CN118228201B - Service area electric energy consumption intelligent monitoring method based on Internet of things - Google Patents

Service area electric energy consumption intelligent monitoring method based on Internet of things Download PDF

Info

Publication number
CN118228201B
CN118228201B CN202410641953.XA CN202410641953A CN118228201B CN 118228201 B CN118228201 B CN 118228201B CN 202410641953 A CN202410641953 A CN 202410641953A CN 118228201 B CN118228201 B CN 118228201B
Authority
CN
China
Prior art keywords
electric energy
moment
energy consumption
time
target
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.)
Active
Application number
CN202410641953.XA
Other languages
Chinese (zh)
Other versions
CN118228201A (en
Inventor
王小博
刘晓娜
张维敏
张博
刘攀
刘振宇
王龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shaanxi Highway Construction Group Electronic Engineering Co ltd
Original Assignee
Shaanxi Highway Construction Group Electronic Engineering Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shaanxi Highway Construction Group Electronic Engineering Co ltd filed Critical Shaanxi Highway Construction Group Electronic Engineering Co ltd
Priority to CN202410641953.XA priority Critical patent/CN118228201B/en
Publication of CN118228201A publication Critical patent/CN118228201A/en
Application granted granted Critical
Publication of CN118228201B publication Critical patent/CN118228201B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/26—Discovering frequent patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/10—Pre-processing; Data cleansing
    • G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • 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
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y10/00—Economic sectors
    • G16Y10/35—Utilities, e.g. electricity, gas or water
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/10—Detection; Monitoring
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/20—Analytics; Diagnosis
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2123/00—Data types
    • G06F2123/02—Data types in the time domain, e.g. time-series data

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Accounting & Taxation (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Business, Economics & Management (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Finance (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Power Engineering (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Primary Health Care (AREA)
  • Game Theory and Decision Science (AREA)
  • Tourism & Hospitality (AREA)
  • Human Resources & Organizations (AREA)
  • Water Supply & Treatment (AREA)
  • Public Health (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The invention relates to the technical field of electric energy monitoring, in particular to an intelligent monitoring method for electric energy consumption of a service area based on the Internet of things. According to the method, firstly, electric energy consumption data of each historical moment in each period before a moment to be predicted of a service item area to be detected, the last historical moment is taken as a termination moment, electric energy requirements are obtained according to distribution of the electric energy consumption data of the local part of each historical moment, different influence factors are obtained according to the electric energy consumption data of the local part of each historical moment and the electric energy requirements, influence stability is obtained according to differences of the same influence factors of the local part of a reference moment selected in each historical period, similarity between the termination moment and the reference moment is analyzed, the similar moment is selected from each historical period, the data of the moment to be predicted is predicted based on the electric energy consumption data of the similar moment, and electric energy consumption of the service item area to be detected is monitored. The invention can improve the accuracy of the electric energy consumption data prediction result and the effect of monitoring the electric energy consumption of the service area.

