power demand can be predicted by utilizing the statistics of the average values, the standard deviations and the like of the power demand.
In the embodiment of the invention, the electric power data statistics are based on the time sequence trend data of the electric power enterprises to judge the significance of the change trend of the electric power enterprises.
In the embodiment of the present invention, the bilateral detection trend calculation module 104 is specifically configured to, when generating the power data statistic from the power consumption enterprise time sequence trend data:
Calculating the sign value of the time sequence trend data of the power utilization enterprise through the following preset sign function:
wherein H is the symbol value, y j is the time sequence data value of the nth power utilization enterprise index data in the power utilization enterprise time sequence data at the j-th moment, and y n(j+1) is the time sequence data value of the nth power utilization enterprise index data in the power utilization enterprise time sequence data at the j+1-th moment;
generating a symbol sequence corresponding to the power utilization enterprise time sequence trend data according to the symbol value;
calculating power data statistics of the power utilization enterprise time sequence trend data according to the symbol sequence:
Wherein S is the power data statistic, H d is the d symbol value in the symbol sequence, and m is the sequence length of the symbol sequence.
In detail, firstly, calculating the sign value of the time sequence trend data of the electricity consumption enterprise through a sign function, converting the difference value between each adjacent data point of the time sequence data of the electricity consumption enterprise into a corresponding sign value, so as to help to analyze the trend and the characteristics of the electricity consumption enterprise, more intuitively observing the trend of the electricity consumption enterprise through calculating the difference value between the adjacent data points and converting the difference value into the sign value, if the sequence of the time sequence trend data of the electricity consumption enterprise is expressed as (y n1,yn2,…,yni,…,ynt), respectively calculating the difference value between the adjacent data points, if the difference value is larger than zero, determining the sign value between the adjacent data points as-1, if the difference value is equal to zero, determining the sign value between the adjacent data points as-1, if the difference value is smaller than zero, further generating a sign sequence according to the sign value of each adjacent time sequence data, such as y n1-yn2>0,yn2-yn3＜0,ynj-yn(j+1) =0, and the like, and calculating various statistics according to the sign sequence to comprehensively evaluating the trend and the characteristics of the electricity consumption enterprise.
Specifically, the power data statistics of the power utility time sequence trend data are calculated according to the symbol sequence, and the average value of all symbol values in the symbol sequence is calculated to be used as the power data statistics, and in addition, the standard deviation and the fluctuation rate can be calculated according to the symbol sequence, wherein the fluctuation rate refers to the standard deviation of the symbol sequence divided by the average value, so that the overall characteristics and the fluctuation of the power utility time sequence data can be better understood according to the power data statistics.
Further, by carrying out bilateral detection trend analysis on the power data statistics, the trend direction of the time sequence data of the power utilization enterprise and the significance degree of the trend can be obtained, and the method has comprehensiveness and accuracy compared with the method for observing the change of only a single data point.
In the embodiment of the invention, the bilateral detection trend refers to an increasing trend, a decreasing trend or a trend stability of power utilization enterprise data based on power utilization enterprise time sequence data analysis.
In the embodiment of the present invention, when the bilateral detection trend calculation module 104 calculates the bilateral detection trend of the time series data of the power consumption enterprise according to the power data statistics, the bilateral detection trend calculation module is specifically configured to:
calculating the power data variance of the power utilization enterprise time sequence trend data according to the symbol sequence;
Calculating a bilateral check value of the power utilization enterprise time sequence data according to the power data statistic and the power data variance:
wherein Z is the bilateral check value, S is the power data statistic, and D is the power data variance;
and determining the bilateral detection trend of the time sequence data of the power utilization enterprise according to the bilateral detection value.
In detail, the variance in the symbol sequence is counted, namely, the variance of all symbol values is calculated as the variance of the power data, the variance is a statistic for measuring the dispersion degree of the data, the variance of the time sequence trend data of the power enterprise is calculated by using the symbol sequence, so that the dispersion degree of the data in the trend can be known, the larger the variance is, the higher the fluctuation of the data in the trend is, and the lower the fluctuation of the data is otherwise; and further calculating the bilateral check value of the time sequence data of the power utilization enterprise according to the power data statistic and the power data variance.
