CN110705750A - Method and system for predicting electric quantity of columnar power users in region - Google Patents
Method and system for predicting electric quantity of columnar power users in region Download PDFInfo
- Publication number
- CN110705750A CN110705750A CN201910826364.8A CN201910826364A CN110705750A CN 110705750 A CN110705750 A CN 110705750A CN 201910826364 A CN201910826364 A CN 201910826364A CN 110705750 A CN110705750 A CN 110705750A
- Authority
- CN
- China
- Prior art keywords
- power
- time
- region
- area
- columnar
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000005611 electricity Effects 0.000 claims abstract description 89
- 239000011159 matrix material Substances 0.000 claims abstract description 72
- 238000005265 energy consumption Methods 0.000 claims abstract description 15
- 238000011156 evaluation Methods 0.000 claims description 131
- 238000013528 artificial neural network Methods 0.000 claims description 28
- 238000003062 neural network model Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 9
- 230000005484 gravity Effects 0.000 claims description 8
- 150000001875 compounds Chemical class 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 238000009440 infrastructure construction Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 239000010865 sewage Substances 0.000 claims description 4
- 239000002699 waste material Substances 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 4
- 238000010200 validation analysis Methods 0.000 claims 1
- 238000009826 distribution Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to a method and a system for predicting electric quantity of columnar power users in an area, wherein the method comprises the following steps: determining columnar power users in the region according to a dimensionless index matrix of the power users in the region; and predicting the electricity consumption of the columnar electricity consumers in the area by utilizing the historical electricity consumption data of the columnar electricity consumers in the area. The technical scheme provided by the invention accurately predicts the electric energy consumption of the prop electric power user, thereby providing technical support for reasonable planning and layout of the local power distribution network and further avoiding the problems of insufficient power supply and excessive electric energy.
Description
Technical Field
The invention relates to the technical field of big data, in particular to a method and a system for predicting electric quantity of columnar power users in an area.
Background
The prop industry plays a role in keeping the bone dryness and the support in the economy of a region, the production condition of the prop industry has great influence on the local economic development, and the electric energy use condition of an enterprise can more intuitively reflect the production state of the prop industry. Therefore, in order to understand the production condition and economic development situation of a region, the prediction can be performed according to the electric energy situation of the pillar industry.
The method has the advantages that the electric energy consumption of the prop industry is accurately calculated and predicted, powerful data support can be provided for reasonable planning and layout of the local power distribution network, the method has important significance for avoiding the problems of insufficient power supply and surplus electric energy, and meanwhile, huge economic benefits can be brought to power system planning departments.
However, due to the complexity of power prediction, the prediction result usually differs from the actual power consumption value, and the referential property of the prediction data is poor.
At present, the existing patents cannot accurately predict the electric energy condition of the prop industry.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a method and a system for predicting the electric quantity of a columnar power user in an area, which accurately predict the electric energy consumption of the columnar power user, thereby providing technical support for reasonable planning and layout of a local power distribution network and further avoiding the problems of insufficient power supply and excessive electric energy.
The purpose of the invention is realized by adopting the following technical scheme:
the invention provides a method for predicting the electric quantity of a columnar power consumer in an area, which is improved in that the method comprises the following steps:
determining columnar power users in the region according to a dimensionless index matrix of the power users in the region;
and predicting the electricity consumption of the columnar electricity consumers in the area by utilizing the historical electricity consumption data of the columnar electricity consumers in the area.
Preferably, the determining the columnar power consumers in the region according to the non-dimensionalized index matrix of the power consumers in the region includes:
step 1: initializing t ═ t0-1;
Step 2: determining a support evaluation index of the power consumer in the t-time region according to a dimensionless index matrix of the power consumer in the t-time region;
and step 3: determining the columnar power users in the t-moment area according to the columnar evaluation indexes of the power users in the t-moment area;
and 4, step 4: judging t as t0-N is true, if yes, then t is output0The columnar power users in the region of N moments before the moment; otherwise, making t equal to t-1 and returning to the step 2;
and 5: selecting t0The first N times of the time share the regional columnar power consumer as t0Columnar power users in a time zone;
wherein N is preSetting the total time of the reference time interval; t is t0Is the predicted time of day.
Further, a dimensionless index matrix x (t) of the power consumers in the time t region is determined according to the following formula:
in the formula, x0j(t) is a reference index value, x, in the dimensionless index of the jth power consumer in the t-time regionij(t) is the ith non-reference index value in the dimensionless index of the jth power consumer in the time t region, i belongs to (1-n), j belongs to (1-m), and n is the total number of the non-reference index values of the power consumers in the region; and m is the total number of power users in the area.
Further, the step 2 includes:
determining a correlation coefficient matrix of the power users in the t-moment area according to a dimensionless index matrix of the power users in the t-moment area;
determining the grey correlation degree of the reference index and the non-reference index of the power consumer in the t moment area according to the correlation coefficient matrix of the power consumer in the t moment area;
and selecting the non-reference index of which the grey correlation degree with the non-reference index of the power consumer in the t-time area is greater than a threshold value as the prop evaluation index of the power consumer in the t-time area.
Further, the determining a correlation coefficient matrix of the power consumers in the time t area according to the dimensionless index matrix of the power consumers in the time t area includes:
determining a correlation coefficient matrix Y (t) of the power users in the time t region according to the following formula:
in the formula, xi0i,j(t) a correlation coefficient between a reference index value and an ith non-reference index value in the dimensionless index of the jth power consumer in the t-time region;
wherein the content of the first and second substances,determining a correlation coefficient xi between a reference index value and an ith non-reference index value in a dimensionless index of the jth power consumer in a time t region according to the following formula0i,j(t):
Wherein △ (max) is the maximum value in the absolute difference matrix of the power consumers in the time t region, △ (min) is the minimum value in the absolute difference matrix of the power consumers in the time t region, and ρ is a resolution coefficient;
the matrix of absolute differences △ (t) for the power consumers in the area at time t is determined as follows:
in the formula, △0i,j(t) is a difference value between a reference index value and an ith non-reference index value in the dimensionless index of the jth power consumer in the t-time region.
Further, the determining a gray correlation degree between a reference index and a non-reference index of the power consumer in the time t area according to the correlation coefficient matrix of the power consumer in the time t area includes:
determining a gray association degree gamma of a reference index value and an ith non-reference index value in a dimensionless index of the jth power consumer in the t-time region according to the following formula0i(t):
In the formula, xi0i,j(t) is a correlation coefficient between a reference index value and an ith non-reference index value in the dimensionless index of the jth power consumer in the t-time region.