Description

Service area electric energy consumption intelligent monitoring method based on Internet of things
Technical Field
The invention relates to the technical field of electric energy monitoring, in particular to an intelligent monitoring method for electric energy consumption of a service area based on the Internet of things.
Background
Various service item areas such as catering, rest areas and convenience stores which are usually arranged in the service area are used for passengers, each service item area needs to operate based on electric energy, the electric energy input of the service area is improperly controlled, the loss of electric energy sources is large, the cost of the service area is increased, and therefore the electric energy consumption of the service area needs to be monitored, so that reasonable use of electric energy is guaranteed, and the phenomenon of electric energy waste is avoided.
In the related art, the time sequence of the historical electric energy consumption data is generally utilized to predict the future electric energy consumption data, and the electric energy input of the service area is regulated in real time through the predicted electric energy consumption data, but the current time sequence prediction method only depends on the data of the historical time point to predict, so that the prediction result is seriously distorted, and the monitoring of the electric energy consumption of the service area cannot achieve an ideal effect.
Disclosure of Invention
In order to solve the technical problem that the existing time sequence prediction method can cause serious distortion of a prediction result and further cause that the monitoring of the electric energy consumption of a service area cannot achieve an ideal effect, the invention aims to provide an intelligent monitoring method for the electric energy consumption of the service area based on the Internet of things, and the adopted technical scheme is as follows:
The invention provides an intelligent monitoring method for electric energy consumption of a service area based on the Internet of things, which comprises the following steps:
Acquiring electric energy consumption data of each historical moment in a preset time before a moment to be predicted of a service item area to be detected in a service area; dividing the preset duration into a plurality of periods uniformly, taking the last historical moment as the termination moment, taking the period of the termination moment as the current period, and taking other periods except the current period as the historical period;
Taking any one historical moment as a target moment, and obtaining the electric energy requirement of the target moment according to the distribution of the electric energy consumption data of each historical moment in a preset window of the target moment; obtaining different influence factors of the target moment according to the electric energy consumption data and the electric energy demand of each historical moment in a preset window of the target moment;
In each history period, selecting the history time with the same position as the termination time in the current period as the reference time of each history period, and obtaining the influence stability of the termination time on the same influence factor according to the difference of the same influence factor between the reference times of different history periods and the change of the same influence factor of each history time in a preset window of the reference time;
Selecting a similar time of the time to be predicted from each history period according to the difference of the electric energy consumption data between the termination time and the reference time of each history period, the difference of the electric energy demand, the difference of the same influence factor and the influence stability of the termination time about the same influence factor; obtaining electric energy consumption prediction data of a time to be predicted according to the electric energy consumption data of each similar time;
and monitoring the electric energy consumption of the service project area to be tested in the service area based on the electric energy consumption prediction data.
Further, the obtaining the electric energy demand at the target time according to the distribution of the electric energy consumption data at each historical time in the preset window at the target time includes:
analyzing the overall level of the electric energy consumption data at all the historical moments in the preset window at the target moment to obtain the overall data value of the preset window at the target moment;
And carrying out normalization processing on the integral data value of the preset window to obtain the electric energy requirement at the target moment.
Further, the obtaining the different influencing factors of the target time according to the electric energy consumption data and the electric energy demand of each historical time in the preset window of the target time includes:
the influence factors include a first influence factor and a second influence factor;
analyzing the discrete degree of the electric energy consumption data at each historical moment in a preset window at the target moment to obtain the data discrete degree of the preset window at the target moment;
Integrating the data dispersion of a preset window of the target moment and the electric energy demand of the target moment, and performing negative correlation mapping to obtain a first influence factor of the target moment;
counting the number of vehicles at each historical moment, and integrating the electric energy requirement and the number of vehicles at each historical moment to obtain personnel requirement parameters at each historical moment;
and analyzing the linear change relation between the electric energy consumption data and the personnel demand parameters at each historical moment in a preset window of the target moment to obtain a second influence factor of the target moment.
Further, the obtaining the stability of the effect of the termination moment on the same influence factor includes:
Taking the first influence factor or the second influence factor as a target influence factor, and taking any one history period as a target history period;
mapping target influence factors of each historical moment in a preset window of the reference moment of the target historical period into a two-dimensional coordinate system to obtain different two-dimensional data points; according to the difference of the positions of the two-dimensional data points, the change degree of each historical moment in a preset window of the reference moment is obtained;
Analyzing the overall level of the variation degree of all the historical moments in a preset window of the reference moment of the target historical period to obtain the local fluctuation degree of the reference moment, and performing negative correlation mapping on the local fluctuation degree to obtain the local stability degree of the reference moment;
Adjusting the target influence factor of the reference moment by utilizing the local stability of the reference moment to obtain a target influence factor adjustment value of the reference moment of the target history period;
And obtaining the influence stability of the termination time on the target influence factor according to the difference of the target influence factor adjustment values between the reference time of any two history periods.
Further, the obtaining the stability of the influence of the termination time on the target influence factor according to the difference of the target influence factor adjustment values between the reference time points of any two history periods includes:
Taking any two history periods as a history period group;
Obtaining the adjustment value difference of each history period group according to the difference of the adjustment values of the target influence factors between the reference moments of the two history periods in each history period group;
And integrating the adjustment value differences of all the history period groups, and performing negative correlation normalization processing to obtain the influence stability of the termination moment on the target influence factors.
Further, the selecting similar time points of the time points to be predicted from each history period includes:
Obtaining similarity parameters of the reference time of each history period according to the difference of the electric energy consumption data points between the termination time and the reference time of each history period, the difference of the electric energy demands, the difference of the same influence factor and the influence stability of the termination time on the same influence factor;
and taking the next historical moment of the reference moment of each historical period, of which the similarity parameter is larger than a preset threshold value, as the similar moment of the moment to be predicted.
Further, the obtaining the similarity parameter of the reference time of each history period includes:
according to the difference of the electric energy consumption data between the termination time and the reference time of each history period, obtaining the electric energy consumption data difference of the reference time of each history period;
Obtaining the electric energy demand difference of the reference time of each history period according to the electric energy demand difference between the termination time and the reference time of each history period;
Adjusting the difference of the same influence factor between the termination time and the reference time of each history period by utilizing the influence stability of the termination time on the same influence factor, and obtaining the adjustment difference of the reference time of each history period on the same influence factor;
And integrating the electric energy consumption data difference, the electric energy demand difference and the adjustment difference about the same influence factor at the reference moment of each historical period, and carrying out negative correlation normalization processing to obtain similarity parameters at the reference moment of each historical period.
Further, the obtaining the predicted data of the electric energy consumption at the time to be predicted according to the electric energy consumption data at each similar time includes:
Carrying out normalization processing on the electric energy consumption data at each similar moment to obtain a weight parameter at each similar moment;
The electric energy consumption data are weighted and adjusted by utilizing the weight parameter of each similar moment, and electric energy consumption adjustment data of each similar moment are obtained;
and analyzing the overall level of the electric energy consumption adjustment data at all similar moments to obtain electric energy consumption prediction data at the moment to be predicted.
Further, the monitoring the electric energy consumption of the service project area to be tested based on the electric energy consumption prediction data includes:
and optimizing and allocating the real-time electric energy input power of the service project area to be tested in the service area according to the electric energy consumption prediction data.
Further, the length of the period ranges from 1 to 3, and the unit is day.
The invention has the following beneficial effects:
The invention considers that the existing time sequence prediction method does not consider that the electric energy consumption data at different time points has larger difference, so that the prediction result has serious distortion phenomenon, and the monitoring of the electric energy consumption of the service area can not reach the ideal effect, therefore, the invention firstly obtains the electric energy consumption data of each history time in the preset time before the time to be predicted of the service item area to be measured of the service area, simultaneously equally divides the preset time into a plurality of periods, takes the last history time as the termination time, takes the period of the termination time as the current period, takes the other periods except the current period as the history period, is convenient for selecting the history time with higher relativity with the time to be predicted from the history periods, improves the accuracy of the data prediction result of the time to be predicted, and considers that two factors with larger electric energy consumption data difference affecting different history times, the invention firstly reflects the demand degree of the electric energy at the target moment through the acquired electric energy demand, further respectively reflects the influence degree of each influence factor on the electric energy consumption data at the target moment through different influence factors, considers the situation that the electric energy consumption data at different historical moments are large in difference and causes the distortion of the data prediction result in the existing time sequence prediction method, firstly selects the reference moment in each historical period, has large correlation of the electric energy consumption data between the reference moment and the termination moment, simultaneously considers the difference of the influence degree of the same influence factor on the electric energy consumption data at the reference moment of different historical periods, reflects the consistency of the influence of the same influence factor on the electric energy consumption data at the reference moment of different historical periods through the acquired influence stability, more accurate similar moments are conveniently extracted from each history period, accuracy of follow-up electric energy consumption prediction data is improved, and therefore electric energy consumption monitoring effect of service project areas to be detected in the service areas is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a service area electric energy consumption intelligent monitoring method based on internet of things according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for obtaining stability of an influence of a same influence factor at a termination time according to an embodiment of the present invention;