Specifically, calculating a bilateral test value according to the electric power data statistic and the electric power data variance, firstly judging the positive and negative of the electric power data statistic S, and carrying the positive and negative of the electric power data statistic S into different formulas to obtain different test values, further judging the bilateral detection trend of the time sequence data of the electric power enterprise according to the test values, wherein the bilateral test value is a statistic for judging whether the data is obvious or not, if the bilateral test value is greater than zero, the data is shown to have obvious difference, and the sequence is shown to have an increasing trend; if the bilateral check value is smaller than zero, the data are shown to have significant differences, and the sequence is shown to have a decreasing trend; if the bilateral check value is equal to zero, the bilateral check value indicates that the data has no significant difference, and in the time sequence data analysis of the power utilization enterprises, the bilateral check value can judge whether the trend of the data is significant or not.
Further, by arranging the power data in a matrix in time series, the trend of the power data can be seen more intuitively, so that regularity and abnormality in the data can be found more easily.
The power consumption enterprise data trend analysis module 105 is configured to generate a power data trend matrix according to the power time sequence data and the bilateral detection trend, generate a trend graph of the power consumption enterprise data according to the power data trend matrix, and perform trend analysis on the power consumption enterprise data by using the trend graph.
In the embodiment of the present invention, the power data trend matrix refers to using power time sequence type data as a row dimension and using bilateral type detection trend as a column dimension, where each power time sequence type data corresponds to one bilateral type detection trend.
In the embodiment of the present invention, when the power consumption enterprise data trend analysis module 105 generates a power data trend matrix according to the power time series data and the bilateral detection trend, the power consumption enterprise data trend analysis module is specifically configured to:
dividing the power time sequence data into power data types to obtain power time sequence type data;
Extracting a bilateral category detection trend in the bilateral detection trends;
And generating a power data trend matrix according to the power time sequence type data and the bilateral type detection trend.
In detail, the power time sequence data is divided according to the power data types, such as the power data types including power consumption, power generation, voltage, power consumption price and the like, the power time sequence type data can be obtained, such as the power time sequence type data corresponding to the power consumption index is (y 11,y12,…,y1i,…,y1t), the power time sequence type data corresponding to the power generation index is (y 21,y22,…,y2i,…,y2t), the power time sequence type data corresponding to the voltage index is (y 31,y32,…,y3i,…,y3t), and the bilateral type detection trend is determined based on the bilateral detection value calculated by the power time sequence type data corresponding to each type, so that the power time sequence type data is used as a row dimension, the bilateral type detection trend is used as a column dimension, and then the power data trend matrix is generated.
For example, if the bilateral class detection trend corresponding to the electricity consumption index is an upward trend, the bilateral class detection trend corresponding to the electricity generation index is an upward trend, and the bilateral class detection trend corresponding to the voltage index is a downward trend, the power data trend matrix is
Further, the trend graph of the power enterprise data is constructed by the corresponding time sequence data and the bilateral detection trend in the power data trend matrix, the trend graph is generated by the corresponding time sequence data in the power time sequence type data, the horizontal axis represents time, the vertical axis represents the numerical value of the power enterprise data, and various tools and software can be utilized to draw the trend graph.
Furthermore, by analyzing the trend graph of the power enterprise data, long-term trends and modes can be identified, so that the overall development trend of power demand, supply and consumption can be known, and guidance is provided for future planning and decision making.
In the embodiment of the present invention, when the trend analysis module 105 performs trend analysis on the electrical enterprise data by using the trend graph, the trend analysis module is specifically configured to:
determining a long-term trend of the electricity enterprise data according to the overall change trend of the trend graph;
Determining a periodic trend of the electricity utilization enterprise data according to peaks and valleys of the trend graph;
Determining the mutation trend of the power utilization enterprise data according to the mutation points of the trend graph;
And determining multidimensional trend changes of the power utilization enterprise data according to the long-term trend, the periodic trend and the abrupt trend.