Further, the step 3 includes:
clustering the power users in the region according to the prop evaluation index of the power users in the region at the time t;
determining the expression degree of each cluster according to the prop evaluation index of the power consumer in each cluster at the time t;
and selecting the power users in the cluster with the highest expression degree as the columnar power users in the area at the time t.
Further, the clustering the regional power consumers according to the prop evaluation index of the regional power consumers at the time t includes:
and if the weighted Euclidean distance between the support evaluation index of the jth power consumer and the support evaluation index of the u power consumer in the time t region is the smallest in the weighted Euclidean distance between the support evaluation index of the jth power consumer and the support evaluation indexes of all the power consumers in the time t region, the support evaluation index of the jth power consumer and the u power consumer are grouped into one.
Furthermore, a weighted Euclidean distance d between the support evaluation index of the jth power consumer and the support evaluation index of the uth power consumer in the time zone t is determined according to the following formulaju(t):
In the formula, ωv(t) is the weight of the v-th prop evaluation index of the power consumer in the time t region; x is the number ofvj(t) is a vth support evaluation index value of a jth power consumer in the time t region; x is the number ofvu(t) is a vth prop evaluation index value of a u th power consumer in the time t region, u, j belongs to the group from 1 to m, m is the total number of the power consumers in the region, v belongs to the group from 1 to S (t), and S (t) is the total number of the prop evaluation indexes of the power consumers in the time t region;
wherein, the weight omega of the v-th prop evaluation index of the power consumer in the time t region is determined according to the following formulav(t):
In the formula, cv(t) is the contribution of the v-th prop evaluation index of the power consumer in the area at the time t to the clusteringDegree;
determining the contribution degree c of the v-th prop evaluation index of the power consumer in the t-time region to the cluster according to the following formulav(t):
In the formula (I), the compound is shown in the specification,the characteristic evaluation index value of the v th support column of the c th power consumer in the k th cluster in the time t region is obtained; m iskv(t) is the mean value of the v-th prop evaluation index of the power consumer in the k-th cluster in the t-moment area; m isv(t) is the mean value of the vth prop evaluation indexes of the power users in the time t region, K belongs to (1-K), and K is the total number of clusters in the time t region; c is an element of (1 to n)k(t)),nkAnd (t) is the total number of the power users of the kth cluster in the time t region.
Further, the determining the expression degree of each cluster according to the support evaluation index of the power consumer in each cluster at the time t includes:
determining the expression degree P of the kth cluster in the t-time area according to the following formulak(t):
Pk(t)=Mk(t)·ω(t)
In the formula, Mk(t) is an average proportion matrix of the support evaluation indexes of the power users in the kth cluster in the time t region; ω (t) is a weight matrix of the support evaluation index of the power consumer;
wherein, an average proportion matrix M of the support evaluation indexes of the power users in the kth cluster in the time t region is determined according to the following formulak(t):
Mk(t)=[Mk1(t)…Mkv(t)…MkS(t)(t)]
In the formula, Mkv(t) is the average specific gravity value of the v-th prop evaluation index of the power consumer in the k-th cluster in the time t region;
determining a weight matrix omega (t) of the support evaluation index of the power consumer according to the following formula:
ω(t)=[ω1(t)…ωv(t)…ωS(t)(t)]
in the formula, ωv(t) is the weight of the v-th prop evaluation index of the power consumer in the time t region;
determining the average specific gravity value M of the v-th prop evaluation index of the power consumer in the k-th cluster in the t-time area according to the following formulakv(t):
In the formula, xvj(t) is a vth support evaluation index value of a jth power consumer in the time t region;the characteristic evaluation index value of the v th support of the c th power consumer in the k th cluster in the time t region, j belongs to (1-m), m is the total number of the power consumers in the region, nkAnd (t) is the total number of the power users of the kth cluster in the time t region.
Preferably, the predicting the power consumption of the regional pillar electricity consumers by using the historical power consumption data of the regional pillar electricity consumers includes:
and substituting the electricity utilization data of the columnar electricity users in the area delta moments before the moment to be measured into a pre-constructed neural network model to obtain the predicted value of the electricity utilization of the columnar electricity users in the area at the moment to be measured.
Further, the process of building the pre-constructed neural network model includes:
and taking the electricity utilization data of the columnar power users in the area delta moments before the historical moment as input layer training samples of the initial neural network, taking the electricity utilization data of the columnar power users in the area delta moments before the historical moment as output layer training samples of the initial neural network, training the initial neural network, and obtaining the pre-constructed neural network.
Further, the verification process of the pre-constructed neural network model includes:
substituting the electricity utilization data of the columnar power users in the area of delta moments before the historical moment into a pre-established neural network model to obtain the output data of the pre-established neural network;
and comparing the output data with the electricity utilization data of the columnar power users in the region at the historical moment, wherein if the relative errors of the output data and the electricity utilization data of the columnar power users in the region at the historical moment are less than 5%, the pre-constructed neural network is qualified, otherwise, the pre-constructed neural network is unqualified.
Further, the relative error μ of the output data and the electricity consumption data of the columnar power consumers in the region of the historical time is determined according to the following formula:
in the formula, b0The power utilization data are power utilization data of the columnar power users in the historical time; b1And substituting the electricity utilization data of the columnar power consumers in the area of the previous delta moments of the historical moment into the output data of the pre-constructed neural network model.
Further, a reference index in the dimensionless indexes of the power consumer is a tax total index of the power consumer;
the non-reference indexes in the dimensionless indexes of the power users comprise power user energy efficiency characteristic indexes, power user economic contribution characteristic indexes and energy-saving and environment-friendly characteristic indexes;
the energy efficiency characteristic indexes of the power consumer comprise: the method comprises the following steps of (1) industrial total output value, economic added value, power saving rate, power saving amount, economic elasticity coefficient, phase voltage of each phase, phase current of each phase, power factor of each phase, unqualified voltage accumulated time, unbalanced current accumulated time, overload accumulated time, three-phase current unbalance degree, load rate, ten thousand yuan of output value power consumption, product energy consumption, energy efficiency of energy consumption equipment, electromagnetic pollution, harmonic content and lost electric quantity;
the economic contribution characteristic indexes of the power users comprise: an industry increase value coefficient, an industry final consumption coefficient, an industry investment coefficient, an industry export coefficient, a backward industry drive contribution index, a forward industry drive contribution index and an industry influence coefficient;
the energy-saving and environment-friendly characteristic indexes comprise: the method comprises the steps of industrial pollution source treatment investment, environment infrastructure construction investment, environment-friendly investment of three construction projects, the number of personnel of an environment-friendly system, ten thousand-yuan GDP energy consumption, sewage harmless treatment rate, garbage harmless treatment rate, water reuse rate, COD reduction and waste comprehensive utilization rate.