Fig. 3 is a flowchart of a method for obtaining similar time of a time to be predicted according to an embodiment of the present invention.
Detailed Description
In order to further explain the technical means and effects adopted by the invention to achieve the preset aim, the service area electric energy consumption intelligent monitoring method based on the internet of things, which is provided by the invention, is combined with the accompanying drawings and the preferred embodiment, and the specific implementation, structure, characteristics and effects thereof are described in detail below. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
Service area electric energy consumption intelligent monitoring method embodiment based on Internet of things:
the specific scheme of the service area electric energy consumption intelligent monitoring method based on the Internet of things provided by the invention is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a service area electric energy consumption intelligent monitoring method based on internet of things according to an embodiment of the present invention is shown, where the method includes:
Step S1: acquiring electric energy consumption data of each historical moment in a preset time before a moment to be predicted of a service item area to be detected in a service area; the preset time length is uniformly divided into a plurality of periods, the last historical time is taken as the termination time, the period where the termination time is located is taken as the current period, and other periods except the current period are taken as the historical periods.
Various service item areas such as catering, rest areas, convenience stores and the like which are usually arranged in the service area are used for passengers, each service item area needs to be operated on an electric energy basis, the electric energy input of the service area is controlled improperly, so that larger electric energy loss is caused, the cost of the service area is increased, the electric energy consumption of the service area is required to be monitored, reasonable use of electric energy is guaranteed, the phenomenon of electric energy waste is avoided, the time sequence of historical electric energy consumption data is usually utilized to predict future electric energy consumption data, the electric energy input of the service area is regulated in real time through the predicted electric energy consumption data, but the current time sequence prediction method only depends on the data of the historical time points to predict, so that serious distortion phenomenon occurs to the predicted result, and the monitoring of the electric energy consumption of the service area cannot achieve ideal effect.
The embodiment of the invention firstly collects the electric energy consumption data of each historical moment in a preset time period before the moment to be predicted of a service item area to be detected in the service area by using electric power monitoring equipment such as a smart electric meter, wherein the service item area to be detected can be various service item areas set in the service area, such as catering, rest areas, charging areas or gas stations, the electric energy consumption data can be electric power data, the preset time period is set to 30 days, specific numerical values of the preset time period can also be set by an operator according to specific implementation scenes without limitation, the time interval between two adjacent electric energy consumption data is set to 10 minutes, namely, the electric energy consumption data of the service item area to be detected is collected every 10 minutes, and the specific numerical values of the time interval can also be set by the operator according to specific implementation scenes without limitation.
It should be noted that, the electric energy consumption data at the time to be predicted is unknown, and the electric energy consumption data at the time to be predicted is required to be predicted subsequently, so as to monitor the electric energy consumption of the service area.
The method comprises the steps of determining a time sequence of the service project area, wherein the time sequence of the service project area is used for predicting the time sequence of the service project area, and the time sequence of the service project area is used for predicting the time sequence of the service project area.
Step S2: taking any one historical moment as a target moment, and obtaining the electric energy requirement of the target moment according to the distribution of the electric energy consumption data of each historical moment in a preset window of the target moment; and obtaining different influence factors of the target moment according to the electric energy consumption data and the electric energy demand of each historical moment in the preset window of the target moment.
Considering that two main influencing factors causing larger difference of electric energy consumption data at different historical moments exist, the first influencing factor is the difference of positions of different historical moments in corresponding periods, the second influencing factor is the difference of demands of personnel in a service area, for example, the demands of the personnel in the service area on a catering area are larger between 11 am and 1 pm each day, the electric energy consumption data of the catering area are larger, therefore, the embodiment of the invention takes any one historical moment as a target moment, analyzes the distribution of the electric energy consumption data at each historical moment in a preset window at the target moment, reflects the demand degree of the personnel in the service area on electric energy of a service project area to be tested at the target moment through the acquired electric energy demand, can be based on the electric energy demand subsequently, and accurately analyzes the influence degree of each influencing factor on the electric energy consumption data by combining the electric energy consumption data, wherein the length of the preset window is set to 9, namely, the preset window comprises the target moment and 8 recent historical moments from the target moment, the specific numerical value of the preset window length can be set by an implementer according to a specific implementation scene, and the method is not limited.
Preferably, in one embodiment of the present invention, the method for obtaining the electric energy demand at the target time specifically includes:
the larger the overall electric energy consumption data in the preset window is, the larger the electric energy demand degree at the target moment is, so that the overall level of the electric energy consumption data at all the historical moments in the preset window at the target moment can be analyzed, and the overall data value of the preset window can be obtained.
In one embodiment of the invention, the average value of the electric energy consumption data at all the historical moments in the preset window at the target moment can be used as the integral data value of the preset window, so that the integral level of the electric energy consumption data at all the historical moments in the preset window is analyzed, and the integral level of the data in the preset window at the target moment is reflected through the integral data value.
In other embodiments of the present invention, the overall data level of the preset window may also be analyzed based on the median, and the median of the electric energy consumption data at all the historical moments in the preset window at the target moment is used as the overall data value of the preset window.
And carrying out normalization processing on the whole data value of the preset window to obtain the electric energy requirement at the target moment, wherein the larger the electric energy requirement is, the larger the electric energy requirement degree of the target moment is. The expression of the power demand may specifically be, for example:
；
Wherein, Representing the electrical energy demand at the target instant; preset window of target moment The electric energy consumption data of each historical moment; Representing the number of historical moments in a preset window of target moments; Representing the normalization function.
The power demand at each historical moment can be obtained by the same method as described above.
In one embodiment of the present invention, the normalization process may specifically be, for example, maximum and minimum normalization processes, and the normalization in the subsequent steps may be performed by using the maximum and minimum normalization processes, and in other embodiments of the present invention, other normalization methods may be selected according to a specific range of values, which will not be described herein.
For each influence factor, the influence degree of the influence factors on the electric energy consumption data at different historical moments is different, so that the embodiment of the invention analyzes the electric energy demand at each historical moment in the preset window of the target moment, combines the electric energy consumption data at each historical moment in the preset window to obtain different influence factors at the target moment, each influence factor reflects the influence degree of the corresponding influence factor on the electric energy consumption data at the target moment, and then can analyze the similarity of the electric energy consumption data at each historical moment interfered by each influence factor based on the difference of the influence factors, thereby improving the accuracy of the data prediction result at the moment to be predicted.
Preferably, in one embodiment of the present invention, the method for acquiring the impact factors with different target moments specifically includes:
According to the analysis, the electric energy consumption data at the target moment is mainly interfered by two influencing factors, so that the influencing factors comprise a first influencing factor and a second influencing factor, the first influencing factor reflects the influence degree of the first influencing factor on the electric energy consumption data at the target moment, and the second influencing factor reflects the influence degree of the second influencing factor on the electric energy consumption data at the target moment.
The smaller the fluctuation of the electric energy consumption data at each historical moment in the preset window of the target moment is, the smaller the electric energy demand at the target moment is, which means that the electric energy consumption data at the target moment is greatly influenced by the position of the target moment in the corresponding period, namely, the degree of influence of the first influencing factor on the electric energy consumption data at the target moment is great.
Therefore, the degree of dispersion of the electric energy consumption data at each historical time in the preset window at the target time can be analyzed first to obtain the data dispersion of the preset window, and in the embodiment of the invention, the standard deviation or variance of the electric energy consumption data at all the historical times in the preset window at the target time can be used as the data dispersion of the preset window, which is not limited herein. The larger the variance or standard deviation is, the larger the degree of dispersion of the electric energy consumption data at each historical moment in the preset window at the target moment is, and further the larger fluctuation of the electric energy consumption data at each historical moment in the preset window is.