In detail, by observing the overall trend of the trend graph, such as linear increase, exponential increase, or periodic fluctuation, it is possible to determine the long-term trend of the electricity enterprise data, and then the long-term trend is whether the overall trend of the observed data shows an ascending, descending, or stationary trend; by observing peaks and valleys in the trend graph, i.e., periodic fluctuations, a periodic trend of the electricity enterprise data can be determined, which is helpful for identifying periodic patterns of electricity demand and supply over a particular season, month, or day of the week, and based on the periodic trend, electricity scheduling and resource planning can be optimized to meet peak demand and avoid supply shortages, then the seasonal trend is to find seasonal changes in the data, such as periodic seasonal peaks and valleys; the mutation points in the trend graph, namely abnormal and sudden data changes, can be observed to determine mutation trends of the power enterprise data, the mutation points are possibly caused by factors such as emergencies, equipment faults, policy adjustment and the like, the mutation trends are discovered and identified early, and corresponding measures can be taken to cope with the changes and mitigate potential risks.
Specifically, through the analysis results of comprehensive long-term trend, periodic trend and mutation trend, multidimensional trend change of the electricity consumption enterprise data can be determined, a more comprehensive visual angle can be provided, so that the change modes and trends of the electricity consumption enterprise on different time scales can be known, a decision maker can be helped to better know the long-term trend, the periodic change and mutation point by utilizing the trend graph to carry out trend analysis on the electricity consumption enterprise data, and trend change of multiple dimensions is comprehensively analyzed, so that management, planning and decision of the electricity consumption enterprise are guided.
The embodiment of the invention can timely discover abnormal events or faults in the power system by detecting the abnormal conditions in the time sequence data of the power enterprise; generating target power time sequence data according to the abnormal time sequence data, and analyzing the target power time sequence data to know the basic characteristics and rules of power enterprise data; the target power time sequence data is decomposed into trend component data and other component data through a time sequence decomposition technology, the trend component data reflects the trend of long-term change of the power system, and the trend of the power market and the trend of the load demand are judged; generating time sequence trend data of the power utilization enterprises according to the trend component data, calculating bilateral detection trend of the time sequence data of the power utilization enterprises through statistics, and intuitively displaying important information such as development trend, periodical change and the like of the power utilization enterprises through trend graphs and statistics; and the trend graph is utilized to analyze the trend of the power enterprise data, so that a decision maker can be helped to better understand the development dynamic of the power market, forecast the future power demand and supply condition and optimize the planning and scheduling of the power system. Therefore, the regional power utilization enterprise data trend analysis system, method and medium provided by the invention can solve the problem of lower accuracy in power utilization enterprise data trend analysis.
Referring to fig. 2, a flow chart of an operation method of the regional power-consumption enterprise data trend analysis system according to an embodiment of the present invention is shown. In this embodiment, the method for operating the regional power consumption enterprise data trend analysis system includes:
s1, acquiring power utilization enterprise data of a target area, performing data enhancement data on the power utilization enterprise data to obtain power utilization enterprise enhancement data, and converting the power utilization enterprise enhancement data into power utilization enterprise time sequence data;
S2, detecting abnormal power consumption enterprise time sequence data of the power consumption enterprise time sequence data by using a preset double weight algorithm, and generating target power time sequence data corresponding to the power consumption enterprise time sequence data according to the abnormal power consumption enterprise time sequence data;
S3, performing time sequence decomposition on the target power time sequence data according to a preset decomposition window to obtain trend component data of the target power time sequence data;
S4, generating power utilization enterprise time sequence trend data according to the trend component data, generating power data statistics through the power utilization enterprise time sequence trend data, and calculating bilateral detection trend of the power utilization enterprise time sequence data according to the power data statistics;
and S5, generating a power data trend matrix according to the power time sequence data and the bilateral detection trend, generating a trend chart of the power enterprise data according to the power data trend matrix, and carrying out trend analysis on the power enterprise data by using the trend chart.
The device implementing the method of operation for a regional power usage enterprise data trend analysis system may include a processor, a memory, a communication bus, and a communication interface, and may further include a computer program stored in the memory and executable on the processor, such as a regional power usage enterprise data trend analysis system program.