The invention provides an electric quantity prediction system of columnar power users in an area, which is improved in that the system comprises:
the determining module is used for determining columnar power users in the region according to the dimensionless index matrix of the power users in the region;
and the prediction module is used for predicting the electricity consumption of the pillar electricity consumers in the area by utilizing the historical electricity consumption data of the pillar electricity consumers in the area.
Compared with the closest prior art, the invention has the following beneficial effects:
according to the technical scheme provided by the invention, columnar power users in the region are determined according to a dimensionless index matrix of the power users in the region; the method comprises the following steps of extracting indexes of a dimensionless index matrix of power users from three aspects of comprehensive energy efficiency, economic contribution and energy conservation and environmental protection, further more accurately determining columnar power users in an area, and laying a foundation for predicting the power consumption of the power users in the area; the historical electricity utilization data of the columnar electricity users in the area is utilized to predict the electricity consumption of the columnar electricity users in the area, and more accurate and detailed information is provided for specific scheduling of the power grid and local economic prediction.
Drawings
Fig. 1 is a flow chart of a method for predicting power consumption of a columnar power consumer in an area;
fig. 2 is a diagram of a power prediction system for a columnar power consumer in an area.
Detailed Description
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a method for predicting electric quantity of columnar power users in an area, which comprises the following steps of:
step 101, determining columnar power users in an area according to a non-dimensionalized index matrix of the power users in the area;
and 102, predicting the electricity consumption of the columnar power consumers in the area by using the historical electricity consumption data of the columnar power consumers in the area.
In the embodiment of the present invention, electric power users in the area, such as industrial electricity, commercial electricity, residential electricity, rice field irrigation and drainage electricity, non-industrial electricity, and agricultural production electricity, upload electric energy data, which may have different sources, formats, and characteristics, may encounter the troublesome problems of data format being unable to be converted or information loss after data format conversion, and seriously hinders the flow and sharing of data in each department and each software system, so that the electric energy data of the electric power users in the area needs to be processed as follows before the specific operation of the present invention is performed:
and performing a series of integrated operations such as extraction, screening, cleaning, conversion and synthesis on the electric energy data scattered in various places to keep the electric energy data consistent.
Conversion: converting electric energy data with different sources, formats and characteristics into data with consistent formats;
screening: and non-research object data such as residential life electricity consumption, commercial electricity consumption, agricultural electricity consumption and the like are filtered.
Extracting: the data processing workload is reduced, and the collected electric energy data is subjected to data sampling. The reason for the extraction is: the uploading of the electric energy data is very frequent and fast, a large amount of data can be uploaded to a data platform every moment, the data are likely to be similar or repeated, the value density is low, the electric energy prediction may not need so much data, the data can be sampled, and the data quantity to be processed is reduced.
Cleaning: and cleaning dirty data such as error data and conflict data in the extracted electric energy data.
Specifically, the step 101 includes:
step 1: initializing t ═ t0-1;
Step 2: determining a support evaluation index of the power consumer in the t-time region according to a dimensionless index matrix of the power consumer in the t-time region;
and step 3: determining the columnar power users in the t-moment area according to the columnar evaluation indexes of the power users in the t-moment area;
and 4, step 4: judging t as t0-N is true, if yes, then t is output0The columnar power users in the region of N moments before the moment; otherwise, making t equal to t-1 and returning to the step 2;
and 5: selecting t0The first N times of the time share the regional columnar power consumer as t0Columnar power users in a time zone;
wherein N is the total time of a preset reference time interval; t is t0Is the predicted time of day.
Specifically, a dimensionless index matrix x (t) of the power consumers in the time t region is determined according to the following formula:
in the formula, x0j(t) is a reference index value, x, in the dimensionless index of the jth power consumer in the t-time regionij(t) is the jth power consumer in the t time zoneI belongs to (1-n), j belongs to (1-m), and n is the total number of the non-reference index values of the power users in the region; and m is the total number of power users in the area.
Further, the step 2 includes:
determining a correlation coefficient matrix of the power users in the t-moment area according to a dimensionless index matrix of the power users in the t-moment area;
determining the grey correlation degree of the reference index and the non-reference index of the power consumer in the t moment area according to the correlation coefficient matrix of the power consumer in the t moment area;
and selecting the non-reference index of which the grey correlation degree with the non-reference index of the power consumer in the t-time area is greater than a threshold value as the prop evaluation index of the power consumer in the t-time area.
Further, the determining a correlation coefficient matrix of the power consumers in the time t area according to the dimensionless index matrix of the power consumers in the time t area includes:
determining a correlation coefficient matrix Y (t) of the power users in the time t region according to the following formula:
in the formula, xi0i,j(t) a correlation coefficient between a reference index value and an ith non-reference index value in the dimensionless index of the jth power consumer in the t-time region;
wherein, the association coefficient xi of the reference index value and the ith non-reference index value in the dimensionless index of the jth power consumer in the t-time area is determined according to the following formula0i,j(t):
Wherein △ (max) is the maximum value in the absolute difference matrix of the power consumers in the time t region, △ (min) is the minimum value in the absolute difference matrix of the power consumers in the time t region, and ρ is a resolution coefficient;
in the best embodiment of the invention, the resolution coefficient rho is more from 0.1 to 0.5, and the difference between the correlation coefficients can be improved as the rho is smaller.
The matrix of absolute differences △ (t) for the power consumers in the area at time t is determined as follows:
in the formula, △0i,j(t) is a difference value between a reference index value and an ith non-reference index value in the dimensionless index of the jth power consumer in the t-time region.
Further, the determining a gray correlation degree between a reference index and a non-reference index of the power consumer in the time t area according to the correlation coefficient matrix of the power consumer in the time t area includes:
determining a gray association degree gamma of a reference index value and an ith non-reference index value in a dimensionless index of the jth power consumer in the t-time region according to the following formula0i(t):
In the formula, xi0i,j(t) is a correlation coefficient between a reference index value and an ith non-reference index value in the dimensionless index of the jth power consumer in the t-time region.