Then, the data dispersion of the preset window and the electric energy requirement at the target moment are integrated and then are subjected to negative correlation mapping to obtain a first influence factor at the target moment, the data dispersion and the electric energy requirement can be multiplied or added to realize the integration of the data dispersion and the electric energy requirement in the embodiment of the invention, and the negative correlation mapping can be used for example as an inverse proportion function and a natural indexThe negative correlation functions such as the negative exponential function or the linear function are realized, which are not limited and described herein, and the negative correlation mapping in the subsequent steps can be realized in this way.
The expression of the first influencing factor may specifically be, for example:
；
Wherein, A first influence factor representing a target time; data dispersion of a preset window representing a target moment; indicating the power demand at the target time, since the power consumption data at the different historic times are not identical And the electric energy consumption data at different historical moments are collected under the condition of normal operation of the service area, and the electric energy consumption data is more than 0, so。
The second influencing factor, namely, the difference of the personnel demands of the service area can also influence the electric energy consumption data of each historical moment, the demands of the personnel and the quantity of the personnel in the service area have strong correlation, but the personnel data are difficult to count, but the quantity of vehicles in the service area is convenient to count, and the quantity of vehicles and the quantity of the personnel have positive correlation, so that the embodiment of the invention counts the quantity of vehicles in the service area at each historical moment, synthesizes the electric energy demands and the quantity of vehicles at each historical moment, obtains personnel demand parameters at each historical moment, reflects the demand degree of the service area personnel at each historical moment to the service item area to be tested through the personnel demand parameters, and can realize the synthesis of the two by multiplying or adding the electric energy demands and the quantity of vehicles at each historical moment in the embodiment of the invention, and the embodiment of the invention is not limited.
The more the electric energy consumption data and personnel demand parameters at each historical moment in the preset window accord with the linear change relation, the larger the influence degree of the second influence factor on the electric energy consumption data at the target moment is, so that the linear change relation between the electric energy consumption data at each historical moment and the personnel demand parameters at each historical moment in the preset window at the target moment can be analyzed, the second influence factor at the target moment is obtained, and the larger the second influence factor is, the larger the influence degree of the second influence factor on the electric energy consumption data at the target moment is.
In one embodiment of the present invention, two arbitrary adjacent historical time points in a preset window of the target time point may be used as a historical time point group, an absolute value of a difference value of electric energy consumption data of the two historical time points in each historical time point group is used as a first difference value of each historical time point group, and an absolute value of a difference value of personnel demand parameters of the two historical time points in each historical time point group is used as a second difference value of each historical time point group; and taking the ratio of the first difference value and the second difference value of each historical time group as the initial change trend of each historical time group, and carrying out negative correlation mapping on the variances of the initial change trends of all the historical time groups to obtain a second influence factor of the target time.
In other embodiments of the present invention, the linear change relationship between the pearson correlation coefficient and the personnel demand parameter at each historical time in the preset window of the target time may be analyzed based on the pearson correlation coefficient, and when the absolute value of the pearson correlation coefficient is closer to the real number 1, it is indicated that the pearson correlation coefficient and the real number 1 conform to the linear change relationship, for example, the difference between the absolute value of the pearson correlation coefficient and the real number 1 may be mapped in a negative correlation manner, so as to obtain the second influence factor of the target time.
The expression of the second influencing factor may specifically be, for example:
；
；
Wherein, A second influence factor representing the target time; preset window of target moment Initial trend of change of each historical time group; representing the average value of initial change trends of all historical time groups in a preset window of target time; Indicating the number of history moments in a preset window of target moments, then The number of historical time groups in a preset window representing the target time; And The first of preset windows respectively representing target timeThe electric energy consumption data of two historical moments in the historical moment groups; And The first of preset windows respectively representing target timeThe personnel demand parameters of two historical moments in the historical moment group have different quantity of vehicles at different historical moments due to different electric energy demands at different historical moments and stronger mobility of the vehicles in the service area, so the quantity of the vehicles at different historical moments is different；Representing preset adjustment parameters, preventing denominator from being 0,The range of the values is as followsIn one embodiment of the inventionThe setting is made to be 0.01,The specific numerical values of (2) may also be set by the practitioner according to the specific implementation scenario, and are not limited herein.
In the process of acquiring the second influence factor of the target moment, the first difference valueAnd a second difference valueRatio of (1), i.e. initial trend of changeReflects the trend change direction between the electric energy consumption data and the personnel demand parameters of two adjacent historical moments in the preset window, so that the variance of the initial change trend of all the historical moment groupsThe smaller the trend change direction between the electric energy consumption data and the personnel demand parameters at each historical moment in the preset window is, the more consistent the trend change direction is, and the more consistent the linear change relation is, the second influence factor isThe larger the analysis process is, the more the electric energy consumption data is taken as the vertical axis, the personnel requirement parameter is taken as the horizontal axis, a coordinate system is established, then the data points composed of the electric energy consumption data and the personnel requirement parameter at each historical moment in the preset window of the target moment are mapped into the coordinate system, and the absolute value of the slope of the connection line of any two adjacent data points is the initial change trend in the formulaWhen the absolute value of the slope of all the connecting lines is smaller, that is, the variance of the initial change trend is smaller, the more the electric energy consumption data and the personnel demand data at each historical moment in the preset window of the target moment are consistent with the linear change, the second influence factor is obtainedThe larger.
Thus, different influence factors of the target moment, namely a first influence factor and a second influence factor, are obtained, and the first influence factor and the second influence factor of each historical moment can be obtained through the same method.
Step S3: and in each history period, selecting the history time with the same position as the termination time in the current period as the reference time of each history period, and obtaining the influence stability of the termination time on the same influence factor according to the difference of the same influence factor between the reference times of different history periods and the change of the same influence factor of each history time in a preset window of the reference time.
Considering that the existing time series prediction method directly utilizes the data of each historical time point to predict future data, for example, an average value of the data of all the historical time points is used as the future data, when the existing time series prediction method is applied to the process of the embodiment of the invention, the influence of the influence factors existing objectively in the outside on the electric energy consumption data is not considered, so that the accurate electric energy consumption data of the moment to be predicted cannot be obtained by using the existing time series prediction method, serious distortion occurs to the prediction result, certain periodic-like characteristics exist in the electric energy consumption data of each period, namely, certain degree of correlation or similarity exists between the electric energy consumption data of the historical moment of the same position in each period, therefore, the embodiment of the invention firstly selects the historical moment which is the same as the position of the termination moment in the current period in each historical period, and takes the 3 rd historical moment in each historical period as the reference moment of each historical period, for example, if the termination moment is the 3 rd historical moment in the current period, the 3 rd historical moment in each historical period is taken as the reference moment of each historical period, the electric energy consumption data between the reference moment and the termination moment in each historical period has a certain degree of correlation or similarity, and the accuracy is improved.
Although the electric energy consumption data among different historical periods has a similar periodic characteristic, because each influence factor has different influence degrees on the electric energy consumption data of the reference time of different historical periods, the electric energy consumption data of the reference time of each historical period can be also different, so the embodiment of the invention analyzes the difference of the same influence factor among the reference time of different historical periods, combines the change of the same influence factor of each historical time in a preset window of each reference time, obtains the influence stability of the termination time on the same influence factor, and can reflect the consistency of the influence degree of the same influence factor on the electric energy consumption data of the reference time of each historical period through the obtained influence stability.
Preferably, in an embodiment of the present invention, the method for acquiring the stability of the effect of the termination time on the same influence factor specifically includes:
Referring to fig. 2, a flowchart of a method for obtaining stability of influence of the same influence factor at a termination time according to an embodiment of the invention is shown.
Step S301: the analysis process of the first influence factor and the analysis process of the first influence factor in the subsequent step are completely the same, so that the first influence factor or the second influence factor can be used as a target influence factor, the subsequent step only analyzes the target influence factor, and any history period is used as a target history period.
Step S302: mapping target influence factors of each historical moment in a preset window of the reference moment of the target historical period into a two-dimensional coordinate system to obtain different two-dimensional data points; according to the difference of the positions of the two-dimensional data points, the change degree of each historical moment in the preset window is obtained, and the larger the change degree is, the stronger the change of the target influence factor of each historical moment in the preset window is, and further the larger the change of the degree of interference of the same influence factor between the historical moment and the adjacent historical moment is.
In one embodiment of the present invention, curve fitting may be performed on two-dimensional data points to obtain a fitted curve, where data of a first dimension of the two-dimensional data points represents a target influence factor, data of a second dimension represents a historical moment, and an absolute value of a slope of the fitted curve at each two-dimensional data point is used as a variation degree of each historical moment in a preset window, where a method of curve fitting may use, for example, polynomial fitting or a least square method, and the like, which is not limited and described herein.