The regional power utility data trend analysis system program stored by the memory in the device is a combination of instructions that, when executed in the processor, implement:
acquiring power utilization enterprise data of a target area, performing data enhancement data on the power utilization enterprise data to obtain power utilization enterprise enhancement data, and converting the power utilization enterprise enhancement data into power utilization enterprise time sequence data;
Detecting abnormal power consumption enterprise time sequence data of the power consumption enterprise time sequence data by using a preset double weight algorithm, and generating target power time sequence data corresponding to the power consumption enterprise time sequence data according to the abnormal power consumption enterprise time sequence data;
performing time sequence decomposition on the target power time sequence data according to a preset decomposition window to obtain trend component data of the target power time sequence data;
generating power utilization enterprise time sequence trend data according to the trend component data, generating power data statistics through the power utilization enterprise time sequence trend data, and calculating bilateral detection trend of the power utilization enterprise time sequence data according to the power data statistics;
Generating a power data trend matrix according to the power time sequence data and the bilateral detection trend, generating a trend graph of the power enterprise data according to the power data trend matrix, and carrying out trend analysis on the power enterprise data by using the trend graph.
Specifically, the specific implementation method of the above instruction by the processor may refer to descriptions of related steps in the corresponding embodiment of the drawings, which are not repeated herein.
Further, the device-integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer-readable storage medium. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a Read-only memory (ROM).
The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, may implement:
acquiring power utilization enterprise data of a target area, performing data enhancement data on the power utilization enterprise data to obtain power utilization enterprise enhancement data, and converting the power utilization enterprise enhancement data into power utilization enterprise time sequence data;
Detecting abnormal power consumption enterprise time sequence data of the power consumption enterprise time sequence data by using a preset double weight algorithm, and generating target power time sequence data corresponding to the power consumption enterprise time sequence data according to the abnormal power consumption enterprise time sequence data;
performing time sequence decomposition on the target power time sequence data according to a preset decomposition window to obtain trend component data of the target power time sequence data;
generating power utilization enterprise time sequence trend data according to the trend component data, generating power data statistics through the power utilization enterprise time sequence trend data, and calculating bilateral detection trend of the power utilization enterprise time sequence data according to the power data statistics;
Generating a power data trend matrix according to the power time sequence data and the bilateral detection trend, generating a trend graph of the power enterprise data according to the power data trend matrix, and carrying out trend analysis on the power enterprise data by using the trend graph.
In the several embodiments provided by the present invention, it should be understood that the disclosed media, systems, and methods may be implemented in other ways. For example, the system embodiments described above are merely illustrative, e.g., the division of the modules is merely a logical function division, and other manners of division may be implemented in practice.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
The above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made thereto without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. A regional power consumption enterprise data trend analysis system is characterized by comprising a power consumption enterprise time sequence data conversion module, a target power time sequence data generation module, a time sequence decomposition module, a bilateral detection trend calculation module and a power consumption enterprise data trend analysis module, wherein,
The power utilization enterprise time sequence data conversion module is used for acquiring power utilization enterprise data of a target area, carrying out data enhancement data on the power utilization enterprise data to obtain power utilization enterprise enhancement data, and converting the power utilization enterprise enhancement data into power utilization enterprise time sequence data;
The target power time sequence data generation module is configured to detect abnormal power consumption time sequence data of the power consumption enterprise time sequence data by using a preset double weight algorithm, and generate target power time sequence data corresponding to the power consumption enterprise time sequence data according to the abnormal power consumption time sequence data, where the method is specifically configured to:
Calculating the power data average value of the time sequence data of the power utilization enterprise; calculating the power weight of each time sequence data in the power utilization enterprise time sequence data according to the power data average value by using the following double weight algorithm:
Wherein, W ni is the power weight of the nth power utilization enterprise index data at the ith moment, x ni is the power value of the nth power utilization enterprise index data at the ith moment, B is the power data average value, k ni is the position serial number of the nth power utilization enterprise index data at the ith moment, a is the position serial number of the nearest time sequence data corresponding to the power data average value, and e is the sequence length of the time sequence data of the power utilization enterprise;
Selecting time sequence data with the power weight smaller than a preset weight threshold as abnormal time sequence data;
Collecting the abnormal time sequence data as abnormal time sequence data of the power utilization enterprise;
the time sequence decomposition module is used for performing time sequence decomposition on the target power time sequence data according to a preset decomposition window to obtain trend component data of the target power time sequence data;
The bilateral detection trend calculation module is used for generating power utilization enterprise time sequence trend data according to the trend component data, generating power data statistics through the power utilization enterprise time sequence trend data, and calculating bilateral detection trend of the power utilization enterprise time sequence data according to the power data statistics;
and the power utilization enterprise data trend analysis module is used for generating a power data trend matrix according to the power time sequence data and the bilateral detection trend, generating a trend chart of the power utilization enterprise data according to the power data trend matrix, and carrying out trend analysis on the power utilization enterprise data by utilizing the trend chart.
