CN111191826A - Load prediction method based on cosine similarity classification - Google Patents
Load prediction method based on cosine similarity classification Download PDFInfo
- Publication number
- CN111191826A CN111191826A CN201911336841.9A CN201911336841A CN111191826A CN 111191826 A CN111191826 A CN 111191826A CN 201911336841 A CN201911336841 A CN 201911336841A CN 111191826 A CN111191826 A CN 111191826A
- Authority
- CN
- China
- Prior art keywords
- load
- data
- weather
- clustering model
- value
- 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 30
- 238000010219 correlation analysis Methods 0.000 claims abstract description 10
- 238000001514 detection method Methods 0.000 claims abstract description 8
- 238000010276 construction Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 4
- 241000288105 Grus Species 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Biology (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a load prediction method based on cosine similarity classification, which comprises the steps of extracting the characteristics of cosine characteristic values of load data of load detection points in units of days, and clustering the cosine characteristic values of the load detection points in units of days to generate a clustering model of the load data; performing correlation analysis on the generated clustering model of the load data and the clustering model of the weather data to find out the correlation between the specific weather and the specific load curve; and forming a set of { C, D } relationships; c is a cluster value of the load data for the network in the clustering model, and D is a cluster value of the weather data in the clustering model; after the load data and the weather data are clustered, extracting a network load data set and weather conditions on the same date according to cluster types, and performing model construction on holiday condition data, specifically, adding related load data, weather data and holiday data into input parameters of a model.
Description
Technical Field
The invention relates to the field of power grid data acquisition, in particular to a load prediction method based on cosine similarity classification.
Background
The analysis and prediction of the power supply load characteristics of the power grid enterprise network are an important aspect of the prediction work of the power grid dispatching operation mode, and the accurate grasp of the power supply load characteristics and the change trend thereof is an important basis for the work of power grid dispatching, operation mode adjustment and the like, and is also an important reference for making power grid planning and arranging equipment maintenance. Particularly, in recent years, due to the large-scale access of new energy and diversified power requirements of users, the difficulty in predicting the load characteristics of the power grid is greatly increased, on one hand, the indexes of the load supply characteristics of the power grid are increased, and the relevance among the indexes is further strengthened; on the other hand, factors influencing the change of the load characteristics are more complex, and some climatic factors such as illumination, duration, temperature, rainfall and the like have great uncertainty. Therefore, only by long-term tracking and researching the load characteristics of the power grid, the change rule of the load characteristics of the power grid can be accurately grasped. For the prediction of the network supply load, the existing algorithm basically classifies the load curve based on seasonal factors and weather condition factors. Although visually plausible, such classification approaches lack theoretical grounds to justify it. Therefore, a power grid short-term load prediction method capable of adapting to an intelligent power consumption big data environment is needed, and a prediction result can provide technical support for improving the accuracy of load prediction.
In the prediction technology of short-term load, data set feature analysis selection and prediction model construction are two important research fields currently under research. In the aspect of data set characteristic analysis selection, great progress is made from the traditional research of the regularity of load data to the analysis of the internal mechanism of load change. At present, with the wide popularization of intelligent instruments and the development of the sensing technology of the internet of things, more comprehensive and accurate fine-grained load, related influence factors and exogenous variable dependence data can be measured and collected. Consideration of multiple multi-source heterogeneous impact factors is an important basis for choosing the best feature set. The weather factors and the date type are closely related to the load change, and the weather factors mainly comprise real-time temperature, relative humidity, wind speed, rainfall and the like. The types of the dates mainly comprise working days, rest days, major holidays, years, months and the like. The load is affected differently by different factors, and too many similar redundant features will cause the training period to be prolonged and the prediction effect to be poor. Analytical selection of influencing factors is therefore necessary. The main methods for feature selection are correlation coefficient method (CA), Mutual Information (MI) and Conditional Mutual Information (CMI) techniques, etc., and the feature variables affecting the load are often non-linear, such as temperature, relative humidity, etc. Therefore, the short-term prediction of the water load by adopting the correlation coefficient method has good effect.
Disclosure of Invention
1. The technical problem to be solved is as follows:
aiming at the technical problems, the invention provides a load prediction method based on cosine similarity classification.
2. The technical scheme is as follows:
a load prediction method based on cosine similarity classification is characterized in that: the method comprises the following steps:
the method comprises the following steps: performing characteristic extraction on the cosine characteristic values of the load data of the load detection points by taking days as units, and performing clustering processing on the cosine characteristic values of the load detection points by taking days as units to generate a clustering model of the load data;
step two: performing correlation analysis on the clustering model of the load data and the clustering model of the weather data generated in the step one to find out the correlation between the specific weather and the specific load curve; and forming a set of { C, D } relationships; c is a cluster value of the load data for the network in the clustering model, and D is a cluster value of the weather data in the clustering model;
step three: after the load data and the weather data are clustered, extracting a network load data set and weather conditions on the same date according to cluster types, and performing model construction on holiday condition data, specifically, adding related load data, weather data and holiday data into input parameters of a model.