In other embodiments of the present invention, the absolute value of the slope of the line between each two-dimensional data point and the next adjacent two-dimensional data point can also be used as the variation degree of each historical moment in the preset window.
Step S303: the greater the overall level of the change degree of each history time in the preset window of the reference time, the more frequently the influence degree of the same influence factor on each history time in the preset window of the reference time is described, the lower the confidence level of the target influence factor of the reference time is, so that the overall level of the change degree of all the history times in the preset window of the reference time of the target history period can be analyzed, the local fluctuation degree of the reference time is obtained, the local fluctuation degree is mapped in a negative correlation manner, the local stability degree of the reference time is obtained, the greater the local stability degree is, the more consistent the influence degree of the same influence factor on each history time in the preset window of the reference time is described, the higher the confidence level of the target influence factor of the reference time is, the target influence factor of the reference time can be adjusted in a weighting manner by the local stability degree, and the accuracy of the influence stability calculation result is improved.
In one embodiment of the invention, the average value of the variation degrees of all the history moments in the preset window of the reference moment of the target history period can be used as the local fluctuation degree of the reference moment, so that the analysis of the overall level of the variation degrees of all the history moments in the preset window of the reference moment of the target history period is realized.
In other embodiments of the present invention, the median of the variation degrees of all the history times in the preset window of the reference time of the target history period may also be used as the local fluctuation degree of the reference time.
Step S304: according to the analysis, the greater the local stability of the reference moment is, the higher the confidence of the target influence factor of the reference moment is, so that the target influence factor of the reference moment can be adjusted by using the local stability of the reference moment, the target influence factor adjustment value of the reference moment of the target history period is obtained, the greater the target influence factor adjustment value is, the greater the influence degree of the same influence factor on the reference moment of the target history period is also, the target influence factor adjustment value is an adjusted numerical value, the evaluation accuracy is higher, and the accuracy of the subsequent calculation of the influence stability can be improved.
In one embodiment of the invention, the local stability of the reference moment can be regarded as the weight of the target influence factor, the local stability of the reference moment and the target influence factor are multiplied to obtain the target influence factor adjustment value of the reference moment of the target history period, and therefore the adjustment of the target influence factor by the local stability of the reference moment is realized.
The target influence factor adjustment value of the reference time of each history period can be obtained by the same method.
Step S305: the larger the difference of the target influence factor adjustment values between the reference moments of each history period is, the worse the consistency of the influence degree of the same influence factor on the reference moments of each history period is, so that the influence stability of the termination moment on the target influence factor is obtained according to the difference of the target influence factor adjustment values between the reference moments of any two history periods, the larger the influence stability is, the more consistent the influence degree of the same influence factor on the electric energy consumption data of the reference moments of each history period is, the later the difference of the same influence factor can be adjusted based on the influence stability, the accuracy of similarity analysis between the termination moment and each reference moment is improved, and the accuracy of data prediction is further improved.
Preferably, in one embodiment of the present invention, the method for acquiring the stability of the influence of the termination time on the target influence factor specifically includes:
and taking any two history periods as history period groups, and obtaining the adjustment value difference of each history period group according to the adjustment value difference of the target influence factor between the reference moments of the two history periods in each history period group.
In one embodiment of the present invention, the absolute value of the difference in the adjustment value of the target influence factor between the reference moments of the two history periods in each history period group may be regarded as the adjustment value difference for each history period group.
The larger the difference of the adjustment values of each history period group is, the more inconsistent the influence degree of the same influence factor on the reference time of two history periods in the history period group is, so that the integrated adjustment value differences of all the history period groups can be subjected to negative correlation normalization processing to obtain the influence stability of the termination time on the target influence factor, the larger the influence stability is, and the more consistent the influence degree of the same influence factor on the electric energy consumption data of each reference time is.
In the embodiment of the invention, the integration of the adjustment value differences of all the history period groups can be realized by calculating the accumulated value or the average value of the adjustment value differences of all the history period groups, which is not limited herein.
The expression affecting stability may specifically be, for example:
；
Wherein, Indicating the stability of the effect of the termination moment with respect to the target impact factor; And Respectively represent the firstLocal fluctuation degree of reference time of two history periods in each history period group, and since target influence factors of each history time in a preset window of reference time are not identical, the change degree of each history time in the preset window of reference time is not equal to 0, and，；AndRespectively represent the firstTarget influence factors of reference moments of two history periods in the history period group; And Respectively represent the firstLocal stability of reference moments of two history periods in the history period group; And Respectively represent the firstTarget influence factor adjustment values of reference moments of two history periods in the history period group; Represent the first The adjustment value differences of the history period groups; Representing the number of history period groups; Representing the normalization function.
The stability of the effect of the termination time on the same influencing factor is obtained so far, and the method can be used for facilitating the subsequent distinctionIndicating the stability of the effect of the termination moment with respect to the first influencing factor,Indicating the stability of the effect of the termination moment with respect to the second influencing factor.
Step S4: according to the difference of the electric energy consumption data between the termination time and the reference time of each history period, the difference of the electric energy demand, the difference of the same influence factor and the influence stability of the termination time about the same influence factor, selecting similar time of the time to be predicted from each history period; and obtaining the electric energy consumption prediction data of the time to be predicted according to the electric energy consumption data of each similar time.
The method and the device have the advantages that the similarity between the termination time and the reference time of each history period is analyzed, so that the similarity between the termination time and the reference time of each history period is extracted from each history period, the similarity between the termination time and the reference time of each history period is not only related to the electric energy consumption data, but also related to the electric energy demand and the influence degree of each influence factor on the electric energy consumption data, and therefore, the method and the device combine the difference of the electric energy consumption data, the difference of the electric energy demand and the difference of the same influence factor between the termination time and the reference time of each history period, properly adjust the difference of the same influence factor by utilizing the influence stability of the termination time on the same influence factor, so that more accurate similarity is extracted, and the electric energy consumption data at the time to be predicted can be accurately predicted based on the electric energy consumption data at the similar time in the history period.
Preferably, in one embodiment of the present invention, the method for acquiring similar time to the time to be predicted specifically includes:
Referring to fig. 3, a flowchart of a method for obtaining similar time to a time to be predicted according to an embodiment of the present invention is shown.
Step S401: according to the difference of the electric energy consumption data points between the termination time and the reference time of each history period, the difference of the electric energy demand, the difference of the same influence factor and the influence stability of the termination time about the same influence factor, the similarity parameter of the reference time of each history period is obtained, and the larger the similarity parameter is, the higher the similarity between the reference time of each history period and the termination time is, so that the follow-up accurate selection of the similarity time from each history period based on the similarity parameter is facilitated.
Preferably, in one embodiment of the present invention, the method for acquiring the similarity parameter at the reference time of each history period specifically includes:
obtaining the difference of the electric energy consumption data of the reference time of each history period according to the difference of the electric energy consumption data between the termination time and the reference time of each history period; and obtaining the electric energy demand difference of the reference moment of each history period according to the electric energy demand difference between the termination moment and the reference moment of each history period.
The greater the influence stability of the same influence factor, the more consistent the influence degree of the same influence factor on each reference moment is, the higher the confidence of the difference of the same influence factor between the termination moment and the reference moment of each history period is, so that the difference of the same influence factor between the termination moment and the reference moment of each history period can be adjusted by utilizing the influence stability of the same influence factor of the termination moment, and the adjustment difference of the reference moment of each history period about the same influence factor is obtained.
In one embodiment of the present invention, the square of the difference in power consumption data between the termination time and the reference time of each history period, the square of the difference in power demand, and the square of the difference in the same influence factor may be respectively represented as the difference in power consumption data, the difference in power demand, and the difference in the same influence factor.
In other embodiments of the present invention, the absolute value of the difference of the power consumption data, the absolute value of the difference of the power demand and the absolute value of the difference of the same influencing factor between the termination time and the reference time of each history period may also represent the difference of the power consumption data, the difference of the power demand and the difference of the same influencing factor, respectively.
The smaller the electric energy consumption data difference, the electric energy demand difference and the adjustment difference, the larger the similarity between the reference time and the termination time of each history period is, so that the electric energy consumption data difference, the electric energy demand difference and the adjustment difference about the same influence factor of each history period can be integrated and then subjected to negative correlation normalization processing, and the similarity parameter of the reference time of each history period is obtained.