2. The regional power utility data trend analysis system of claim 1, wherein the power utility time series data conversion module is configured to, when performing data enhancement on the power utility data to obtain power utility enhancement data:
performing numerical quantization processing on the power utilization enterprise data to obtain first power utilization enterprise data;
Performing missing value processing on the first power utilization enterprise data to obtain second power utilization enterprise data;
performing outlier processing on the second electricity utilization enterprise data to obtain third electricity utilization enterprise data;
and carrying out standardized processing on the third electricity enterprise data to obtain electricity enterprise enhancement data.
3. The regional power utility data trend analysis system of claim 1, wherein the power utility time series data conversion module is configured to, when converting the power utility enhancement data into power utility time series data:
the enhanced data of the power utilization enterprises are subjected to time sequence sorting according to a preset time stamp, and an initial power utilization enterprise data sequence is obtained;
the time stamp is in one-to-one correspondence with the power utilization enterprise enhancement data in the initial power utilization enterprise data sequence, so that time sequence corresponding data is obtained;
and generating the time sequence corresponding data into the power utilization enterprise time sequence data according to a preset time granularity.
4. The regional power utility data trend analysis system of claim 1, wherein the time series decomposition module is configured to, when performing time series decomposition on the target power time series data according to a preset decomposition window to obtain trend component data of the target power time series data:
performing preliminary decomposition on the target power time sequence data by using the following additive decomposition formula to obtain target power time sequence decomposition data:
Yt＝Rt+Qt
Wherein Y t is the power observation value of the target power time sequence data at the time t, R t is the power trend value of the target power time sequence data at the time t, and Q t is the power fluctuation value of the target power time sequence data at the time t;
performing smoothing operation on the target power time sequence data according to a preset decomposition window to obtain target power smoothing time sequence data;
Determining a trend value according to the power observed value of the target power smoothing time sequence data and the power trend value of the target power time sequence decomposition data, wherein the trend value calculation formula is as follows:
wherein R' t is a trend value at time t, Y t is a power observation value of target power time series data at time t, For initial fluctuation value at time t at the f+1st cycle,/>Is a smooth fluctuation value at the time t of the f+1st cycle;
And carrying out numerical fitting on the trend values to obtain trend component data of the target power time sequence data.
5. The regional power utility data trend analysis system of claim 1, wherein the bilateral detection trend calculation module is configured to, when generating power data statistics from the power utility time series trend data:
Calculating the sign value of the time sequence trend data of the power utilization enterprise through the following preset sign function:
wherein H is the symbol value, y j is the time sequence data value of the nth power utilization enterprise index data in the power utilization enterprise time sequence data at the j-th moment, and y n(j+1) is the time sequence data value of the nth power utilization enterprise index data in the power utilization enterprise time sequence data at the j+1-th moment;
generating a symbol sequence corresponding to the power utilization enterprise time sequence trend data according to the symbol value;
calculating power data statistics of the power utilization enterprise time sequence trend data according to the symbol sequence:
Wherein S is the power data statistic, H d is the d symbol value in the symbol sequence, and m is the sequence length of the symbol sequence.
6. The regional power utility data trend analysis system of claim 5, wherein the bilateral detection trend calculation module is configured to, when calculating the bilateral detection trend of the power utility time series data from the power data statistics:
calculating the power data variance of the power utilization enterprise time sequence trend data according to the symbol sequence;
Calculating a bilateral check value of the power utilization enterprise time sequence data according to the power data statistic and the power data variance:
wherein Z is the bilateral check value, S is the power data statistic, and D is the power data variance;
and determining the bilateral detection trend of the time sequence data of the power utilization enterprise according to the bilateral detection value.