Further, the step 3 includes:
clustering the power users in the region according to the prop evaluation index of the power users in the region at the time t;
determining the expression degree of each cluster according to the prop evaluation index of the power consumer in each cluster at the time t;
and selecting the power users in the cluster with the highest expression degree as the columnar power users in the area at the time t.
In the specific embodiment of the invention, each power consumer is a sample, the characteristic attribute of each power consumer is one-dimensional data of the sample, all samples, namely all power consumers, are clustered into different clusters according to actual requirements, and one class with the most excellent comprehensive value of each characteristic attribute is selected from all the clusters to serve as a pillar power consumer;
further, the clustering the regional power consumers according to the prop evaluation index of the regional power consumers at the time t includes:
and if the weighted Euclidean distance between the support evaluation index of the jth power consumer and the support evaluation index of the u power consumer in the time t region is the smallest in the weighted Euclidean distance between the support evaluation index of the jth power consumer and the support evaluation indexes of all the power consumers in the time t region, the support evaluation index of the jth power consumer and the u power consumer are grouped into one.
In a specific embodiment of the present invention, a specific process of clustering power consumers in an area according to a support evaluation index of the power consumers in the area at time t may be:
initializing clusters where all power users are located in a t-moment area;
calculating a weighted Euclidean distance between a support character evaluation index of the jth power consumer and a support character evaluation index of the u power consumer in a time t region;
and c, updating the cluster of each power user in the t-moment area according to the weighted Euclidean distance between each power user in the t-moment area, outputting the cluster at the moment if the center of the cluster in the t-moment area is unchanged before and after updating, and otherwise, returning to the step b.
Furthermore, a weighted Euclidean distance d between the support evaluation index of the jth power consumer and the support evaluation index of the uth power consumer in the time zone t is determined according to the following formulaju(t):
In the formula, ωv(t) is the weight of the v-th prop evaluation index of the power consumer in the time t region; x is the number ofvj(t) is a vth support evaluation index value of a jth power consumer in the time t region; x is the number ofvu(t) is a vth prop evaluation index value of a u th power consumer in the time t region, u, j belongs to the group from 1 to m, m is the total number of the power consumers in the region, v belongs to the group from 1 to S (t), and S (t) is the total number of the prop evaluation indexes of the power consumers in the time t region;
wherein, the weight omega of the v-th prop evaluation index of the power consumer in the time t region is determined according to the following formulav(t):
In the formula, cv(t) is the contribution degree of the v-th prop evaluation index of the power consumer in the area at the time t to the clustering;
determining the contribution degree c of the v-th prop evaluation index of the power consumer in the t-time region to the cluster according to the following formulav(t):
In the formula (I), the compound is shown in the specification,the characteristic evaluation index value of the v th support column of the c th power consumer in the k th cluster in the time t region is obtained; m iskv(t) is the mean value of the v-th prop evaluation index of the power consumer in the k-th cluster in the t-moment area; m isv(t) is the mean value of the vth prop evaluation indexes of the power users in the time t region, K belongs to (1-K), and K is the total number of clusters in the time t region; c is an element of (1 to n)k(t)),nkAnd (t) is the total number of the power users of the kth cluster in the time t region.
Further, the determining the expression degree of each cluster according to the support evaluation index of the power consumer in each cluster at the time t includes:
determining the expression degree P of the kth cluster in the t-time area according to the following formulak(t):
Pk(t)=Mk(t)·ω(t)
In the formula, Mk(t) is the region at time tAn average proportion matrix of the support evaluation indexes of the power users in the kth cluster; ω (t) is a weight matrix of the support evaluation index of the power consumer;
wherein, an average proportion matrix M of the support evaluation indexes of the power users in the kth cluster in the time t region is determined according to the following formulak(t):
Mk(t)=[Mk1(t)…Mkv(t)…MkS(t)(t)]
In the formula, Mkv(t) is the average specific gravity value of the v-th prop evaluation index of the power consumer in the k-th cluster in the time t region;
determining a weight matrix omega (t) of the support evaluation index of the power consumer according to the following formula:
ω(t)=[ω1(t)…ωv(t)…ωS(t)(t)]
in the formula, ωv(t) is the weight of the v-th prop evaluation index of the power consumer in the time t region;
determining the average specific gravity value M of the v-th prop evaluation index of the power consumer in the k-th cluster in the t-time area according to the following formulakv(t):
In the formula, xvj(t) is a vth support evaluation index value of a jth power consumer in the time t region;the characteristic evaluation index value of the v th support of the c th power consumer in the k th cluster in the time t region, j belongs to (1-m), m is the total number of the power consumers in the region, nkAnd (t) is the total number of the power users of the kth cluster in the time t region.
Specifically, the step 102 includes:
and substituting the electricity utilization data of the columnar electricity users in the area delta moments before the moment to be measured into a pre-constructed neural network model to obtain the predicted value of the electricity utilization of the columnar electricity users in the area at the moment to be measured.
Further, the process of building the pre-constructed neural network model includes:
and taking the electricity utilization data of the columnar power users in the area delta moments before the historical moment as input layer training samples of the initial neural network, taking the electricity utilization data of the columnar power users in the area delta moments before the historical moment as output layer training samples of the initial neural network, training the initial neural network, and obtaining the pre-constructed neural network.
Further, the verification process of the pre-constructed neural network model includes:
substituting the electricity utilization data of the columnar power users in the area of delta moments before the historical moment into a pre-established neural network model to obtain the output data of the pre-established neural network;
and comparing the output data with the electricity utilization data of the columnar power users in the region at the historical moment, wherein if the relative errors of the output data and the electricity utilization data of the columnar power users in the region at the historical moment are less than 5%, the pre-constructed neural network is qualified, otherwise, the pre-constructed neural network is unqualified.
Further, the relative error μ of the output data and the electricity consumption data of the columnar power consumers in the region of the historical time is determined according to the following formula:
in the formula, b0The power utilization data are power utilization data of the columnar power users in the historical time; b1And substituting the electricity utilization data of the columnar power consumers in the area of the previous delta moments of the historical moment into the output data of the pre-constructed neural network model.