The expression of the similarity parameter in one embodiment of the present invention may specifically be, for example:
；
the expression of the similarity parameter in other embodiments of the present invention may also be specifically, for example:
；
Wherein, Represent the firstSimilarity parameters for reference moments of the historical periods; Represent the first Electric energy consumption data at reference moments of a history period; Electric energy consumption data representing termination time; Represent the first The power demand at a reference time of each historical cycle; Indicating the power demand at the termination time; Represent the first A first influence factor for reference moments of the history period; A first influence factor representing a termination time; Represent the first A second influence factor for reference moments of the historical periods; a second influencing factor representing the termination time; indicating an influence stability of the termination moment with respect to the first influence factor; indicating an influence stability of the termination moment with respect to the second influence factor; Expressed in natural constant An exponential function of the base.
Step S402: the larger the similarity parameter, the more similar the electric energy consumption data between the reference time and the termination time of each history period are, and the more similar the electric energy demand and the external influence are, and further the higher the similarity between the reference time and the termination time of each history period is, and the termination time is the previous history time adjacent to the time to be predicted, the next history time of the reference time of each history period with the higher similarity parameter is also higher in similarity with the time to be predicted, so the next history time of the reference time of each history period with the similarity parameter larger than the preset threshold value can be used as the similar time of the time to be predicted, and the value range of the preset threshold value is generallyIn one embodiment of the present invention, the preset threshold is set to 0.8, and the specific value of the preset threshold may also be set by the practitioner according to the specific implementation scenario, which is not limited herein.
After the similar time of the time to be predicted is extracted from the history period, the electric energy consumption data of the time to be predicted can be accurately predicted based on the electric energy consumption data of each similar time.
Preferably, in one embodiment of the present invention, the method for acquiring the electric energy consumption prediction data at the time to be predicted specifically includes:
Carrying out normalization processing on the electric energy consumption data at each similar moment to obtain a weight parameter at each similar moment; weighting and adjusting the electric energy consumption data by using the weight parameter of each similar moment to obtain electric energy consumption adjustment data of each similar moment; the overall level of the electric energy consumption adjustment data at all similar moments is analyzed to obtain electric energy consumption prediction data at the moment to be predicted, and in one embodiment of the invention, the average value or the median of the electric energy consumption adjustment data at all similar moments can be used as the electric energy consumption prediction data at the moment to be predicted, so that the overall level of the electric energy consumption adjustment data at all similar moments is analyzed. The expression of the electric energy consumption prediction data at the time to be predicted may specifically be, for example:
；
Wherein, Electric energy consumption prediction data representing a time to be predicted; Electric energy consumption data representing each similar instant; Representing the number of similar moments; Representing the normalization function.
In the process of acquiring the electric energy consumption data at the moment to be predicted, carrying out normalization processing on the electric energy consumption data at the similar moment to obtain the weight parameter of each similar momentAnd meanwhile, the electric energy consumption data at the similar moment are subjected to weighted adjustment and averaging by using the weight parameters, so that a more accurate prediction result is obtained.
Step S5: and monitoring the electric energy consumption of the service project area to be tested in the service area based on the electric energy consumption prediction data.
The method can accurately predict the electric energy consumption prediction data of the service item area to be detected in the service area at a future time point, so that the electric energy consumption of the service item area to be detected in the service area can be monitored based on the electric energy consumption prediction data, and the accuracy of monitoring the electric energy consumption is improved.
Preferably, in an embodiment of the present invention, real-time electric energy input power of a service project area to be tested in a service area can be optimally allocated according to electric energy consumption prediction data, for example, real-time electric power of the service project area to be tested in the service area at each future time point can be adjusted, so that the real-time electric power is the same as the electric energy prediction data, thereby ensuring reasonable use of electric energy and avoiding electric energy waste.
In summary, in the embodiment of the present invention, first, the electric energy consumption data of each historical moment in a preset time period before a moment to be predicted in a service item area to be detected in a service area is obtained; dividing the preset duration into a plurality of periods uniformly, taking the last historical moment as the termination moment, taking the period of the termination moment as the current period, and taking other periods except the current period as the historical period; taking any one historical moment as a target moment, and obtaining the electric energy requirement of the target moment according to the distribution of the electric energy consumption data of each historical moment in a preset window of the target moment; obtaining different influence factors of the target moment according to the electric energy consumption data and the electric energy demand of each historical moment in a preset window of the target moment; in each history period, selecting the history time with the same position as the termination time in the current period as the reference time of each history period, and obtaining the influence stability of the termination time on the same influence factor according to the difference of the same influence factor between the reference times of different history periods and the change of the same influence factor of each history time in a preset window of the reference time; according to the difference of the electric energy consumption data between the termination time and the reference time of each history period, the difference of the electric energy demand, the difference of the same influence factor and the influence stability of the termination time about the same influence factor, selecting similar time of the time to be predicted from each history period; obtaining electric energy consumption prediction data of a time to be predicted according to the electric energy consumption data of each similar time; and monitoring the electric energy consumption of the service project area to be tested in the service area based on the electric energy consumption prediction data.
An embodiment of a data prediction method for monitoring electric energy consumption of a service area comprises the following steps:
Before monitoring the electric energy consumption of the service area, the time sequence of the historical electric energy consumption data is usually required to be used for predicting the future electric energy consumption data in the related technology, but the current time sequence prediction method only depends on the data of the historical time point for prediction, so that serious distortion phenomenon can occur to the prediction result, and the accuracy of the prediction result is reduced.
To solve the problem, the present embodiment provides a data prediction method for monitoring electric energy consumption of a service area, including:
Step S1: acquiring electric energy consumption data of each historical moment in a preset time before a moment to be predicted of a service item area to be detected in a service area; the preset time length is uniformly divided into a plurality of periods, the last historical time is taken as the termination time, the period where the termination time is located is taken as the current period, and other periods except the current period are taken as the historical periods.
Step S2: taking any one historical moment as a target moment, and obtaining the electric energy requirement of the target moment according to the distribution of the electric energy consumption data of each historical moment in a preset window of the target moment; and obtaining different influence factors of the target moment according to the electric energy consumption data and the electric energy demand of each historical moment in the preset window of the target moment.
Step S3: and in each history period, selecting the history time with the same position as the termination time in the current period as the reference time of each history period, and obtaining the influence stability of the termination time on the same influence factor according to the difference of the same influence factor between the reference times of different history periods and the change of the same influence factor of each history time in a preset window of the reference time.
Step S4: according to the difference of the electric energy consumption data between the termination time and the reference time of each history period, the difference of the electric energy demand, the difference of the same influence factor and the influence stability of the termination time about the same influence factor, selecting similar time of the time to be predicted from each history period; and obtaining the electric energy consumption prediction data of the time to be predicted according to the electric energy consumption data of each similar time.
The steps S1 to S4 are already described in detail in the embodiment of the service area electric energy consumption intelligent monitoring method based on the internet of things, and are not described herein.
The beneficial effects brought by the embodiment are as follows: the invention considers that the prior time sequence prediction method does not consider that the electric energy consumption data of different time points have larger difference, which leads to serious distortion phenomenon of the prediction result, therefore, the invention firstly obtains the electric energy consumption data of each historical time in the preset time before the time to be predicted of the service project area to be measured in the service area, simultaneously equally divides the preset time into a plurality of periods, takes the last historical time as the termination time, takes the period of the termination time as the current period, takes other periods except the current period as the historical period, is convenient for selecting the historical time with higher relativity with the time to be predicted from the historical periods, improves the accuracy of the data prediction result of the time to be predicted, and considers two main factors with larger difference of the electric energy consumption data affecting different historical times, therefore, the invention firstly reflects the demand degree of the electric energy at the target moment through the acquired electric energy demand, further respectively reflects the influence degree of each influence factor on the electric energy consumption data at the target moment through different influence factors, considers the situation that the electric energy consumption data at different historical moments are large in difference and causes the distortion of the data prediction result in the existing time sequence prediction method, firstly selects the reference moment in each historical period, has large correlation with the electric energy consumption data between the reference moment and the termination moment, simultaneously considers the difference of the influence degree of the same influence factor on the electric energy consumption data at the reference moment of different historical periods, reflects the consistency of the influence of the same influence factor on the electric energy consumption data at the reference moment of different historical periods through the acquired influence stability, is convenient for extracting more accurate similar moments from the historical periods, and the accuracy of the subsequent electric energy consumption prediction data is improved.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.