7. The regional power utility data trend analysis system of claim 1, wherein the power utility data trend analysis module is configured to, when generating a power data trend matrix from the power time series data and the bilateral detection trend:
dividing the power time sequence data into power data types to obtain power time sequence type data;
Extracting a bilateral category detection trend in the bilateral detection trends;
And generating a power data trend matrix according to the power time sequence type data and the bilateral type detection trend.
8. The regional power utility data trend analysis system of claim 1, wherein the power utility data trend analysis module is operable, when utilizing the trend graph to trend the power utility data, to:
determining a long-term trend of the electricity enterprise data according to the overall change trend of the trend graph;
Determining a periodic trend of the electricity utilization enterprise data according to peaks and valleys of the trend graph;
Determining the mutation trend of the power utilization enterprise data according to the mutation points of the trend graph;
And determining multidimensional trend changes of the power utilization enterprise data according to the long-term trend, the periodic trend and the abrupt trend.
9. A method of operation for a regional power utility data trend analysis system, for executing the regional power utility data trend analysis system of any one of claims 1-8, the method comprising:
acquiring power utilization enterprise data of a target area, performing data enhancement data on the power utilization enterprise data to obtain power utilization enterprise enhancement data, and converting the power utilization enterprise enhancement data into power utilization enterprise time sequence data;
Detecting abnormal power consumption enterprise time sequence data of the power consumption enterprise time sequence data by using a preset double weight algorithm, and generating target power time sequence data corresponding to the power consumption enterprise time sequence data according to the abnormal power consumption enterprise time sequence data, wherein when the abnormal power consumption enterprise time sequence data of the power consumption enterprise time sequence data is detected by using the preset double weight algorithm, the abnormal power consumption enterprise time sequence data detection method is specifically used for:
Calculating the power data average value of the time sequence data of the power utilization enterprise; calculating the power weight of each time sequence data in the power utilization enterprise time sequence data according to the power data average value by using the following double weight algorithm:
Wherein, W ni is the power weight of the nth power utilization enterprise index data at the ith moment, x ni is the power value of the nth power utilization enterprise index data at the ith moment, B is the power data average value, k ni is the position serial number of the nth power utilization enterprise index data at the ith moment, a is the position serial number of the nearest time sequence data corresponding to the power data average value, and e is the sequence length of the time sequence data of the power utilization enterprise;
Selecting time sequence data with the power weight smaller than a preset weight threshold as abnormal time sequence data;
Collecting the abnormal time sequence data as abnormal time sequence data of the power utilization enterprise;
performing time sequence decomposition on the target power time sequence data according to a preset decomposition window to obtain trend component data of the target power time sequence data;
generating power utilization enterprise time sequence trend data according to the trend component data, generating power data statistics through the power utilization enterprise time sequence trend data, and calculating bilateral detection trend of the power utilization enterprise time sequence data according to the power data statistics;
Generating a power data trend matrix according to the power time sequence data and the bilateral detection trend, generating a trend graph of the power enterprise data according to the power data trend matrix, and carrying out trend analysis on the power enterprise data by using the trend graph.