Further, the step one further includes a load data per unit processing process, specifically: the formula of the per-unit treatment is as the formula (1):
x in the formula (1)iIs the load value, p, of the measurement point i after per unitiFor measuring the load value, p, of point imax、pminRespectively a maximum value and a minimum value in the original load curve; performing cosine value calculation on the load points a and b adjacent to each other after per unit in the formula (2), wherein: suppose the vector of a is (x)1,y1) The vector of b is (x)2,y2)。
Further, the step two also includes: before the clustering model of the load data and the clustering model of the weather data are subjected to correlation analysis, the weather data are converted from unstructured data to structured data, namely the literal information of the weather state and the wind direction are converted into numerical formats; and performing correlation analysis on the clustering model of the load data and the clustering model of the weather data to form a group of { C, D } relations, wherein C is a cluster value of the load characteristic of the network in the clustering model, and D is a specific formula of the cluster value of the weather data in the clustering model:
Support(Ci->Cj)=P(CiU Cj) (3)
Confidence(Ci->Cj)=P(Ci|Cj) (4)
wherein, Support (C)i->Cj) Refers to the probability that a given set of items will occur simultaneously in transaction T; confidence (C)i->Cj) Finger appearance of CiIn transaction T, item set CjProbability of occurrence at the same time; the support degree is as formula (3), and the confidence degree is as publicFormula (4).
Further, the third step comprises the following specific steps:
301 constructing a 5-layer network based on GRU, comprising 1 input layer, 3 hidden layers and 1 output layer; the input layer is load data and weather data of an input time point; the output layer is a predicted load value of a single time point;
302, designating 3D data with input layer nodes as GRUs, wherein the time step is 240, the characteristics are 7, the number of nodes of the first hidden layer is GRU layer is 25, the number of nodes of the second hidden layer is 25, the number of nodes of the third hidden layer is 32, and the number of output nodes is 1;
303, calculating output values of 3 hidden layers and 1 output layer and weight values and bias values among the layers by the trained GRU network; and adding dropout method between layers for preventing and fitting to complete GRU global training;
and 304, obtaining an optimal power grid load prediction model according to the optimal weight and the bias value of the prediction system.
3. Has the advantages that:
the method comprises the steps of firstly, carrying out cluster analysis on the load characteristics of the power grid by adopting a cosine method, carrying out association analysis on the cluster analysis and weather data on the basis, finally, constructing a depth sequence neural network load prediction model, and predicting the load by using a depth sequence neural network.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The present invention will be described in detail with reference to the accompanying drawings.
As shown in figure 1: a load prediction method based on cosine similarity classification is characterized in that: the method comprises the following steps:
the method comprises the following steps: performing characteristic extraction on the cosine characteristic values of the load data of the load detection points by taking days as units, and performing clustering processing on the cosine characteristic values of the load detection points by taking days as units to generate a clustering model of the load data;
step two: performing correlation analysis on the clustering model of the load data and the clustering model of the weather data generated in the step one to find out the correlation between the specific weather and the specific load curve; and forming a set of { C, D } relationships; c is a cluster value of the load data for the network in the clustering model, and D is a cluster value of the weather data in the clustering model;
step three: after the load data and the weather data are clustered, extracting a network load data set and weather conditions on the same date according to cluster types, and performing model construction on holiday condition data, specifically, adding related load data, weather data and holiday data into input parameters of a model.
Further, the step one further includes a load data per unit processing process, specifically: the formula of the per-unit treatment is as the formula (1):
x in the formula (1)iIs the load value, p, of the measurement point i after per unitiFor measuring the load value, p, of point imax、pminRespectively a maximum value and a minimum value in the original load curve; performing cosine value calculation on the load points a and b adjacent to each other after per unit in the formula (2), wherein: suppose the vector of a is (x)1,y1) The vector of b is (x)2,y2)。
Further, the step two also includes: before the clustering model of the load data and the clustering model of the weather data are subjected to correlation analysis, the weather data are converted from unstructured data to structured data, namely the literal information of the weather state and the wind direction are converted into numerical formats; and performing correlation analysis on the clustering model of the load data and the clustering model of the weather data to form a group of { C, D } relations, wherein C is a cluster value of the load characteristic of the network in the clustering model, and D is a specific formula of the cluster value of the weather data in the clustering model:
Support(Ci->Cj)=P(CiU Cj) (3)
Confidence(Ci->Cj)=P(Ci|Cj) (4)
wherein, Support (C)i->Cj) Refers to the probability that a given set of items will occur simultaneously in transaction T; confidence (C)i->Cj) Finger appearance of CiIn transaction T, item set CjProbability of occurrence at the same time; the support degree is as formula (3), and the confidence degree is as formula (4).