Claims (10)

1. The service area electric energy consumption intelligent monitoring method based on the Internet of things is characterized by comprising the following steps of:
Acquiring electric energy consumption data of each historical moment in a preset time before a moment to be predicted of a service item area to be detected in a service area; dividing the preset duration into a plurality of periods uniformly, taking the last historical moment as the termination moment, taking the period of the termination moment as the current period, and taking other periods except the current period as the historical period;
Taking any one historical moment as a target moment, and obtaining the electric energy requirement of the target moment according to the distribution of the electric energy consumption data of each historical moment in a preset window of the target moment; obtaining different influence factors of the target moment according to the electric energy consumption data and the electric energy demand of each historical moment in a preset window of the target moment;
In each history period, selecting the history time with the same position as the termination time in the current period as the reference time of each history period, and obtaining the influence stability of the termination time on the same influence factor according to the difference of the same influence factor between the reference times of different history periods and the change of the same influence factor of each history time in a preset window of the reference time;
Selecting a similar time of the time to be predicted from each history period according to the difference of the electric energy consumption data between the termination time and the reference time of each history period, the difference of the electric energy demand, the difference of the same influence factor and the influence stability of the termination time about the same influence factor; obtaining electric energy consumption prediction data of a time to be predicted according to the electric energy consumption data of each similar time;
and monitoring the electric energy consumption of the service project area to be tested in the service area based on the electric energy consumption prediction data.
2. The method for intelligently monitoring the electric energy consumption of the service area based on the internet of things according to claim 1, wherein the obtaining the electric energy demand at the target moment according to the distribution of the electric energy consumption data at each historical moment in the preset window at the target moment comprises:
analyzing the overall level of the electric energy consumption data at all the historical moments in the preset window at the target moment to obtain the overall data value of the preset window at the target moment;
And carrying out normalization processing on the integral data value of the preset window to obtain the electric energy requirement at the target moment.
3. The method for intelligently monitoring the electric energy consumption of the service area based on the internet of things according to claim 1, wherein the obtaining the different influence factors of the target time according to the electric energy consumption data and the electric energy demand of each historical time in the preset window of the target time comprises:
the influence factors include a first influence factor and a second influence factor;
analyzing the discrete degree of the electric energy consumption data at each historical moment in a preset window at the target moment to obtain the data discrete degree of the preset window at the target moment;
Integrating the data dispersion of a preset window of the target moment and the electric energy demand of the target moment, and performing negative correlation mapping to obtain a first influence factor of the target moment;
counting the number of vehicles at each historical moment, and integrating the electric energy requirement and the number of vehicles at each historical moment to obtain personnel requirement parameters at each historical moment;
and analyzing the linear change relation between the electric energy consumption data and the personnel demand parameters at each historical moment in a preset window of the target moment to obtain a second influence factor of the target moment.
4. The method for intelligently monitoring the electric energy consumption of the service area based on the internet of things according to claim 3, wherein the obtaining the influence stability of the termination moment about the same influence factor comprises:
Taking the first influence factor or the second influence factor as a target influence factor, and taking any one history period as a target history period;
mapping target influence factors of each historical moment in a preset window of the reference moment of the target historical period into a two-dimensional coordinate system to obtain different two-dimensional data points; according to the difference of the positions of the two-dimensional data points, the change degree of each historical moment in a preset window of the reference moment is obtained;
Analyzing the overall level of the variation degree of all the historical moments in a preset window of the reference moment of the target historical period to obtain the local fluctuation degree of the reference moment, and performing negative correlation mapping on the local fluctuation degree to obtain the local stability degree of the reference moment;
Adjusting the target influence factor of the reference moment by utilizing the local stability of the reference moment to obtain a target influence factor adjustment value of the reference moment of the target history period;
And obtaining the influence stability of the termination time on the target influence factor according to the difference of the target influence factor adjustment values between the reference time of any two history periods.
5. The intelligent monitoring method for electric energy consumption of service area based on internet of things according to claim 4, wherein the obtaining the stability of the influence of the termination time on the target influence factor according to the difference of the target influence factor adjustment values between the reference time of any two history periods comprises:
Taking any two history periods as a history period group;
Obtaining the adjustment value difference of each history period group according to the difference of the adjustment values of the target influence factors between the reference moments of the two history periods in each history period group;
And integrating the adjustment value differences of all the history period groups, and performing negative correlation normalization processing to obtain the influence stability of the termination moment on the target influence factors.
6. The intelligent monitoring method for electric energy consumption of service area based on internet of things according to claim 1, wherein the selecting similar time of to-be-predicted time from each history period comprises:
Obtaining similarity parameters of the reference time of each history period according to the difference of the electric energy consumption data points between the termination time and the reference time of each history period, the difference of the electric energy demands, the difference of the same influence factor and the influence stability of the termination time on the same influence factor;
and taking the next historical moment of the reference moment of each historical period, of which the similarity parameter is larger than a preset threshold value, as the similar moment of the moment to be predicted.
7. The intelligent monitoring method for electric energy consumption in service areas based on internet of things according to claim 6, wherein the obtaining similarity parameters of reference time of each history period comprises:
according to the difference of the electric energy consumption data between the termination time and the reference time of each history period, obtaining the electric energy consumption data difference of the reference time of each history period;
Obtaining the electric energy demand difference of the reference time of each history period according to the electric energy demand difference between the termination time and the reference time of each history period;
Adjusting the difference of the same influence factor between the termination time and the reference time of each history period by utilizing the influence stability of the termination time on the same influence factor, and obtaining the adjustment difference of the reference time of each history period on the same influence factor;
And integrating the electric energy consumption data difference, the electric energy demand difference and the adjustment difference about the same influence factor at the reference moment of each historical period, and carrying out negative correlation normalization processing to obtain similarity parameters at the reference moment of each historical period.
8. The method for intelligently monitoring the electric energy consumption of the service area based on the internet of things according to claim 1, wherein the obtaining the electric energy consumption prediction data of the time to be predicted according to the electric energy consumption data of each similar time comprises:
Carrying out normalization processing on the electric energy consumption data at each similar moment to obtain a weight parameter at each similar moment;
The electric energy consumption data are weighted and adjusted by utilizing the weight parameter of each similar moment, and electric energy consumption adjustment data of each similar moment are obtained;
and analyzing the overall level of the electric energy consumption adjustment data at all similar moments to obtain electric energy consumption prediction data at the moment to be predicted.
9. The intelligent monitoring method for electric energy consumption of service area based on internet of things according to claim 1, wherein the monitoring for electric energy consumption of service project area to be tested of service area based on the predicted electric energy consumption data comprises:
and optimizing and allocating the real-time electric energy input power of the service project area to be tested in the service area according to the electric energy consumption prediction data.
10. The intelligent monitoring method for the electric energy consumption of the service area based on the Internet of things according to claim 1, wherein the length range of the period is an integer ranging from 1 to 3, and the unit is a day.
CN202410641953.XA 2024-05-23 2024-05-23 Service area electric energy consumption intelligent monitoring method based on Internet of things Active CN118228201B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410641953.XA CN118228201B (en) 2024-05-23 2024-05-23 Service area electric energy consumption intelligent monitoring method based on Internet of things

