CN115392527A - Regional electric quantity prediction method based on daily electric quantity collection number - Google Patents
Regional electric quantity prediction method based on daily electric quantity collection number Download PDFInfo
- Publication number
- CN115392527A CN115392527A CN202210608488.0A CN202210608488A CN115392527A CN 115392527 A CN115392527 A CN 115392527A CN 202210608488 A CN202210608488 A CN 202210608488A CN 115392527 A CN115392527 A CN 115392527A
- Authority
- CN
- China
- Prior art keywords
- electric quantity
- daily
- data
- model
- prediction
- 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 29
- 238000004458 analytical method Methods 0.000 claims abstract description 7
- 238000013528 artificial neural network Methods 0.000 claims abstract description 5
- 238000012360 testing method Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims abstract description 4
- 230000005611 electricity Effects 0.000 claims description 20
- 238000011176 pooling Methods 0.000 claims description 6
- 230000002457 bidirectional effect Effects 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 claims 2
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 claims 2
- 238000011161 development Methods 0.000 description 5
- 239000003795 chemical substances by application Substances 0.000 description 4
- 238000010248 power generation Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008520 organization Effects 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
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Biomedical Technology (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Power Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a regional electric quantity prediction method based on a daily electric quantity collection number, which is based on the daily electric quantity data of a collection system and a neural network algorithm and comprises the following steps; s1, acquiring basic data from an acquisition system and a meteorological data network; s2, performing relevance analysis on the acquired daily electric quantity data by combining meteorological data, and finding out characteristic quantity with strong relevance with the daily electric quantity as input of a prediction model; and S3, designing a prediction model according to local cities and industries. The model self-learns through a training set, and the optimal parameters are searched and stored; then inputting the test set into a model, automatically calculating the model and inputting the predicted electric quantity of the model to realize prediction; the method and the device can improve the prediction precision of the regional internet surfing electric quantity.
Description
Technical Field
The invention relates to the technical field of power grid operation, in particular to a regional electric quantity prediction method based on daily electric quantity collection number.
Background
The national development and improvement committee printed a notice on further deepening the market reformation of the price of the coal-fired power generation on-line electricity (development and improvement price [2021 ]) 1439), a relevant item on the operation of carrying out the power grid enterprise agency electricity purchase work by the organization (development and improvement price [2021 ]) and related file requirements cancel the price of the industrial and commercial catalog electricity sale and promote industrial and commercial users to enter the electricity market in 2021. For industrial and commercial users who do not purchase electricity directly from the electricity market temporarily, the electricity is purchased from the electricity market by the power grid enterprise in a proxy mode.
According to government document requirements and electric power market rules, the power grid enterprise agent users participate in electric power market transactions to form agent electricity purchasing prices, the power grid enterprise needs to predict the electric quantity and a typical load curve of the agent electricity purchasing business users every month, separately predict the electric quantity of residents and agriculture, and consider factors such as season changes and holiday arrangement. Therefore, monthly electric quantity prediction becomes an important index for assessing power grid enterprises, and has very important significance for national power grid companies to determine the total quantity of electric quantity sold, decompose electric quantity sales indexes, formulate ordered power utilization schemes, guide the reasonable operation of power plants and power transmission and distribution networks, and promote the construction and development of power markets.
With the continuous development of the power industry in China and the continuous increase of the data volume of power utilization business, a massive customer power utilization data source is formed, and the fact that the power industry in China is in a big data era is marked. Under the background of the electric big data era, accurate prediction of electric power demand also becomes one of the main bases for better decision-making deployment and reasonable arrangement work of power generation and electricity selling enterprises of power grid enterprises.
Disclosure of Invention
The invention provides a regional electric quantity prediction method based on daily electric quantity collection number, which can improve the prediction precision of regional internet electric quantity prediction.
The invention adopts the following technical scheme.
A regional electric quantity prediction method based on a daily electric quantity collection number is based on the daily electric quantity data of a collection system and a neural network algorithm and comprises the following steps;
s1, acquiring basic data from an acquisition system and a meteorological data network;
s2, performing relevance analysis on the acquired daily electric quantity data by combining meteorological data, and finding out characteristic quantity with strong relevance with the daily electric quantity as input of a prediction model;
and S3, designing a prediction model according to local cities and industry. The model self-learns through a training set, and the optimal parameters are searched and stored; and then inputting the test set into a model, and automatically calculating and inputting the predicted electric quantity by the model to realize prediction.