10. A computer readable storage medium storing a computer program, which when executed by a processor implements the method of operation for a regional power utility data trend analysis system of claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410029627.3A CN118014386A (en) | 2024-01-08 | 2024-01-08 | Regional power utilization enterprise data trend analysis system, method and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410029627.3A CN118014386A (en) | 2024-01-08 | 2024-01-08 | Regional power utilization enterprise data trend analysis system, method and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118014386A true CN118014386A (en) | 2024-05-10 |
Family
ID=90944174
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410029627.3A Pending CN118014386A (en) | 2024-01-08 | 2024-01-08 | Regional power utilization enterprise data trend analysis system, method and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118014386A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951840A (en) * | 2014-03-24 | 2015-09-30 | 国网上海市电力公司 | Analysis method for overall electricity utilization trend of electric power market |
| WO2020087829A1 (en) * | 2018-10-31 | 2020-05-07 | 深圳壹账通智能科技有限公司 | Data trend analysis method and system, computer device and readable storage medium |
| CN112686491A (en) * | 2020-10-30 | 2021-04-20 | 国网浙江省电力有限公司台州供电公司 | Enterprise power data analysis method based on power consumption behavior |
| CN115563880A (en) * | 2022-10-25 | 2023-01-03 | 福建师范大学 | Enterprise power consumption abnormity detection method based on Isolated forest-variable point enhancement |
| CN115796937A (en) * | 2023-01-10 | 2023-03-14 | 佰聆数据股份有限公司 | Big data complex relevance electric power supply and demand trend analysis method and device |
| CN116894687A (en) * | 2023-06-16 | 2023-10-17 | 国网浙江省电力有限公司湖州供电公司 | Power consumption analysis method and system based on machine learning and electronic equipment |
-
2024
- 2024-01-08 CN CN202410029627.3A patent/CN118014386A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951840A (en) * | 2014-03-24 | 2015-09-30 | 国网上海市电力公司 | Analysis method for overall electricity utilization trend of electric power market |
| WO2020087829A1 (en) * | 2018-10-31 | 2020-05-07 | 深圳壹账通智能科技有限公司 | Data trend analysis method and system, computer device and readable storage medium |
| CN112686491A (en) * | 2020-10-30 | 2021-04-20 | 国网浙江省电力有限公司台州供电公司 | Enterprise power data analysis method based on power consumption behavior |
| CN115563880A (en) * | 2022-10-25 | 2023-01-03 | 福建师范大学 | Enterprise power consumption abnormity detection method based on Isolated forest-variable point enhancement |
| CN115796937A (en) * | 2023-01-10 | 2023-03-14 | 佰聆数据股份有限公司 | Big data complex relevance electric power supply and demand trend analysis method and device |
| CN116894687A (en) * | 2023-06-16 | 2023-10-17 | 国网浙江省电力有限公司湖州供电公司 | Power consumption analysis method and system based on machine learning and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 张东 等: "基于时间序列的用电数据趋势分析", 东北电力技术, vol. 41, no. 02, 31 December 2020 (2020-12-31), pages 27 - 29 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112199367B (en) | Long-time scale power balance check and big data analysis method and system | |
| CN116976707B (en) | User electricity consumption data anomaly analysis method and system based on electricity consumption data acquisition | |
| US20190369570A1 (en) | System and method for automatically detecting anomalies in a power-usage data set | |
| CN118037469B (en) | Financial management system based on big data | |
| CN116203352A (en) | Fault early warning method, device, equipment and medium for power distribution network | |
| CN115907822A (en) | Load characteristic index relevance mining method considering region and economic influence | |
| CN118249504A (en) | Intelligent diagnosis and alarm notification system for state of micro-grid equipment | |
| CN112417627A (en) | Power distribution network operation reliability analysis method based on four-dimensional index system | |
| CN116882804A (en) | Intelligent power monitoring method and system | |
| CN117421994A (en) | Edge application health monitoring method and system | |
| CN115409120A (en) | Data-driven-based auxiliary user electricity stealing behavior detection method | |
| CN116383645A (en) | Intelligent system health degree monitoring and evaluating method based on anomaly detection | |
| CN117349624A (en) | Electric power energy monitoring method, system, terminal equipment and storage medium | |
| CN116894687A (en) | Power consumption analysis method and system based on machine learning and electronic equipment | |
| CN114820036A (en) | Charging market analysis system oriented to big data and regression analysis prediction algorithm | |
| CN116777124B (en) | Power stealing monitoring method based on user power consumption behavior | |
| CN114138601A (en) | Service alarm method, device, equipment and storage medium | |
| CN116166655B (en) | Big data cleaning system | |
| CN111506636A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive and neighbor algorithm | |
| CN116720983A (en) | Power supply equipment abnormality detection method and system based on big data analysis | |
| CN115908082A (en) | Enterprise pollution discharge monitoring method and device based on electricity utilization characteristic indexes | |
| CN118014386A (en) | Regional power utilization enterprise data trend analysis system, method and medium | |
| Yang et al. | Root Cause Location Based on Prophet and Kernel Density Estimation | |
| CN118656802B (en) | Distributed scheduling system for mathematical modeling | |
| CN117291479B (en) | UPFC-based equipment portrait generation method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |