CN114549095B - Sliding window type electricity selling amount prediction method based on time sequence - Google Patents
Sliding window type electricity selling amount prediction method based on time sequence Download PDFInfo
- Publication number
- CN114549095B CN114549095B CN202210447606.4A CN202210447606A CN114549095B CN 114549095 B CN114549095 B CN 114549095B CN 202210447606 A CN202210447606 A CN 202210447606A CN 114549095 B CN114549095 B CN 114549095B
- Authority
- CN
- China
- Prior art keywords
- window
- sliding
- similarity
- electricity
- sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- 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
Abstract
The invention discloses a sliding window type electricity selling amount prediction method based on a time sequence, which comprises the following steps: inputting a prediction period by a user; acquiring a temperature data set and an electricity sales data set, and preprocessing to obtain a temperature sequence and an electricity sales sequence; determining a reference window, and acquiring air temperature data and electricity sales data of corresponding sequences; setting a sliding window on the preprocessed sequence; calculating the similarity between the sliding window and the reference window, and sliding the sliding window to obtain a similarity set; selecting a sliding window corresponding to the maximum similarity in the similarity set as a prediction window; dividing the prediction window into a front window and a rear window, and obtaining the window change rate according to the data corresponding to the front window and the rear window; and calculating the electricity selling amount of the prediction period according to the window change rate. By the method, the after-window electricity selling quantity can be predicted quickly and accurately, and good implementability is achieved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a sliding window type electricity selling quantity prediction method based on a time sequence.
Background
With the construction of the smart grid, the monthly electricity sales amount reflects the electricity sales capacity and the comprehensive management level of the power enterprises, so that the intelligent power grid is widely concerned by enterprises of all levels. According to the data analysis result related to the monthly electricity sales in different areas over the years, the research object shows a very complex nonlinear characteristic, and proves that the nonlinear characteristic can be driven by different property factors, such as seasonal alternation, emergencies, economic changes and the like.
The current method for predicting the electricity sales amount has the problems that the calculation amount is huge and the prediction result is not accurate enough due to the fact that a large amount of data are predicted through regression analysis and the consideration of some factors influencing the electricity sales amount is not enough; the notice number is CN 106651055A, the name is a short-term electricity sales prediction method and system, and the method and system provide a method for obtaining electricity distribution of low-voltage users and high-voltage users who have issued electricity by an electric power company so as to predict the electricity consumption of the high-voltage users and the low-voltage users in a non-issuing time period, and sum the electricity consumption to obtain a predicted value of monthly electricity sales. However, the method has less data dependence, the predicted result is possibly greatly influenced by factors such as seasons and the like, and the predicted result is not accurate enough. The notice number is CN 105096159A, the name is a regional electricity sales amount prediction method and device, a historical electricity sales amount curve of each region to be predicted is obtained, the characteristics of the historical electricity sales amount curve of each region to be predicted in a time domain and a frequency domain are determined, clustering is carried out, a prediction algorithm is obtained, electricity sales amount prediction is carried out, the prediction range of the method is limited, and other seasonal environment factors are not considered.
Disclosure of Invention
The invention mainly solves the technical problem of providing a sliding window type electricity selling quantity prediction method based on a time sequence, which can solve the problem of electricity selling quantity prediction for T days after the current date.
In order to solve the technical problems, the technical scheme is as follows: the sliding window type electricity selling amount prediction method based on the time sequence comprises the following steps:
s100: inputting a prediction period T by a user;
s200: acquiring a temperature data set and an electricity sales data set, and preprocessing to obtain a temperature sequence and an electricity sales sequence;
s300: determining a reference window, and acquiring air temperature data and electricity sales data of corresponding sequences;
s400: setting sliding windows on the preprocessed air temperature sequence and electricity selling quantity sequence;
s500: calculating the similarity between the sliding window and the reference window, and sliding the sliding window to obtain a similarity set;
s600: selecting a sliding window corresponding to the maximum similarity in the similarity set as a prediction window;
s700: dividing the prediction window into a front window and a rear window, and calculating according to the data of the sequences corresponding to the front window and the rear window to obtain the window change rate;
s800: and calculating the electricity selling amount of the prediction period according to the window change rate.