In step S1, original data is transformed by a normalized data processing method, the data is mapped to a designated interval to form basic data, the designated interval is defaulted to [0,1], and the formula is
X"＝X′*(mx-mi)+mi
The formula acts on each row of the original data, max is the maximum value of one row, min is the minimum value of one row, X' is the final result, and mx and mi are respectively designated interval values; default mx is 1 and mi is 0.
And (3) performing relevance analysis in the step (S2), measuring the linear correlation degree between the characteristics by adopting a pearson correlation coefficient method, and selecting the characteristics with large absolute values of the correlation coefficients as the input characteristics of the model.
The prediction model in the step S3 is a DRSN-BiLSTM-self-attention model, a DRSN network and a BiLSTM network are combined, and a self-attention mechanism self-attention is introduced at the output end;
the overall structure of the DRSN-BilSTM-self-attention model consists of three parts: an input layer, a hidden layer and an output layer; the stacking mode is according to the structure of a model, namely from bottom to top, the output of the former is used as the input of the latter; wherein, the hidden layer comprises a pooling layer, a BilSTM layer and a full-connection layer;
firstly, the DRSN adaptively extracts effective characteristics from input data; then, the BilSTM automatically calculates the time sequence dependence relationship between the characteristics and the daily electric quantity through the rich characteristics output by the BiLSTM; then, introducing a self-attention mechanism at the output end of the deep learning network, aiming at distributing attention weight to the output of the BilSTM hidden layer and highlighting the influence of key factors on daily electric quantity; and finally, outputting the data by the full connection layer, thereby realizing the prediction of the daily electric quantity.
The prediction model is a daily electric quantity prediction model, the used data is various data related to daily electric quantity prediction, namely data related to time information, and a DRSN network is adopted for deep feature extraction;
the DRSN network is based on a ResNet model, soft thresholding is used as a nonlinear layer to be introduced into a network structure of the ResNet, effective features are directly obtained from original data through alternate use of a convolutional layer and a pooling layer in a local connection and weight sharing mode, local features of the data are automatically extracted, and complete feature vectors are established.
The prediction model optimizes the capture of bidirectional semantic dependence through a BilSTM network; the BilSTM network is based on an LSTM model that can capture dependencies over longer distances.
The self-attention mechanism is used for reducing dependence on external information, capturing internal relevance of data or features, and screening out a small amount of important information from a large amount of information.
The evaluation indexes of the self-attention mechanism comprise a Root Mean Square Error (RMSE) and a Mean Absolute Percentage Error (MAPE);
the Root Mean Square Error (RMSE) represents a sample standard deviation of a difference value between a predicted value and a true value;
wherein y is i Represents the actual value, and f i Is a predicted value;
the average absolute percentage error MAPE expresses the prediction effect by calculating the absolute error percentage, the smaller the value is, the better the formula is
Where At represents the actual value and Ft is the predicted value.
The basic data comprises data related to full-aperture daily electric quantity, data related to resident daily electric quantity, data related to agricultural daily electric quantity and data related to general industrial and commercial daily electric quantity;
the data related to the full-aperture daily electric quantity comprises historical data of the full-aperture daily electric quantity of a plurality of cities; the data related to the daily electric quantity of residents comprises the daily electric quantity history, the highest air temperature, the lowest air temperature and the legal holiday of residents of a plurality of cities;
the agricultural daily electric quantity related data comprises agricultural daily electric quantity history, highest air temperature, lowest air temperature, solar terms and daily rainfall;
the data related to the general industrial and commercial daily electric quantity comprises general industrial and commercial daily electric quantity history, highest air temperature, lowest air temperature, legal holidays and social consumer goods retail total; wherein the social consumer goods retail gross needs to decompose monthly data into daily granularity data.
The method and the device can improve the prediction precision of the regional internet surfing electric quantity.
Drawings
The invention is described in further detail below with reference to the following figures and detailed description:
FIG. 1 is a schematic flow diagram of the present invention.
Detailed Description
As shown in the figure, the regional electric quantity prediction method based on the daily electric quantity collection number comprises the following steps based on the daily electric quantity data of a collection system and a neural network algorithm;
s1, acquiring basic data from an acquisition system and a meteorological data network;
s2, performing relevance analysis on the acquired daily electric quantity data in combination with meteorological data, and finding out characteristic quantities with strong relevance with the daily electric quantity as input of a prediction model;
and S3, designing a prediction model according to local cities and industries. The model self-learns through a training set, and the optimal parameters are searched and stored; and then inputting the test set into a model, and automatically calculating and inputting the predicted electric quantity by the model to realize prediction.