Further, a reference index in the dimensionless indexes of the power consumer is a tax total index of the power consumer;
the non-reference indexes in the dimensionless indexes of the power users comprise power user energy efficiency characteristic indexes, power user economic contribution characteristic indexes and energy-saving and environment-friendly characteristic indexes;
the energy efficiency characteristic indexes of the power consumer comprise: the method comprises the following steps of (1) industrial total output value, economic added value, power saving rate, power saving amount, economic elasticity coefficient, phase voltage of each phase, phase current of each phase, power factor of each phase, unqualified voltage accumulated time, unbalanced current accumulated time, overload accumulated time, three-phase current unbalance degree, load rate, ten thousand yuan of output value power consumption, product energy consumption, energy efficiency of energy consumption equipment, electromagnetic pollution, harmonic content and lost electric quantity;
the economic contribution characteristic indexes of the power users comprise: an industry increase value coefficient, an industry final consumption coefficient, an industry investment coefficient, an industry export coefficient, a backward industry drive contribution index, a forward industry drive contribution index and an industry influence coefficient;
the energy-saving and environment-friendly characteristic indexes comprise: the method comprises the steps of industrial pollution source treatment investment, environment infrastructure construction investment, environment-friendly investment of three construction projects, the number of personnel of an environment-friendly system, ten thousand-yuan GDP energy consumption, sewage harmless treatment rate, garbage harmless treatment rate, water reuse rate, COD reduction and waste comprehensive utilization rate.
The invention provides an electric quantity prediction system of a columnar power consumer in an area, as shown in fig. 2, the system comprises:
the determining module is used for determining columnar power users in the region according to the dimensionless index matrix of the power users in the region;
and the prediction module is used for predicting the electricity consumption of the pillar electricity consumers in the area by utilizing the historical electricity consumption data of the pillar electricity consumers in the area.
Specifically, the determining module includes:
an initialization unit: for initializing t ═ t0-1;
A first determination unit: the method comprises the steps that a support evaluation index of the power consumer in a t-time area is determined according to a dimensionless index matrix of the power consumer in the t-time area;
a second determination unit: the method comprises the steps that the columnar power users in the t moment area are determined according to the columnar evaluation indexes of the power users in the t moment area;
an output unit: for judging t ═ t0-N is true, if yes, then t is output0The columnar power users in the region of N moments before the moment; otherwise, making t equal to t-1 and returning to the step 2;
a selection unit: for selecting t0The first N times of the time share the regional columnar power consumer as t0Columnar power users in a time zone;
wherein N is the total time of a preset reference time interval; t is t0Is the predicted time of day.
Specifically, a dimensionless index matrix x (t) of the power consumers in the time t region is determined according to the following formula:
in the formula, x0j(t) is a reference index value, x, in the dimensionless index of the jth power consumer in the t-time regionij(t) is the ith non-reference index value in the dimensionless index of the jth power consumer in the time t region, i belongs to (1-n), j belongs to (1-m), and n is the total number of the non-reference index values of the power consumers in the region; and m is the total number of power users in the area.
Specifically, the first determining unit includes:
the first determining subunit is used for determining a correlation coefficient matrix of the power users in the t-time area according to the dimensionless index matrix of the power users in the t-time area;
the second determining subunit is used for determining the grey correlation degree of the reference index and the non-reference index of the power consumer in the t moment area according to the correlation coefficient matrix of the power consumer in the t moment area;
and the first selection subunit is used for selecting the non-reference index of which the gray correlation degree with the non-reference index of the power consumer in the time t area is greater than a threshold value as the prop evaluation index of the power consumer in the time t area.
Specifically, the first determining subunit is configured to:
determining a correlation coefficient matrix Y (t) of the power users in the time t region according to the following formula:
in the formula, xi0i,j(t) a correlation coefficient between a reference index value and an ith non-reference index value in the dimensionless index of the jth power consumer in the t-time region;
wherein, the association coefficient xi of the reference index value and the ith non-reference index value in the dimensionless index of the jth power consumer in the t-time area is determined according to the following formula0i,j(t):
Wherein △ (max) is the maximum value in the absolute difference matrix of the power consumers in the time t region, △ (min) is the minimum value in the absolute difference matrix of the power consumers in the time t region, and ρ is a resolution coefficient;
the matrix of absolute differences △ (t) for the power consumers in the area at time t is determined as follows:
in the formula, △0i,j(t) is a difference value between a reference index value and an ith non-reference index value in the dimensionless index of the jth power consumer in the t-time region.
Specifically, the second determining subunit is configured to:
determining a gray association degree gamma of a reference index value and an ith non-reference index value in a dimensionless index of the jth power consumer in the t-time region according to the following formula0i(t):
In the formula, xi0i,j(t) isAnd a correlation coefficient between the reference index value and the ith non-reference index value in the dimensionless index of the jth power consumer in the time t region.
Specifically, the second determining unit includes:
the clustering subunit is used for clustering the power users in the region according to the prop evaluation index of the power users in the region at the time t;
the third determining subunit is used for determining the expression degree of each cluster according to the prop evaluation index of the power consumer in each cluster at the time t;
and the second selection subunit is used for selecting the power users in the cluster with the highest expression degree as the columnar power users in the area at the time t.
Specifically, the clustering subunit is configured to:
and if the weighted Euclidean distance between the support evaluation index of the jth power consumer and the support evaluation index of the u power consumer in the time t region is the smallest in the weighted Euclidean distance between the support evaluation index of the jth power consumer and the support evaluation indexes of all the power consumers in the time t region, the support evaluation index of the jth power consumer and the u power consumer are grouped into one.
Specifically, a weighted Euclidean distance d between a support evaluation index of the jth power consumer and a support evaluation index of the uth power consumer in a time zone t is determined according to the following formulaju(t):
In the formula, ωv(t) is the weight of the v-th prop evaluation index of the power consumer in the time t region; x is the number ofvj(t) is a vth support evaluation index value of a jth power consumer in the time t region; x is the number ofvu(t) is a vth prop evaluation index value of a u th power consumer in the time t region, u, j belongs to the group from 1 to m, m is the total number of the power consumers in the region, v belongs to the group from 1 to S (t), and S (t) is the total number of the prop evaluation indexes of the power consumers in the time t region;
wherein is pressed downDetermining weight omega of the v-th prop evaluation index of the power consumer in the time t region by using the formulav(t):
In the formula, cv(t) is the contribution degree of the v-th prop evaluation index of the power consumer in the area at the time t to the clustering;
determining the contribution degree c of the v-th prop evaluation index of the power consumer in the t-time region to the cluster according to the following formulav(t):
In the formula (I), the compound is shown in the specification,the characteristic evaluation index value of the v th support column of the c th power consumer in the k th cluster in the time t region is obtained; m iskv(t) is the mean value of the v-th prop evaluation index of the power consumer in the k-th cluster in the t-moment area; m isv(t) is the mean value of the vth prop evaluation indexes of the power users in the time t region, K belongs to (1-K), and K is the total number of clusters in the time t region; c is an element of (1 to n)k(t)),nkAnd (t) is the total number of the power users of the kth cluster in the time t region.
Specifically, the third determining subunit is configured to:
determining the expression degree P of the kth cluster in the t-time area according to the following formulak(t):
Pk(t)=Mk(t)·ω(t)
In the formula, Mk(t) is an average proportion matrix of the support evaluation indexes of the power users in the kth cluster in the time t region; ω (t) is a weight matrix of the support evaluation index of the power consumer;
wherein, an average proportion matrix M of the support evaluation indexes of the power users in the kth cluster in the time t region is determined according to the following formulak(t):
Mk(t)=[Mk1(t)…Mkv(t)…MkS(t)(t)]
In the formula, Mkv(t) is the average specific gravity value of the v-th prop evaluation index of the power consumer in the k-th cluster in the time t region;
determining a weight matrix omega (t) of the support evaluation index of the power consumer according to the following formula:
ω(t)=[ω1(t)…ωv(t)…ωS(t)(t)]
in the formula, ωv(t) is the weight of the v-th prop evaluation index of the power consumer in the time t region;
determining the average specific gravity value M of the v-th prop evaluation index of the power consumer in the k-th cluster in the t-time area according to the following formulakv(t):
In the formula, xvj(t) is a vth support evaluation index value of a jth power consumer in the time t region;the characteristic evaluation index value of the v th support of the c th power consumer in the k th cluster in the time t region, j belongs to (1-m), m is the total number of the power consumers in the region, nkAnd (t) is the total number of the power users of the kth cluster in the time t region.
Specifically, the prediction module is configured to:
and substituting the electricity utilization data of the columnar electricity users in the area delta moments before the moment to be measured into a pre-constructed neural network model to obtain the predicted value of the electricity utilization of the columnar electricity users in the area at the moment to be measured.
Specifically, the process of establishing the pre-constructed neural network model includes:
and taking the electricity utilization data of the columnar power users in the area delta moments before the historical moment as input layer training samples of the initial neural network, taking the electricity utilization data of the columnar power users in the area delta moments before the historical moment as output layer training samples of the initial neural network, training the initial neural network, and obtaining the pre-constructed neural network.
Specifically, the verification process of the pre-constructed neural network model includes:
substituting the electricity utilization data of the columnar power users in the area of delta moments before the historical moment into a pre-established neural network model to obtain the output data of the pre-established neural network;
and comparing the output data with the electricity utilization data of the columnar power users in the region at the historical moment, wherein if the relative errors of the output data and the electricity utilization data of the columnar power users in the region at the historical moment are less than 5%, the pre-constructed neural network is qualified, otherwise, the pre-constructed neural network is unqualified.
Specifically, the relative error μ between the output data and the electricity consumption data of the columnar electricity consumers in the region at the historical time is determined according to the following formula:
in the formula, b0The power utilization data are power utilization data of the columnar power users in the historical time; b1And substituting the electricity utilization data of the columnar power consumers in the area of the previous delta moments of the historical moment into the output data of the pre-constructed neural network model.
Specifically, a reference index in the dimensionless index of the power consumer is a total tax amount index of the power consumer;
the non-reference indexes in the dimensionless indexes of the power users comprise power user energy efficiency characteristic indexes, power user economic contribution characteristic indexes and energy-saving and environment-friendly characteristic indexes;
the energy efficiency characteristic indexes of the power consumer comprise: the method comprises the following steps of (1) industrial total output value, economic added value, power saving rate, power saving amount, economic elasticity coefficient, phase voltage of each phase, phase current of each phase, power factor of each phase, unqualified voltage accumulated time, unbalanced current accumulated time, overload accumulated time, three-phase current unbalance degree, load rate, ten thousand yuan of output value power consumption, product energy consumption, energy efficiency of energy consumption equipment, electromagnetic pollution, harmonic content and lost electric quantity;
the economic contribution characteristic indexes of the power users comprise: an industry increase value coefficient, an industry final consumption coefficient, an industry investment coefficient, an industry export coefficient, a backward industry drive contribution index, a forward industry drive contribution index and an industry influence coefficient;
the energy-saving and environment-friendly characteristic indexes comprise: the method comprises the steps of industrial pollution source treatment investment, environment infrastructure construction investment, environment-friendly investment of three construction projects, the number of personnel of an environment-friendly system, ten thousand-yuan GDP energy consumption, sewage harmless treatment rate, garbage harmless treatment rate, water reuse rate, COD reduction and waste comprehensive utilization rate.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (16)
1. A method for predicting power consumption of a columnar power consumer in an area, the method comprising:
determining columnar power users in the region according to a dimensionless index matrix of the power users in the region;
and predicting the electricity consumption of the columnar electricity consumers in the area by utilizing the historical electricity consumption data of the columnar electricity consumers in the area.
2. The method of claim 1, wherein determining the columnar power consumers in the region according to a non-dimensionalized index matrix of the power consumers in the region comprises:
step 1: initializing t ═ t0-1;
Step 2: determining a support evaluation index of the power consumer in the t-time region according to a dimensionless index matrix of the power consumer in the t-time region;
and step 3: determining the columnar power users in the t-moment area according to the columnar evaluation indexes of the power users in the t-moment area;
and 4, step 4: judging t as t0-N is true, if yes, then t is output0The columnar power users in the region of N moments before the moment; otherwise, making t equal to t-1 and returning to the step 2;
and 5: selecting t0The first N times of the time share the regional columnar power consumer as t0Columnar power users in a time zone;
wherein N is the total time of a preset reference time interval; t is t0Is the predicted time of day.
3. The method according to claim 2, wherein the non-dimensionalized index matrix x (t) of the power consumers in the time t region is determined according to the following equation:
in the formula, x0j(t) is a reference index value, x, in the dimensionless index of the jth power consumer in the t-time regionij(t) is the ith non-reference index value in the dimensionless index of the jth power consumer in the time t region, i belongs to (1-n), j belongs to (1-m), and n is the total number of the non-reference index values of the power consumers in the region; and m is the total number of power users in the area.