Further, the S100 includes:
the prediction period T is a time period in which the user needs to predict the electricity sales amount, and is T days after the current date on the time sequence;
further, the S200 includes:
the acquired temperature data set comprises historical temperature data and temperature data in a prediction period;
the air temperature data comprises highest temperature data and lowest temperature data;
the acquired electricity selling quantity data set comprises historical electricity selling quantity data;
the preprocessing is to respectively carry out normalization processing on the air temperature data set and the electricity sales data set;
the air temperature data set and the electricity selling quantity data set are subjected to normalization processing to obtain an air temperature sequence and an electricity selling quantity sequence;
the air temperature sequence comprises a highest temperature sequence and a lowest temperature sequence.
Further, the normalization process is to data setAnd (4) calculating, wherein the formula of normalization processing is as follows:whereinIs composed ofThe minimum value of the sum of the values of,is composed ofThe maximum value of the number of the first and second,as a data setThe length of (a) of (b),for the data to be normalized, the data is,the normalized data is obtained;
and arranging the normalized data according to a time sequence to obtain a corresponding data sequence.
Further, the S300 includes:
the reference window takes the current date as the reference on the time sequence, and T days are added to the front and the back respectively to form a window with the length of 2T +1, wherein the front T day is the front window of the reference window, and the back T day is the back window of the reference window.
Further, the S400 includes:
the setting sliding window is 2T +1 in length, the starting position is 1 day of the same month of the current date appearing for the first time in the time sequence, and the ending position is the day before the current date.
Further, the S500 includes:
s510: calculating the temperature similarity of the sliding window and the reference window;
s520: calculating the similarity of the electricity sales quantity of the front window of the sliding window and the front window of the reference window;
s530: calculating to obtain the comprehensive similarity of the sliding window and the reference window;
s540: if the sliding window does not reach the end position, the sliding window slides backwards by one step length on the time sequence, and the step returns to the step S510; if the sliding window reaches the termination position, arranging the comprehensive similarity according to the time sequence of the sliding window to obtain a comprehensive similarity set;
the front window of the sliding window is T days before the sliding window;
s540, the sliding step length isWhere d is a positive integer no greater than T and set by the user, the value of d is proportional to the prediction accuracy and inversely proportional to the prediction speed.
Further, the S510 includes:
s511: calculating the highest temperature similarity of the sliding window and the reference window;
s512: calculating the lowest temperature similarity of the sliding window and the reference window;
s513: calculating to obtain the temperature similarity between the sliding window and the reference window;
the highest temperature similarity and the lowest temperature similarity are obtained by calculating Euclidean distances;
the temperature similarity is the product of the highest temperature similarity and the lowest temperature similarity.
Further, the S520 includes:
and the similarity of the electricity sales is obtained by calculating the Euclidean distance.
Further, the S530 includes:
and the comprehensive similarity is obtained by multiplying the temperature similarity and the electricity selling quantity similarity.
Further, the S700 includes:
s710: dividing the prediction window into a front window and a rear window;
s720: calculating the change rate between the total electricity sold in the front window and the total electricity sold in the rear window;
the front window and the rear window are respectively a temperature sequence and an electricity sales sequence corresponding to the front T day and the rear T day of the prediction window on the time sequence;
the calculation formula of the change rate is as follows:whereinIn order to be able to change the rate of change,the total amount of electricity sold for the front window,and selling the total amount of electricity for the rear window.
Further, the S800 includes:
electricity sales of the prediction periodWhereinThe total amount of power sold in the front window of the prediction window.