Further, the third step comprises the following specific steps:
301 constructing a 5-layer network based on GRU, comprising 1 input layer, 3 hidden layers and 1 output layer; the input layer is load data and weather data of an input time point; the output layer is a predicted load value of a single time point;
302, designating 3D data with input layer nodes as GRUs, wherein the time step is 240, the characteristics are 7, the number of nodes of the first hidden layer is GRU layer is 25, the number of nodes of the second hidden layer is 25, the number of nodes of the third hidden layer is 32, and the number of output nodes is 1;
303, calculating output values of 3 hidden layers and 1 output layer and weight values and bias values among the layers by the trained GRU network; and adding dropout method between layers for preventing and fitting to complete GRU global training;
and 304, obtaining an optimal power grid load prediction model according to the optimal weight and the bias value of the prediction system.
Although the present invention has been described with reference to the preferred embodiments, it should be understood that various changes and modifications can be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (4)
1. A load prediction method based on cosine similarity classification is characterized in that: the method comprises the following steps:
the method comprises the following steps: performing characteristic extraction on the cosine characteristic values of the load data of the load detection points by taking days as units, and performing clustering processing on the cosine characteristic values of the load detection points by taking days as units to generate a clustering model of the load data;
step two: performing correlation analysis on the clustering model of the load data and the clustering model of the weather data generated in the step one to find out the correlation between the specific weather and the specific load curve; and forming a set of { C, D } relationships; c is a cluster value of the load data for the network in the clustering model, and D is a cluster value of the weather data in the clustering model;
step three: after the load data and the weather data are clustered, extracting a network load data set and weather conditions on the same date according to cluster types, and performing model construction on holiday condition data, specifically, adding related load data, weather data and holiday data into input parameters of a model.
2. The load prediction method based on cosine similarity classification as claimed in claim 1, wherein: the first step further comprises a load data per unit processing process, which specifically comprises the following steps: the formula of the per-unit treatment is as the formula (1):
x in the formula (1)iIs the load value, p, of the measurement point i after per unitiFor measuring the load value, p, of point imax、pminRespectively a maximum value and a minimum value in the original load curve;
performing cosine value calculation on the load points a and b adjacent to each other after per unit in the formula (2), wherein: suppose the vector of a is (x)1,y1) The vector of b is (x)2,y2)。
3. The load prediction method based on cosine similarity classification as claimed in claim 1, wherein: the second step also comprises: before the clustering model of the load data and the clustering model of the weather data are subjected to correlation analysis, the weather data are converted from unstructured data to structured data, namely the literal information of the weather state and the wind direction are converted into numerical formats; performing correlation analysis on the clustering model of the load data and the clustering model of the weather data to form a group of { C, D } relations, wherein C is a cluster value of the load characteristic in the clustering model for the network, and D is a specific formula of the cluster value of the weather data in the clustering model:
Support(Ci->Cj)=P(CiUCj) (3)
Confidence(Ci->Cj)=P(Ci|Cj) (4)
wherein, Support (C)i->Cj) Refers to the probability that a given set of items will occur simultaneously in transaction T; confidence (C)i->Cj) Finger appearance of CiIn transaction T, item set CjProbability of occurrence at the same time; the support degree is as formula (3), and the confidence degree is as formula (4).