In step S1, original data is transformed by a normalized data processing method, the data is mapped to a designated interval to form basic data, the designated interval is defaulted to be [0,1], and the formula is
X"＝X′*(mx-mi)+mi
The formula acts on each row of the original data, max is the maximum value of one row, min is the minimum value of one row, X' is the final result, and mx and mi are respectively designated interval values; default mx is 1 and mi is 0.
And (3) performing relevance analysis in the step S2, measuring the linear correlation degree between the characteristics by adopting a pearson correlation coefficient method, and selecting the characteristics with large absolute values of the correlation coefficients as the input characteristics of the model.
The prediction model in the step S3 is a DRSN-BiLSTM-self-attention model, a DRSN network and a BiLSTM network are combined, and a self-attention mechanism self-attention is introduced at the output end;
the overall structure of the DRSN-BilSTM-self-anchorage model consists of three parts: an input layer, a hidden layer and an output layer; the stacking mode is according to the structure of a model, namely, the output of the model is used as the input of the model from bottom to top; wherein, the hidden layer comprises a pooling layer, a BilSTM layer and a full-connection layer;
firstly, the DRSN adaptively extracts effective characteristics from input data; then, the BilSTM automatically calculates the time sequence dependence relationship between the characteristics and the daily electric quantity through the rich characteristics output by the BiLSTM; then, introducing a self-attention mechanism at the output end of the deep learning network, aiming at distributing attention weight to the output of the BilSTM hidden layer and highlighting the influence of key factors on daily electricity; and finally, outputting the data by the full connection layer, thereby realizing the prediction of the daily electric quantity.
The prediction model is a daily electric quantity prediction model, the used data is various data related to daily electric quantity prediction, namely data related to time information, and a DRSN network is adopted for deep feature extraction;
the DRSN network is based on a ResNet model, soft thresholding is used as a nonlinear layer to be introduced into a network structure of the ResNet, effective features are directly obtained from original data through alternate use of a convolutional layer and a pooling layer in a local connection and weight sharing mode, local features of the data are automatically extracted, and complete feature vectors are established.
The prediction model optimizes the capture of bidirectional semantic dependence through a BilSTM network; the BilSTM network is based on an LSTM model that can capture dependencies over longer distances.
The self-attention mechanism is used for reducing dependence on external information, capturing internal relevance of data or features, and screening out a small amount of important information from a large amount of information.
The evaluation indexes of the self-attention mechanism comprise a Root Mean Square Error (RMSE) and a Mean Absolute Percentage Error (MAPE);
the root mean square error RMSE represents a sample standard deviation of a difference value between a predicted value and a true value, and the formula is shown as follows;
wherein y is i Represents the actual value, and f i Is a predicted value;
the average absolute percentage error MAPE expresses the prediction effect by calculating the absolute error percentage, the smaller the value is, the better the formula is
Where At represents the actual value and Ft is the predicted value.
The basic data comprises data related to full-aperture daily electric quantity, data related to resident daily electric quantity, data related to agricultural daily electric quantity and data related to general industrial and commercial daily electric quantity;
the data related to the full-aperture daily electric quantity comprises historical data of the full-aperture daily electric quantity of a plurality of cities; the data related to the daily electricity consumption of residents comprises daily electricity consumption history, the highest air temperature, the lowest air temperature and legal festivals and holidays of residents in a plurality of cities;
the agricultural daily electric quantity related data comprises agricultural daily electric quantity history, highest air temperature, lowest air temperature, solar terms and daily rainfall;
the data related to the general industrial and commercial daily electric quantity comprises general industrial and commercial daily electric quantity history, highest air temperature, lowest air temperature, legal holidays and social consumer goods retail total; wherein the social consumer goods retail gross needs to decompose monthly data into daily granularity data.
Example (b):
in the embodiment, an electric quantity prediction mechanism and a model algorithm are established and perfected, next-month required electric quantity such as electric quantity of industrial and commercial users, security electric quantity, pumped storage electric quantity and line loss electric quantity for purchasing electricity by agents of a company, next-month on-line electric quantity such as low-price power supply on-line electric quantity, security and price priority power generation on-line electric quantity and pumped storage on-line electric quantity are predicted respectively every month, next-month marketized purchased electric quantity scale is determined, and prediction accuracy is improved as much as possible.
And predicting the full-aperture (without external power sale, the same below) monthly power of residents, agriculture and general industry and commerce of the company in two months later by using novel prediction algorithms such as a neural network and the like, wherein the results comprise results of the whole province and the Jiu Di city.