The invention has the beneficial effects that: the window temperature similarity is calculated by multiplying the window highest temperature similarity and the window lowest temperature similarity, and the window temperature similarity is multiplied by the window electricity selling quantity similarity to obtain the comprehensive similarity, so that the electricity selling quantity of the rear window is accurately predicted. The change of the electricity sold by residents has certain relevance and periodicity with the air temperature, so when the historical time sequence is long enough and the accuracy of short-term weather forecast data is high, the method can effectively predict the electricity sold. The comprehensive similarity calculation among the windows is based on the daily highest temperature, the daily lowest temperature and the daily electricity selling quantity data, external realistic factors such as climate, holidays and the like can be fully considered through the fine-grained data, and the response to the change of the electricity selling quantity of residents is sensitive, so that the prediction precision can be effectively improved. The principle is simple and easy to understand, and the method has good implementability and accuracy.
Drawings
Fig. 1 is a flowchart of a sliding window type electricity sales amount prediction method based on time series;
FIG. 2 is a schematic diagram of a reference window and its division of a sliding window type electricity sales amount prediction method based on time series;
fig. 3 is a schematic diagram of sliding window sliding of a sliding window type electricity sales amount prediction method based on time series;
FIG. 4 is a schematic diagram of similarity calculation between a sliding window and a reference window of a sliding window type electricity sales amount prediction method based on time series;
fig. 5 is a schematic diagram of a prediction window division of a sliding window type electricity sales amount prediction method based on a time sequence.
Detailed Description
The preferred embodiments are described in detail below with reference to the attached drawings so that advantages and features can be more readily understood by those skilled in the art and the scope of protection is more clearly and clearly defined.
Referring to fig. 1, fig. 2, fig. 3, fig. 4 and fig. 5, an embodiment includes:
a sliding window type electricity selling amount prediction method based on time series comprises the following steps:
s100: inputting a prediction period T by a user;
s200: acquiring a temperature data set and an electricity sales data set, and preprocessing to obtain a temperature sequence and an electricity sales sequence;
s300: determining a reference window, and acquiring air temperature data and electricity sales data of corresponding sequences;
s400: setting sliding windows on the preprocessed air temperature sequence and electricity selling quantity sequence;
s500: calculating the similarity between the sliding window and the reference window, and sliding the sliding window to obtain a similarity set;
s600: selecting a sliding window corresponding to the maximum similarity in the similarity set as a prediction window;
s700: dividing the prediction window into a front window and a rear window, and calculating according to the data of the sequences corresponding to the front window and the rear window to obtain the window change rate;
s800: and calculating the electricity selling amount of the prediction period according to the window change rate.
Further, the S100 includes:
the prediction period T is a time period in which the user needs to predict the electricity sales amount, and is T days after the current date on the time sequence;
and acquiring air temperature data of the prediction period sequence according to the prediction period T, wherein the data source is weather forecast.
Further, the S200 includes:
the acquired temperature data set comprises historical temperature data and temperature data in a prediction period;
the air temperature data comprises highest temperature data and lowest temperature data;
the acquired electricity selling quantity data set comprises historical electricity selling quantity data;
the preprocessing is to respectively carry out normalization processing on the air temperature data set and the electricity sales data set;
the air temperature data set and the electricity selling quantity data set are subjected to normalization processing to obtain an air temperature sequence and an electricity selling quantity sequence;
the air temperature sequence comprises a highest temperature sequence and a lowest temperature sequence.
Further, the normalization process is a data setAnd (4) calculating, wherein the formula of normalization processing is as follows:whereinIs composed ofThe minimum value of the sum of the values of,is composed ofThe maximum value of the number of the first and second,as a data setThe length of (a) of (b),for the data to be normalized, the data is,the normalized data is obtained;
and arranging the normalized data according to a time sequence to obtain a corresponding data sequence.
Further, the S300 includes:
the reference window takes the current date as a reference on the time sequence, and increases T days to the front and the back respectively to form a window with the length of 2T +1, wherein the front T day is a front window of the reference window, and the back T day is a back window of the reference window;
as shown in fig. 2, the reference window uses the current date as a reference, the previous T days as a front window of the reference window, and the next T days as a back window of the reference window, the reference window includes a highest temperature sequence, a lowest temperature sequence and an electricity selling quantity sequence, the length of the window is 2T +1, T days are added to the front and back of the reference window, respectively, with the current date as a reference, wherein the lengths of the highest temperature sequence and the lowest temperature sequence are both 2T +1, and the data is derived from weather forecast; the length of the electricity selling sequence is 2T +1, but the data length is T, only data exists in the front window, and the current date and the rear window are empty.