4. The method of claim 3, wherein step 2, comprises:
determining a correlation coefficient matrix of the power users in the t-moment area according to a dimensionless index matrix of the power users in the t-moment area;
determining the grey correlation degree of the reference index and the non-reference index of the power consumer in the t moment area according to the correlation coefficient matrix of the power consumer in the t moment area;
and selecting the non-reference index of which the grey correlation degree with the non-reference index of the power consumer in the t-time area is greater than a threshold value as the prop evaluation index of the power consumer in the t-time area.
5. The method according to claim 4, wherein the determining the correlation coefficient matrix of the power consumers in the time t region according to the non-dimensionalized index matrix of the power consumers in the time t region comprises:
determining a correlation coefficient matrix Y (t) of the power users in the time t region according to the following formula:
in the formula, xi0i,j(t) a correlation coefficient between a reference index value and an ith non-reference index value in the dimensionless index of the jth power consumer in the t-time region;
wherein, the association coefficient xi of the reference index value and the ith non-reference index value in the dimensionless index of the jth power consumer in the t-time area is determined according to the following formula0i,j(t):
Wherein △ (max) is the maximum value in the absolute difference matrix of the power consumers in the time t region, △ (min) is the minimum value in the absolute difference matrix of the power consumers in the time t region, and ρ is a resolution coefficient;
the matrix of absolute differences △ (t) for the power consumers in the area at time t is determined as follows:
in the formula, △0i,j(t) is a difference value between a reference index value and an ith non-reference index value in the dimensionless index of the jth power consumer in the t-time region.
6. The method of claim 4, wherein the determining the grey correlation degree between the reference index and the non-reference index of the power consumer in the time t region according to the correlation coefficient matrix of the power consumer in the time t region comprises:
determining a gray association degree gamma of a reference index value and an ith non-reference index value in a dimensionless index of the jth power consumer in the t-time region according to the following formula0i(t):
In the formula, xi0i,j(t) is a correlation coefficient between a reference index value and an ith non-reference index value in the dimensionless index of the jth power consumer in the t-time region.
7. The method of claim 2, wherein step 3, comprises:
clustering the power users in the region according to the prop evaluation index of the power users in the region at the time t;
determining the expression degree of each cluster according to the prop evaluation index of the power consumer in each cluster at the time t;
and selecting the power users in the cluster with the highest expression degree as the columnar power users in the area at the time t.
8. The method of claim 7, wherein the clustering the regional power consumers according to the pillar evaluation index of the regional power consumers at time t comprises:
and if the weighted Euclidean distance between the support evaluation index of the jth power consumer and the support evaluation index of the u power consumer in the time t region is the smallest in the weighted Euclidean distance between the support evaluation index of the jth power consumer and the support evaluation indexes of all the power consumers in the time t region, the support evaluation index of the jth power consumer and the u power consumer are grouped into one.
9. The method of claim 8, wherein the weighted euclidean distance d between the jth power consumer's laterality assessment indicator and the jth power consumer's laterality assessment indicator within the time t zone is determined as followsju(t):
In the formula, ωv(t) is the weight of the v-th prop evaluation index of the power consumer in the time t region; x is the number ofvj(t) is a vth support evaluation index value of a jth power consumer in the time t region; x is the number ofvu(t) is a vth prop evaluation index value of a u th power consumer in the time t region, u, j belongs to the group from 1 to m, m is the total number of the power consumers in the region, v belongs to the group from 1 to S (t), and S (t) is the total number of the prop evaluation indexes of the power consumers in the time t region;
wherein, the weight omega of the v-th prop evaluation index of the power consumer in the time t region is determined according to the following formulav(t):
In the formula, cv(t) is the contribution degree of the v-th prop evaluation index of the power consumer in the area at the time t to the clustering;
determining the contribution degree c of the v-th prop evaluation index of the power consumer in the t-time region to the cluster according to the following formulav(t):
In the formula (I), the compound is shown in the specification,the characteristic evaluation index value of the v th support column of the c th power consumer in the k th cluster in the time t region is obtained; m iskv(t) Power consumption in the kth Cluster in the region at time tMean value of the vth prop evaluation index of the house; m isv(t) is the mean value of the vth prop evaluation indexes of the power users in the time t region, K belongs to (1-K), and K is the total number of clusters in the time t region; c is an element of (1 to n)k(t)),nkAnd (t) is the total number of the power users of the kth cluster in the time t region.
10. The method of claim 7, wherein determining the performance of each cluster according to the support evaluation index of the power consumer in each cluster at time t comprises:
determining the expression degree P of the kth cluster in the t-time area according to the following formulak(t):
Pk(t)=Mk(t)·ω(t)
In the formula, Mk(t) is an average proportion matrix of the support evaluation indexes of the power users in the kth cluster in the time t region; ω (t) is a weight matrix of the support evaluation index of the power consumer;
wherein, an average proportion matrix M of the support evaluation indexes of the power users in the kth cluster in the time t region is determined according to the following formulak(t):
Mk(t)=[Mk1(t)…Mkv(t)…MkS(t)(t)]
In the formula, Mkv(t) is the average specific gravity value of the v-th prop evaluation index of the power consumer in the k-th cluster in the time t region;
determining a weight matrix omega (t) of the support evaluation index of the power consumer according to the following formula:
ω(t)=[ω1(t)…ωv(t)…ωS(t)(t)]
in the formula, ωv(t) is the weight of the v-th prop evaluation index of the power consumer in the time t region;
determining the average specific gravity value M of the v-th prop evaluation index of the power consumer in the k-th cluster in the t-time area according to the following formulakv(t):
In the formula, xvj(t) is a vth support evaluation index value of a jth power consumer in the time t region;the characteristic evaluation index value of the v th support of the c th power consumer in the k th cluster in the time t region, j belongs to (1-m), m is the total number of the power consumers in the region, nkAnd (t) is the total number of the power users of the kth cluster in the time t region.
11. The method of claim 1, wherein predicting electricity usage by the columnar electricity consumers in the area using historical electricity usage data of the columnar electricity consumers in the area comprises:
and substituting the electricity utilization data of the columnar electricity users in the area delta moments before the moment to be measured into a pre-constructed neural network model to obtain the predicted value of the electricity utilization of the columnar electricity users in the area at the moment to be measured.
12. The method of claim 11, wherein the pre-constructed neural network model building process comprises:
and taking the electricity utilization data of the columnar power users in the area delta moments before the historical moment as input layer training samples of the initial neural network, taking the electricity utilization data of the columnar power users in the area delta moments before the historical moment as output layer training samples of the initial neural network, training the initial neural network, and obtaining the pre-constructed neural network.