Claims (9)
1. A regional electric quantity prediction method based on daily electric quantity collection number is based on the daily electric quantity data of a collection system and a neural network algorithm, and is characterized in that: comprises the following steps;
s1, acquiring basic data from an acquisition system and a meteorological data network;
s2, performing relevance analysis on the acquired daily electric quantity data in combination with meteorological data, and finding out characteristic quantities with strong relevance with the daily electric quantity as input of a prediction model;
and S3, designing a prediction model according to local cities and industry. The model self-learns through a training set, and the optimal parameters are searched and stored; then the test set is input into the model, and the model automatically calculates and inputs the predicted electric quantity to realize prediction.
2. The method of claim 1, wherein the regional power prediction method based on the number of collected daily power is as follows: in step S1, original data is transformed by a normalized data processing method, the data is mapped to a designated interval to form basic data, the designated interval is defaulted to be [0,1], and the formula is
X″＝X′*(mx-mi)+mi
The formula acts on each row of the original data, max is the maximum value of one row, min is the minimum value of one row, X' is the final result, and mx and mi are respectively designated interval values; default mx is 1 and mi is 0.
3. The method of claim 1, wherein the regional power prediction method based on the number of collected daily power is as follows: and (3) performing relevance analysis in the step (S2), measuring the linear correlation degree between the characteristics by adopting a pearson correlation coefficient method, and selecting the characteristics with large absolute values of the correlation coefficients as the input characteristics of the model.
4. The method of claim 1, wherein the regional power prediction method based on the number of collected daily power is as follows: the prediction model in the step S3 is a DRSN-BilSTM-self-attention model, a DRSN network and a BilSTM network are combined, and an automatic attention mechanism self-attention is introduced into an output end;
the overall structure of the DRSN-BilSTM-self-anchorage model consists of three parts: an input layer, a hidden layer and an output layer; the stacking mode is according to the structure of a model, namely, the output of the model is used as the input of the model from bottom to top; wherein, the hidden layer comprises a pooling layer, a BilSTM layer and a full-connection layer;
firstly, the DRSN adaptively extracts effective characteristics from input data; then, the BilSTM automatically calculates the time sequence dependence relationship between the characteristics and the daily electric quantity through the rich characteristics output by the BiLSTM; then, introducing a self-attention mechanism at the output end of the deep learning network, aiming at distributing attention weight to the output of the BilSTM hidden layer and highlighting the influence of key factors on daily electricity; and finally, outputting the data by the full connection layer, thereby realizing the prediction of the daily electric quantity.
5. The method of claim 4, wherein the regional power prediction method based on the daily power collection number comprises: the prediction model is a daily electric quantity prediction model, the used data is various data related to daily electric quantity prediction, namely data related to time information, and a DRSN network is adopted for deep feature extraction;
the DRSN network is based on a ResNet model, soft thresholding is used as a nonlinear layer to be introduced into a network structure of the ResNet, a local connection and weight sharing mode is adopted, effective features are directly obtained from original data through alternate use of a convolution layer and a pooling layer, local features of the data are automatically extracted, and a complete feature vector is established.
6. The method for predicting the regional power consumption based on the daily power consumption collection number according to claim 4, wherein the method comprises the following steps: the prediction model optimizes the capture of bidirectional semantic dependence through a BilSTM network; the BilSTM network is based on an LSTM model that can capture dependencies over longer distances.
7. The method for predicting the regional power consumption based on the daily power consumption collection number according to claim 4, wherein the method comprises the following steps: the self-attention mechanism is used for reducing dependence on external information, capturing internal relevance of data or features, and screening out a small amount of important information from a large amount of information.
8. The method of claim 4, wherein the regional power prediction method based on the daily power collection number comprises: the evaluation indexes of the self-attention mechanism comprise a root mean square error RMSE and a mean absolute percentage error MAPE;
the root mean square error RMSE represents a sample standard deviation of a difference value between a predicted value and a true value, and the formula is as follows;
wherein y is i Represents the actual value, and f i Is a predicted value;
the average absolute percentage error MAPE expresses the prediction effect by calculating the absolute error percentage, the smaller the value is, the better the formula is
Where At represents the actual value and Ft is the predicted value.