Further, the S400 includes:
the length of the sliding window is 2T +1, the starting position is 1 day of the same month of the current date appearing for the first time in the time sequence, and the ending position is the day before the current date;
as shown in fig. 3, the length of the sliding window is 2T +1, the starting position is the same month 1 day of the earliest year and the current date in the time sequence, the sliding window slides from left to right until the ending position, and the ending position is the day before the current date.
Further, the S500 includes:
s510: calculating the temperature similarity of the sliding window and the reference window;
s520: calculating the similarity of the electricity sales quantity of the front window of the sliding window and the front window of the reference window;
s530: calculating to obtain the comprehensive similarity of the sliding window and the reference window;
s540: if the sliding window does not reach the end position, the sliding window slides backwards by one step length on the time sequence, and the step returns to the step S510; if the sliding window reaches the termination position, arranging the comprehensive similarity according to the time sequence of the sliding window to obtain a comprehensive similarity set;
the front window of the sliding window is T days before the sliding window;
s540, the sliding step length isWhere d is a positive integer no greater than T and set by the user, the value of d is proportional to the accuracy of the prediction and inversely proportional to the speed of the prediction.
Further, the S510 includes:
s511: calculating the highest temperature similarity of the sliding window and the reference window;
s512: calculating the lowest temperature similarity of the sliding window and the reference window;
s513: calculating to obtain the temperature similarity between the sliding window and the reference window;
the highest temperature similarity and the lowest temperature similarity are obtained by calculating Euclidean distances;
as shown in FIG. 4, the sliding window starts fromDuring the process of sliding the position to the termination position, the step length of each sliding isD is a positive integer not greater than T and is set by a user, the value of d is in direct proportion to the prediction accuracy and in inverse proportion to the prediction speed, the highest temperature similarity and the lowest temperature similarity of the sliding window and the reference window are calculated once every sliding, and then the temperature similarity is obtained;
the temperature similarity is the product of the highest temperature similarity and the lowest temperature similarity.
Further, the S520 includes:
the similarity of the electricity sales is obtained by calculating the Euclidean distance;
as shown in FIG. 4, in the process of sliding the sliding window from the starting position to the ending position, each sliding step is as followsWhere d is a positive integer no greater than T and set by the user, the value of d being directly proportional to the accuracy of the prediction and inversely proportional to the speed of the prediction; and calculating the similarity of the electricity sales of the front windows of the sliding window and the reference window once every sliding.
Further, the S530 includes:
and the comprehensive similarity is obtained by multiplying the temperature similarity and the electricity selling quantity similarity.
Further, the S700 includes:
s710: dividing the prediction window into a front window and a rear window;
s720: calculating the change rate between the total electricity sold in the front window and the total electricity sold in the rear window;
the front window and the rear window are respectively a temperature sequence electric quantity sequence of the prediction window on the time sequence at the front T day and the rear T day;
as shown in fig. 5, the prediction window is divided into two parts, namely a front window and a rear window, by a time sequence, namely a front T day and a rear T day, and correspondingly, the air temperature and electricity sales sequence is divided into two parts, namely the front window and the rear window;
the calculation formula of the change rate is as follows:whereinIn order to be able to change the rate of change,the total amount of electricity sold for the front window,and selling the total amount of electricity for the rear window.
Further, the S800 includes:
electricity sales of the prediction periodWhereinThe total amount of power sold in the front window of the forecast window.