13. The method of claim 11, wherein the validation process of the pre-constructed neural network model comprises:
substituting the electricity utilization data of the columnar power users in the area of delta moments before the historical moment into a pre-established neural network model to obtain the output data of the pre-established neural network;
and comparing the output data with the electricity utilization data of the columnar power users in the region at the historical moment, wherein if the relative errors of the output data and the electricity utilization data of the columnar power users in the region at the historical moment are less than 5%, the pre-constructed neural network is qualified, otherwise, the pre-constructed neural network is unqualified.
14. The method of claim 13, wherein the relative error μ of the output data to the power usage data for the columnar power consumers within the region at the historical time is determined as follows:
in the formula, b0The power utilization data are power utilization data of the columnar power users in the historical time; b1And substituting the electricity utilization data of the columnar power consumers in the area of the previous delta moments of the historical moment into the output data of the pre-constructed neural network model.
15. The method of claim 3, wherein the reference indicator in the dimensionless indicator of the power consumer is a total tax amount indicator of the power consumer;
the non-reference indexes in the dimensionless indexes of the power users comprise power user energy efficiency characteristic indexes, power user economic contribution characteristic indexes and energy-saving and environment-friendly characteristic indexes;
the energy efficiency characteristic indexes of the power consumer comprise: the method comprises the following steps of (1) industrial total output value, economic added value, power saving rate, power saving amount, economic elasticity coefficient, phase voltage of each phase, phase current of each phase, power factor of each phase, unqualified voltage accumulated time, unbalanced current accumulated time, overload accumulated time, three-phase current unbalance degree, load rate, ten thousand yuan of output value power consumption, product energy consumption, energy efficiency of energy consumption equipment, electromagnetic pollution, harmonic content and lost electric quantity;
the economic contribution characteristic indexes of the power users comprise: an industry increase value coefficient, an industry final consumption coefficient, an industry investment coefficient, an industry export coefficient, a backward industry drive contribution index, a forward industry drive contribution index and an industry influence coefficient;
the energy-saving and environment-friendly characteristic indexes comprise: the method comprises the steps of industrial pollution source treatment investment, environment infrastructure construction investment, environment-friendly investment of three construction projects, the number of personnel of an environment-friendly system, ten thousand-yuan GDP energy consumption, sewage harmless treatment rate, garbage harmless treatment rate, water reuse rate, COD reduction and waste comprehensive utilization rate.
16. A system for predicting power of a columnar power consumer in an area, the system comprising:
the determining module is used for determining columnar power users in the region according to the dimensionless index matrix of the power users in the region;
and the prediction module is used for predicting the electricity consumption of the pillar electricity consumers in the area by utilizing the historical electricity consumption data of the pillar electricity consumers in the area.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910826364.8A CN110705750A (en) | 2019-09-03 | 2019-09-03 | Method and system for predicting electric quantity of columnar power users in region |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910826364.8A CN110705750A (en) | 2019-09-03 | 2019-09-03 | Method and system for predicting electric quantity of columnar power users in region |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110705750A true CN110705750A (en) | 2020-01-17 |
Family
ID=69193499
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910826364.8A Pending CN110705750A (en) | 2019-09-03 | 2019-09-03 | Method and system for predicting electric quantity of columnar power users in region |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110705750A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111244978A (en) * | 2020-01-19 | 2020-06-05 | 国网冀北电力有限公司电力科学研究院 | Low-voltage distribution network three-phase balancing method based on single-phase user power characteristics |
CN114580795A (en) * | 2022-05-06 | 2022-06-03 | 四川瑞康智慧能源有限公司 | Electric quantity prediction method considering power failure shunting and related equipment |
-
2019
- 2019-09-03 CN CN201910826364.8A patent/CN110705750A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111244978A (en) * | 2020-01-19 | 2020-06-05 | 国网冀北电力有限公司电力科学研究院 | Low-voltage distribution network three-phase balancing method based on single-phase user power characteristics |
CN114580795A (en) * | 2022-05-06 | 2022-06-03 | 四川瑞康智慧能源有限公司 | Electric quantity prediction method considering power failure shunting and related equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104657788B (en) | Key industry electricity demand forecasting method based on Industrial Cycle index | |
CN103714426B (en) | Medium and small radial-flow type GROUP OF HYDROPOWER STATIONS integrated dispatching system | |
CN104715292A (en) | City short-term water consumption prediction method based on least square support vector machine model | |
CN102402726A (en) | Method for predicting electric quantity of large-scale distribution network based on regional load analysis | |
CN106022538B (en) | Photovoltaic power generation prediction method based on K-means clustering improved generalized weather | |
CN107944604A (en) | A kind of weather pattern recognition methods and device for photovoltaic power prediction | |
CN106980910B (en) | Medium-and-long-term power load measuring and calculating system and method | |
CN113554466B (en) | Short-term electricity consumption prediction model construction method, prediction method and device | |
CN109389238B (en) | Ridge regression-based short-term load prediction method and device | |
CN110689162B (en) | Bus load prediction method, device and system based on user side classification | |
CN112330077B (en) | Power load prediction method, power load prediction device, computer equipment and storage medium | |
CN111401732B (en) | Hierarchical identification method for water resource supply and demand situation | |
CN108256724B (en) | Power distribution network open capacity planning method based on dynamic industry coefficient | |
CN114429053B (en) | Basin scale WEFE system adaptability simulation optimization method | |
CN105844399A (en) | Post evaluation method of power distribution network energy-saving reconstruction project | |
CN110705750A (en) | Method and system for predicting electric quantity of columnar power users in region | |
CN104638636A (en) | Power daily load characteristic indicator prediction method | |
Salam et al. | Energy consumption prediction model with deep inception residual network inspiration and LSTM | |
CN116632838B (en) | Method and device for analyzing electric energy supply of power generation enterprise | |
CN115907822A (en) | Load characteristic index relevance mining method considering region and economic influence | |
Xue et al. | Prediction of natural gas consumption for city-level DHS based on attention GRU: A case study for a northern chinese city | |
CN115545333A (en) | Method for predicting load curve of multi-load daily-type power distribution network | |
CN109858668B (en) | Coordination prediction method for power load region in thunder and lightning climate | |
CN110533243A (en) | A kind of building energy consumption prediction technique based on fractal theory | |
CN107590747A (en) | Power grid asset turnover rate computational methods based on the analysis of comprehensive energy big data |
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 |