4. The load prediction method based on cosine similarity classification as claimed in claim 1, wherein: the third step comprises the following specific steps:
301 constructing a 5-layer network based on GRU, comprising 1 input layer, 3 hidden layers and 1 output layer; the input layer is load data and weather data of an input time point; the output layer is a predicted load value of a single time point;
302, designating 3D data with input layer nodes as GRUs, wherein the time step is 240, the characteristics are 7, the number of nodes of the first hidden layer is GRU layer is 25, the number of nodes of the second hidden layer is 25, the number of nodes of the third hidden layer is 32, and the number of output nodes is 1;
303, calculating output values of 3 hidden layers and 1 output layer and weight values and bias values among the layers by the trained GRU network; and adding dropout method between layers for preventing and fitting to complete GRU global training;
and 304, obtaining an optimal power grid load prediction model according to the optimal weight and the bias value of the prediction system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911336841.9A CN111191826A (en) | 2019-12-23 | 2019-12-23 | Load prediction method based on cosine similarity classification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911336841.9A CN111191826A (en) | 2019-12-23 | 2019-12-23 | Load prediction method based on cosine similarity classification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111191826A true CN111191826A (en) | 2020-05-22 |
Family
ID=70709248
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911336841.9A Pending CN111191826A (en) | 2019-12-23 | 2019-12-23 | Load prediction method based on cosine similarity classification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111191826A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112215426A (en) * | 2020-10-16 | 2021-01-12 | 国网山东省电力公司信息通信公司 | Short-term power load prediction method |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105069525A (en) * | 2015-07-30 | 2015-11-18 | 广西大学 | All-weather 96-point daily load curve prediction and optimization correction system |
CN109657844A (en) * | 2018-11-28 | 2019-04-19 | 国电南瑞科技股份有限公司 | Power Short-Term Load Forecasting method and apparatus |
CN109711620A (en) * | 2018-12-26 | 2019-05-03 | 浙江大学 | A kind of Short-Term Load Forecasting Method based on GRU neural network and transfer learning |
CN109934395A (en) * | 2019-03-04 | 2019-06-25 | 三峡大学 | A kind of more small power station areas Short-Term Load Forecasting Method based on timesharing subregion meteorological data |
-
2019
- 2019-12-23 CN CN201911336841.9A patent/CN111191826A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105069525A (en) * | 2015-07-30 | 2015-11-18 | 广西大学 | All-weather 96-point daily load curve prediction and optimization correction system |
CN109657844A (en) * | 2018-11-28 | 2019-04-19 | 国电南瑞科技股份有限公司 | Power Short-Term Load Forecasting method and apparatus |
CN109711620A (en) * | 2018-12-26 | 2019-05-03 | 浙江大学 | A kind of Short-Term Load Forecasting Method based on GRU neural network and transfer learning |
CN109934395A (en) * | 2019-03-04 | 2019-06-25 | 三峡大学 | A kind of more small power station areas Short-Term Load Forecasting Method based on timesharing subregion meteorological data |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112215426A (en) * | 2020-10-16 | 2021-01-12 | 国网山东省电力公司信息通信公司 | Short-term power load prediction method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113962364B (en) | Multi-factor power load prediction method based on deep learning | |
CN111626518A (en) | Urban daily water demand online prediction method based on deep learning neural network | |
CN106779859A (en) | A kind of real-time Method for Sales Forecast method of mobile terminal product | |
CN110414788A (en) | A kind of power quality prediction technique based on similar day and improvement LSTM | |
CN107016068A (en) | Knowledge mapping construction method and device | |
CN109143408B (en) | Dynamic region combined short-time rainfall forecasting method based on MLP | |
CN113157800B (en) | Identification method for discovering dynamic target in air in real time | |
Li et al. | Deep spatio-temporal wind power forecasting | |
CN111062539B (en) | Total electric quantity prediction method based on secondary electric quantity characteristic cluster analysis | |
CN115358437A (en) | Power supply load prediction method based on convolutional neural network | |
CN111191826A (en) | Load prediction method based on cosine similarity classification | |
CN112417308A (en) | User portrait label generation method based on electric power big data | |
CN112132344A (en) | Short-term wind power prediction method based on similar day and FRS-SVM | |
CN110619176A (en) | Aviation kerosene flash point prediction method based on DBN-RLSSVM | |
CN116703644A (en) | Attention-RNN-based short-term power load prediction method | |
CN107507885B (en) | Manufacture of solar cells process monitoring method based on multichannel sensor data | |
CN111435471A (en) | Heat supply gas consumption prediction model based on L STM | |
Yuan et al. | A hybrid deep learning model for predicting PM2. 5 | |
Wang et al. | Time series forecasting based on cloud process neural network | |
Ompusunggu et al. | IMPLEMENTATION OF DATA MINING TO PREDICT THE VALUE OF INDONESIAN OIL AND NON-OIL AND GAS IMPORT EXPORTS USING THE LINEAR REGRESSION METHOD | |
Gao et al. | Integrated deep neural networks-based complex system for urban water management | |
Elahe et al. | An adaptive and parallel forecasting strategy for short-term power load based on second learning of error trend | |
Zeng et al. | Ultra Short-Term Power Load Forecasting Based on Similar Day Clustering and Ensemble Empirical Mode Decomposition. Energies 2023, 16, 1989 | |
Kuang et al. | Short-term power load forecasting method in rural areas based on cnn-lstm | |
Wang et al. | Power load forecasting using data mining and knowledge discovery technology |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200522 |