The above description is only an example and is not intended to limit the scope of the claims, which are included in the following description and accompanying drawings, and all changes and modifications that come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Claims (10)
1. A sliding window type electricity selling amount prediction method based on time series is characterized by comprising the following steps:
s100: inputting a prediction period T by a user;
s200: acquiring a temperature data set and an electricity sales data set, and preprocessing to obtain a temperature sequence and an electricity sales sequence;
s300: determining a reference window, and acquiring air temperature data and electricity sales data of corresponding sequences;
s400: setting sliding windows on the preprocessed air temperature sequence and electricity selling quantity sequence;
s500: calculating the similarity between the sliding window and the reference window, and sliding the sliding window to obtain a similarity set;
s600: selecting a sliding window corresponding to the maximum similarity in the similarity set as a prediction window;
s700: dividing the prediction window into a front window and a rear window, and calculating according to the data of the sequences corresponding to the front window and the rear window to obtain the window change rate;
s800: calculating the electricity selling of the prediction period according to the window change rate;
the S500 includes:
s510: calculating the temperature similarity of the sliding window and the reference window;
s520: calculating the similarity of the electricity sales of the front window of the sliding window and the front window of the reference window;
s530: calculating to obtain the comprehensive similarity of the sliding window and the reference window;
s540: if the sliding window does not reach the end position, the sliding window slides backwards by one step length on the time sequence, and the step returns to the step S510; if the sliding window reaches the termination position, arranging the comprehensive similarity according to the time sequence of the sliding window to obtain a comprehensive similarity set;
in the step S520, the window in front of the sliding window is T days before the sliding window;
the S540, the sliding step size is ⌈ T/d ⌉, wherein d is a positive integer not greater than T and is set by a user, and the value of d is proportional to the prediction accuracy and inversely proportional to the prediction speed;
the S510 includes:
s511: calculating the highest temperature similarity of the sliding window and the reference window;
s512: calculating the lowest temperature similarity of the sliding window and the reference window;
s513: calculating to obtain the temperature similarity between the sliding window and the reference window;
the highest temperature similarity and the lowest temperature similarity are obtained by calculating Euclidean distances;
the temperature similarity is the product of the highest temperature similarity and the lowest temperature similarity.
2. The time-series-based sliding-window electricity sales amount prediction method according to claim 1, wherein the S100 comprises:
the prediction period T is a time period in which the user needs to predict the electricity sales amount, and is T days after the current date on the time sequence;
and acquiring temperature data in the prediction period according to the prediction period T, wherein the data source is weather forecast.
3. The method for predicting the time-series-based sliding-window-type electricity sales amount according to claim 1, wherein the S200 comprises:
the temperature data set comprises historical temperature data and temperature data in a prediction period;
the air temperature data comprises highest temperature data and lowest temperature data;
the electricity selling quantity data set comprises historical electricity selling quantity data;
the preprocessing is to respectively carry out normalization processing on the air temperature data set and the electricity sales data set;
the air temperature data set and the electricity selling quantity data set are subjected to normalization processing to obtain an air temperature sequence and an electricity selling quantity sequence;
the air temperature sequence comprises a highest temperature sequence and a lowest temperature sequence.
4. The time-series-based sliding-window electricity sales amount prediction method according to claim 3, wherein the normalization process is performed on the data setCalculating, wherein the normalization processing formula is as follows:whereinIs composed ofThe minimum value of the sum of the values of,is composed ofThe maximum value of the number of the first and second,as a data setThe length of (a) of (b),for the data to be normalized, the data is,the normalized data is obtained;
and arranging the normalized data according to a time sequence to obtain a corresponding data sequence.
5. The method for predicting the time-series-based sliding-window-type electricity sales amount according to claim 1, wherein the S300 comprises:
the reference window takes the current date as the reference on the time sequence, and T days are added to the front and the back respectively to form a window with the length of 2T +1, wherein the front T day is the front window of the reference window, and the back T day is the back window of the reference window.
6. The method for predicting the time-series-based sliding-window-type electricity sales amount according to claim 1, wherein the S400 comprises:
the length of the sliding window is 2T +1, the starting position is 1 day of the same month of the current date appearing for the first time in the time sequence, and the ending position is the day before the current date.
7. The method for predicting time-series-based sliding-window-type electricity sales amount according to claim 1, wherein said S520 comprises:
and the similarity of the electricity sales is obtained by calculating the Euclidean distance.