9. The method of claim 1, wherein the regional power prediction method based on the number of collected daily power is as follows: the basic data comprises data related to full-aperture daily electric quantity, data related to resident daily electric quantity, data related to agricultural daily electric quantity and data related to general industrial and commercial daily electric quantity;
the data related to the full-aperture daily electric quantity comprises historical data of the full-aperture daily electric quantity of a plurality of cities;
the data related to the daily electricity consumption of residents comprises daily electricity consumption history, the highest air temperature, the lowest air temperature and legal festivals and holidays of residents in a plurality of cities;
the agricultural daily electricity quantity related data comprise agricultural daily electricity quantity history, highest air temperature, lowest air temperature, solar terms and daily rainfall;
the data related to the general industrial and commercial daily electric quantity comprises general industrial and commercial daily electric quantity history, highest air temperature, lowest air temperature, legal holidays and social consumer goods retail total; wherein the social consumer goods retail totals require the monthly data to be broken down into daily granularity data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210608488.0A CN115392527A (en) | 2022-05-31 | 2022-05-31 | Regional electric quantity prediction method based on daily electric quantity collection number |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210608488.0A CN115392527A (en) | 2022-05-31 | 2022-05-31 | Regional electric quantity prediction method based on daily electric quantity collection number |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115392527A true CN115392527A (en) | 2022-11-25 |
Family
ID=84117427
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210608488.0A Pending CN115392527A (en) | 2022-05-31 | 2022-05-31 | Regional electric quantity prediction method based on daily electric quantity collection number |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115392527A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117853275A (en) * | 2024-03-08 | 2024-04-09 | 广东采日能源科技有限公司 | Method and device for electricity utilization prediction |
-
2022
- 2022-05-31 CN CN202210608488.0A patent/CN115392527A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117853275A (en) * | 2024-03-08 | 2024-04-09 | 广东采日能源科技有限公司 | Method and device for electricity utilization prediction |
| CN117853275B (en) * | 2024-03-08 | 2024-07-09 | 广东采日能源科技有限公司 | Method and device for electricity utilization prediction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | Application of a novel discrete grey model for forecasting natural gas consumption: A case study of Jiangsu Province in China | |
| CN109858740A (en) | Appraisal procedure, device, computer equipment and the storage medium of business risk | |
| Rai et al. | Analysis of classical and machine learning based short-term and mid-term load forecasting for smart grid | |
| CN108280541A (en) | Customer service strategies formulating method, device based on random forest and decision tree | |
| CN108388955A (en) | Customer service strategies formulating method, device based on random forest and logistic regression | |
| Yu et al. | Robust supply chain networks design and ambiguous risk preferences | |
| CN109165763A (en) | A kind of potential complained appraisal procedure and device of 95598 customer service work order | |
| Pinheiro et al. | Short-term electricity load forecasting—A systematic approach from system level to secondary substations | |
| d’Amato | Cyclical capitalization and lag vacancy | |
| Bessec et al. | Forecasting electricity spot prices using time-series models with a double temporal segmentation | |
| CN108154311A (en) | Top-tier customer recognition methods and device based on random forest and decision tree | |
| Le et al. | Using the optimization algorithm to evaluate and predict the business performance of logistics companies–a case study in Vietnam | |
| Wu et al. | Regional energy internet project investment decision making framework through interval type-2 fuzzy number based Choquet integral fuzzy synthetic model | |
| Chen et al. | Formerly assembled, but now designed in China? Assessing the domestic value-added of activities in gross exports | |
| CN115392527A (en) | Regional electric quantity prediction method based on daily electric quantity collection number | |
| Azadeh et al. | Optimization of supply chain based on macro ergonomics criteria: A case study in gas transmission unit | |
| CN115271041A (en) | Method for predicting telephone traffic of power service | |
| Fan et al. | Application of COEMD-S-SVR model in tourism demand forecasting and economic behavior analysis: The case of Sanya City | |
| Gao et al. | What can be learned from billions of invoices? The construction and application of China’s multiregional input-output table based on Big Data from the value-added tax | |
| KR100648296B1 (en) | Energy Demand Forecast Method and System | |
| Dalhuisen et al. | Critical factors for achieving multiple goals with water tariff systems: Combining limited data sources and expert testimony | |
| Karbassi Yazdi et al. | A robust model for supplying LNG from different contracts considering overall and incremental discount options | |
| Tan | Performance evaluation model of cross border e-commerce supply chain based on LMBP feedback neural network | |
| CN114971696A (en) | Quotation method based on electricity consumption and flow information uploading system | |
| CN114862104A (en) | Natural gas distribution method, electronic equipment and computer readable storage medium |
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 |