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410641953.XA CN118228201B (en) 2024-05-23 2024-05-23 Service area electric energy consumption intelligent monitoring method based on Internet of things

Publications (2)

Publication Number Publication Date
CN118228201A CN118228201A (en) 2024-06-21
CN118228201B true CN118228201B (en) 2024-07-19

Family

ID=91510301

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410641953.XA Active CN118228201B (en) 2024-05-23 2024-05-23 Service area electric energy consumption intelligent monitoring method based on Internet of things

Country Status (1)

Country Link
CN (1) CN118228201B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113282646A (en) * 2021-04-30 2021-08-20 国网四川省电力公司经济技术研究院 Daily load curve acquisition method based on power consumption behavior influence factors
CN117114213A (en) * 2023-10-25 2023-11-24 北京国旺盛源智能终端科技有限公司 Rural network co-construction convenience network service method and system

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113128781B (en) * 2021-04-30 2021-12-10 大连理工大学 Distributed industrial energy operation optimization platform for automatically constructing intelligent model and algorithm
CN113850439A (en) * 2021-09-29 2021-12-28 广州新科佳都科技有限公司 Energy consumption prediction method, device, equipment and storage medium for rail transit station equipment
CN116204566B (en) * 2023-04-28 2023-07-14 深圳市欣冠精密技术有限公司 Digital factory monitoring big data processing system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113282646A (en) * 2021-04-30 2021-08-20 国网四川省电力公司经济技术研究院 Daily load curve acquisition method based on power consumption behavior influence factors
CN117114213A (en) * 2023-10-25 2023-11-24 北京国旺盛源智能终端科技有限公司 Rural network co-construction convenience network service method and system

Also Published As

Publication number Publication date
CN118228201A (en) 2024-06-21

Similar Documents

Publication Publication Date Title
CN115982602B (en) Photovoltaic transformer electrical fault detection method
CN117407700A (en) Method for monitoring working environment in live working process
CN116092018B (en) Fire-fighting hidden danger monitoring method and system based on intelligent building
CN116307944B (en) Distribution box remote monitoring system based on artificial intelligence and Internet of things
CN113111596A (en) Carbon peak-reaching real-time visual measuring and calculating method based on electric brain center
CN117387172B (en) Terminal air conditioner energy saving method and system based on accurate recommended equipment control parameters
CN107547269A (en) The construction method of intelligent substation communication flow threshold model based on FARIMA
CN116320042A (en) Internet of things terminal monitoring control system for edge calculation
CN116309344A (en) Insulator abnormality detection method, device, equipment and storage medium
CN118013351A (en) Data acquisition method and system based on dual-mode communication technology
CN117591964A (en) Electric power intelligent analysis method based on artificial intelligence
CN118228201B (en) Service area electric energy consumption intelligent monitoring method based on Internet of things
CN118194607A (en) Dynamic modeling method and system for boiler unit data
CN117331705B (en) Data prediction analysis method and system based on big data
CN117540325B (en) Business database anomaly detection method and system based on data variation capture
CN117335409A (en) Power consumer load prediction system based on artificial intelligence
CN117150244A (en) Intelligent power distribution cabinet state monitoring method and system based on electrical parameter analysis
CN112232580B (en) Power supply interruption loss analysis method and device
CN115453447A (en) Online detection method for out-of-tolerance electric meter based on suspected electric meter stepwise compensation rejection
CN114838923A (en) Fault diagnosis model establishing method and fault diagnosis method for on-load tap-changer
CN115081533A (en) Client side load prediction method and system based on two-stage clustering and MGRU-AT
CN113947249A (en) Energy-consumption strategy analysis control device for refueling and gas station
CN108388949B (en) Power equipment allocation method and system based on equipment relative service environment sensitivity
CN109345115B (en) Evaluation method for evolution driving metric value of power information physical system
CN117277565B (en) Communication system and method for monitoring state of power distribution network

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
GR01 Patent grant
GR01 Patent grant