8. The time-series-based sliding-window electricity sales amount prediction method according to claim 1, wherein said S530 comprises:
and the comprehensive similarity is obtained by multiplying the temperature similarity and the electricity selling quantity similarity.
9. The time-series-based sliding-window electricity sales amount prediction method according to claim 1, wherein said S700 comprises:
s710: dividing the prediction window into a front window and a rear window;
s720: calculating the change rate between the total electricity sold in the front window and the total electricity sold in the rear window;
the front window and the rear window are respectively a temperature sequence and an electric quantity selling sequence corresponding to the front T day and the rear T day of the time sequence of the prediction window;
10. The method for predicting the time-series-based sliding-window-type electricity sales amount according to claim 1, wherein the S800 comprises:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210447606.4A CN114549095B (en) | 2022-04-25 | 2022-04-25 | Sliding window type electricity selling amount prediction method based on time sequence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210447606.4A CN114549095B (en) | 2022-04-25 | 2022-04-25 | Sliding window type electricity selling amount prediction method based on time sequence |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114549095A CN114549095A (en) | 2022-05-27 |
CN114549095B true CN114549095B (en) | 2022-08-09 |
Family
ID=81667138
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210447606.4A Active CN114549095B (en) | 2022-04-25 | 2022-04-25 | Sliding window type electricity selling amount prediction method based on time sequence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114549095B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116186560B (en) * | 2023-04-26 | 2023-07-07 | 江西师范大学 | Temperature similarity characterization method based on effective thermodynamic temperature value |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103473613A (en) * | 2013-09-09 | 2013-12-25 | 武汉理工大学 | Landscape structure-surface temperature-electricity consumption coupling model and application thereof |
CN106779147A (en) * | 2016-11-18 | 2017-05-31 | 重庆邮电大学 | A kind of electro-load forecast method based on self adaptation level Time Series Clustering |
CN108564204A (en) * | 2018-03-23 | 2018-09-21 | 西安理工大学 | Least square method supporting vector machine power predicating method based on maximal correlation entropy criterion |
CN109685290A (en) * | 2019-02-11 | 2019-04-26 | 南方电网科学研究院有限责任公司 | A kind of electricity demand forecasting method, device and equipment based on deep learning |
CN111612651A (en) * | 2020-05-27 | 2020-09-01 | 福州大学 | Abnormal electric quantity data detection method based on long-term and short-term memory network |
CN112288187A (en) * | 2020-11-18 | 2021-01-29 | 国网湖南省电力有限公司 | Big data-based electricity sales amount prediction method |
CN112907064A (en) * | 2021-02-08 | 2021-06-04 | 国网安徽省电力有限公司蚌埠供电公司 | Electric quantity prediction method and device based on self-adaptive window, storage medium and terminal |
CN113505935A (en) * | 2021-07-26 | 2021-10-15 | 上海东方低碳科技产业股份有限公司 | Electric power abnormal fluctuation detection and prediction calculation method based on integrated algorithm |
CN113887858A (en) * | 2021-08-11 | 2022-01-04 | 浙江工业大学 | Charging station micro-grid system optimal scheduling method based on CNN-LSTM load prediction |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108510006B (en) * | 2018-04-08 | 2020-06-09 | 重庆邮电大学 | Enterprise power consumption analysis and prediction method based on data mining |
AU2021229123A1 (en) * | 2020-10-01 | 2022-04-21 | Space Pte. Ltd. | Ai-based software service to shave electricity consumption peak |
-
2022
- 2022-04-25 CN CN202210447606.4A patent/CN114549095B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103473613A (en) * | 2013-09-09 | 2013-12-25 | 武汉理工大学 | Landscape structure-surface temperature-electricity consumption coupling model and application thereof |
CN106779147A (en) * | 2016-11-18 | 2017-05-31 | 重庆邮电大学 | A kind of electro-load forecast method based on self adaptation level Time Series Clustering |
CN108564204A (en) * | 2018-03-23 | 2018-09-21 | 西安理工大学 | Least square method supporting vector machine power predicating method based on maximal correlation entropy criterion |
CN109685290A (en) * | 2019-02-11 | 2019-04-26 | 南方电网科学研究院有限责任公司 | A kind of electricity demand forecasting method, device and equipment based on deep learning |
CN111612651A (en) * | 2020-05-27 | 2020-09-01 | 福州大学 | Abnormal electric quantity data detection method based on long-term and short-term memory network |
CN112288187A (en) * | 2020-11-18 | 2021-01-29 | 国网湖南省电力有限公司 | Big data-based electricity sales amount prediction method |
CN112907064A (en) * | 2021-02-08 | 2021-06-04 | 国网安徽省电力有限公司蚌埠供电公司 | Electric quantity prediction method and device based on self-adaptive window, storage medium and terminal |
CN113505935A (en) * | 2021-07-26 | 2021-10-15 | 上海东方低碳科技产业股份有限公司 | Electric power abnormal fluctuation detection and prediction calculation method based on integrated algorithm |
CN113887858A (en) * | 2021-08-11 | 2022-01-04 | 浙江工业大学 | Charging station micro-grid system optimal scheduling method based on CNN-LSTM load prediction |
Non-Patent Citations (3)
Title |
---|
《Sliding Time Window Electricity Consumption Optimization Algorithm for Communities in the Context of Big Data Processing》;Simona Vasilica Oprea;《IEEE Access》;20190113;全文 * |
《武汉市电网用电量、电力负荷与气温的关系及预测模型研究》;洪国平 等;《华中电力》;20060430;全文 * |
基于移动人流数据的商业楼宇负荷用电预测;苏运等;《计算机应用与软件》;20190512(第05期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN114549095A (en) | 2022-05-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Chaouch | Clustering-based improvement of nonparametric functional time series forecasting: Application to intra-day household-level load curves | |
CN110033134A (en) | A kind of short-term load forecasting algorithm of segmentation day by day considering meteorologic factor | |
Gerbec et al. | An approach to customers daily load profile determination | |
CN102426674A (en) | Power system load prediction method based on Markov chain | |
CN105701570A (en) | Short-term electric power demand analysis method based on overall process technology improvement | |
Guo et al. | Maximum power demand prediction using fbprophet with adaptive Kalman filtering | |
CN114549095B (en) | Sliding window type electricity selling amount prediction method based on time sequence | |
CN112330077B (en) | Power load prediction method, power load prediction device, computer equipment and storage medium | |
CN102509173A (en) | Markov chain based method for accurately forecasting power system loads | |
CN107423836A (en) | Short-term load forecasting method based on sendible temperature | |
KR20210013565A (en) | Weather data-based wireless sensor network node solar energy collection power prediction algorithm | |
CN105308853A (en) | Prediction system, prediction device, and prediction method | |
CN112598155A (en) | Load increase and decrease estimation method and system for transformer substation | |
CN116050866A (en) | Combined user missing electric quantity fitting method and system based on typical load curve | |
CN111428745A (en) | Clustering analysis-based low-voltage user electricity utilization feature extraction method | |
KR20160074325A (en) | Electricity Demand Index (EDI) Forecasting System with respect to Weather Condition Change | |
CN113689057A (en) | Photovoltaic power generation power prediction method and device | |
JP2000270473A (en) | Power demand estimating method | |
Filipova-Petrakieva et al. | Short-Term Forecasting of Hourly Electricity Power Demand: Reggresion and Cluster Methods for Short-Term Prognosis | |
KR102011314B1 (en) | Method And System For Peak Power Demand Expectation On Household | |
CN113806899B (en) | Power distribution network topological relation identification method and device and mobile terminal | |
CN113222245A (en) | Method and system for checking monthly electric quantity and electricity charge abnormity of residential user and storage medium | |
CN109274124B (en) | Wind power local consumption capability prediction method based on scene Markov method | |
CN114048200A (en) | User electricity consumption behavior analysis method considering missing data completion | |
Deakin et al. | Calculations of system adequacy considering heat transition pathways |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |