CN112465215A - Distributed energy user side cold and heat power short-term load prediction method and system - Google Patents
Distributed energy user side cold and heat power short-term load prediction method and system Download PDFInfo
- Publication number
- CN112465215A CN112465215A CN202011334619.8A CN202011334619A CN112465215A CN 112465215 A CN112465215 A CN 112465215A CN 202011334619 A CN202011334619 A CN 202011334619A CN 112465215 A CN112465215 A CN 112465215A
- Authority
- CN
- China
- Prior art keywords
- day
- load
- similarity
- days
- characteristic
- 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 31
- 238000010438 heat treatment Methods 0.000 claims abstract description 25
- 238000001816 cooling Methods 0.000 claims abstract description 24
- 239000013598 vector Substances 0.000 claims description 66
- 238000011156 evaluation Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 6
- 238000010219 correlation analysis Methods 0.000 claims description 6
- 238000000556 factor analysis Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000005484 gravity Effects 0.000 claims description 5
- 238000004445 quantitative analysis Methods 0.000 claims description 4
- 150000001875 compounds Chemical class 0.000 claims description 3
- 238000007726 management method Methods 0.000 claims description 3
- 238000001556 precipitation Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000013277 forecasting method Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010977 unit operation Methods 0.000 description 2
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 1
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for forecasting short-term loads of cooling, heating and power at a distributed energy user side.
Description
Technical Field
The invention belongs to the technical field of energy system user side load prediction, and particularly relates to a method and a system for predicting short-term load of cooling, heating and power suitable for a distributed energy user side.
Background
With the rapid promotion of urbanization in China and the gradual formation of urban mass spatial patterns, the idea of building a resource-saving and environment-friendly society is deeply focused. Distributed energy is widely favored in large and medium-sized cities in China due to various energy supply forms, a clean and efficient energy conversion process and distributed system modular arrangement. In consideration of the randomness of the load demands of the user side, in order to effectively utilize renewable energy sources such as wind power and solar energy in distributed energy sources, a reasonable energy supply plan needs to be made in advance, and accurate prediction of the short-term loads of the cold and the heat power of the user side of the distributed energy sources is just an important guarantee for making the reasonable energy supply plan, arranging the unit operation strategy and ensuring the balance of energy supply and demand by an energy scheduling mechanism.
The conventional user-side short-term load prediction technology is mainly based on the traditional mathematical statistics methods such as time series, regression analysis and similar days, or based on the modern intelligent methods such as a support vector machine, grey theory analysis, an artificial neural network and an expert system to respectively predict the cooling, heating and power loads. The prediction method is based on a large amount of historical load data, a large amount of parameters need to be identified in the prediction process or a complex intelligent algorithm is adopted to train a prediction model, the operation speed is low, the load is difficult to predict quickly in engineering application, and an operator can adjust a scheduling plan in time.
Disclosure of Invention
Aiming at the defect that the prior art for forecasting the short-term cooling and heating power load of a distributed energy user side has low operation speed, the user side short-term cooling and heating power load forecasting method and the system which can effectively improve the operation speed while ensuring the load forecasting precision are provided.
The invention is realized by adopting the following technical scheme:
a method for forecasting short-term load of cooling, heating and power at a distributed energy user side comprises the following steps:
and 4, calculating the information entropy of each load similarity day, determining the weight of each load similarity day, and calculating the hourly load of the prediction day by combining the hourly loads of the similarity days.
Preferably, in step 1, quantitative analysis can be performed on the influence factors, and the correlation coefficient between each influence factor and the load is calculated, wherein the calculation formula is as follows:
in the formula, rxyThe correlation coefficient is the load x and the influencing factor y; x is the number ofi、yjThe ith and jth data points of the load x and the influencing factor y respectively;
respectively the average values of the load x and the influencing factor y; z is the number of data points.
Preferably, the influencing factors comprise meteorological factors and non-meteorological factors;
the meteorological factors include: temperature, humidity, wind speed, precipitation, etc.; non-meteorological factors include: economics, policies, day types, demand side management, etc.
Preferably, in step 2, the day feature vectors of each historical day are divided intoRespectively calculating the difference corresponding to the day characteristic vector of the predicted day to obtain the absolute value vector delta of the characteristic erroriThe method comprises the following steps:
δi＝(|Xi(1)-X0(1)|,…,|Xi(n)-X0(n)|)(i＝1,…,m)
in the formula, X0To predict the day's day feature vector, X0＝(X0(1),…,X0(n)), n is the number of features, XiThe day feature vector of the ith historical day is Xi＝(Xi(1),…,Xi(n))。
Preferably, the method for determining the feature weight in step 3 is as follows:
forming a characteristic evaluation matrix according to the day characteristic vector of the predicted day and the day characteristic vector of the historical day, and obtaining a characteristic evaluation standard matrix R ═ R through standardizationij]m×nThen, the specific gravity P of the ith historical day under the jth characteristic is determinedij：
According to specific gravity PijDetermining the information entropy H of the jth featurej：
Suppose PijWhen equal to 0, Pij ln Pij＝0。
To determine the weight w of each featurej：
In the formula (I), the compound is shown in the specification,
is the average of all information entropies other than 1.
Preferably, in step 3, each feature weight is multiplied by the absolute value vector of the feature error and summed to obtain a similarity error ξ between the daily feature vector of each historical day and the daily feature vector of the predicted dayi：
ξi＝w1|Xi(1)-X0(1)|+…+wn|Xi(n)-X0(n)|(i＝1,…,m)
Selecting k days with the minimum similarity error from the historical days as k load similar days of the prediction day, wherein the hourly loads of the similar days are respectively L1，…，Lk。
Preferably, in step 4, the weight of each load similarity day is determined according to the day eigenvector similarity error of the load similarity day, the weight of the load similarity day with smaller similarity error is larger, the weight of the load similarity day is respectively weighted with the hourly load of the similar day to obtain the weighted sum, that is, the hourly load L of the predicted day can be obtained0The formula is as follows:
L0＝W1×L1+…+Wk×Lk
in the formula, L1，…，LkFor hourly loads of similar days of each load, W1，…，WkA daily weight is predicted for each load.
A system of a short-term load forecasting method of cooling, heating and power at a distributed energy user side comprises a load influence factor analysis module, a daily feature vector construction module, a load similarity daily selection module and a short-term load forecasting module.
The load influence factor analysis module is used for carrying out correlation analysis on the cold, heat and power load characteristic influence factors and determining correlation coefficients between the influence factors and the load;
the daily feature vector construction module is used for selecting a plurality of influence factors with stronger correlation coefficients, constructing daily feature vectors of forecast days such as historical days, and determining feature error absolute value vectors;
the load similarity day selection module is used for determining each characteristic weight, analyzing similarity errors of day characteristic vectors of the historical day and the prediction day and selecting a load similarity day;
and the short-term load prediction module is used for determining the weight of each load similar day and obtaining the hourly load of the predicted day by combining the hourly load of the similar day.
A terminal system comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor executes the computer program to realize the steps of the method for predicting the short-term load of cooling, heating and power at the distributed energy user side.
Compared with the prior art, the invention has the following beneficial technical effects:
the invention provides a distributed energy user side cold and heat power short-term load forecasting method, which comprises the steps of carrying out correlation analysis on cold and heat power load characteristic influence factors, constructing daily feature vectors and determining feature error absolute value vectors; calculating the entropy weight of each feature, determining the weight of each feature, and selecting a plurality of load similarity days by using the similarity errors of the historical days and the prediction days; and then, determining the weight of each load similar day again according to the similar error, and then adding the hourly loads of the similar days according to the weights to obtain the hourly loads of the predicted days. The method fully excavates the information contained in the evaluation index information entropy in the traditional weight algorithm, obtains more proper weight, selects the load similarity day with high similarity, and has high prediction result precision, high operation speed and strong adaptability.
Drawings
Fig. 1 is a flowchart of a method for predicting short-term cooling, heating and power loads at a distributed energy user side according to the present invention.
Fig. 2 is a block diagram of a distributed energy user-side cooling, heating and power short-term load prediction system according to the present invention.
Fig. 3 is a hourly cooling, heating and power load curve of a certain distributed energy user side in the beijing area all the year around.
FIG. 4 is a predicted daily short-term thermal load curve of a user side of a certain distributed energy resource in Beijing area obtained by the invention.
Detailed Description
The present invention will now be described in further detail with reference to the attached drawings, which are illustrative, but not limiting, of the present invention.
As shown in fig. 1, a method for predicting short-term cooling, heating and power loads at a distributed energy user side includes the following steps:
The load characteristic influence factors of the user side can be divided into meteorological factors and non-meteorological factors, and the meteorological factors comprise: temperature, humidity, wind speed, precipitation, etc.; non-meteorological factors include: economics, policies, day types, demand side management, etc.
Quantitative analysis can be carried out on the parameter influence factors, and the correlation coefficient between each influence factor and the load is calculated, wherein the calculation formula of the correlation coefficient is as follows:
in the formula, rxyThe correlation coefficient is the load x and the influencing factor y; x is the number ofi、yjThe ith and jth data points of the load x and the influencing factor y respectively;
respectively the average values of the load x and the influencing factor y; n is the number of data points. The value range of the correlation coefficient r is-1 is more than or equal to r and less than or equal to 1, the magnitude of the numerical value represents the strength of the correlation, the sign is positive to represent positive correlation, and the sign is negative to represent negative correlation.
And 2, selecting a plurality of influence factors with strong correlation with the user side cooling, heating and power loads as features according to the analysis result of the user side load characteristic influence factors, constructing a daily feature vector of a historical day and a daily feature vector of a predicted day, and solving an absolute value vector of a feature error.
The constructed day feature vectors of the predicted day and the m historical days are respectively X0、Xi(i-1, …, m) where the day feature vector for the predicted day is X0＝(X0(1),…,X0(n)), n is the number of featuresThe day feature vector of the ith historical day is Xi＝(Xi(1),…,Xi(n)). Calculating the difference value between the daily feature vector of the predicted day and the daily feature vector of each historical day, wherein the absolute value of the difference value is the feature error absolute value vector deltaiThe calculation formula is as follows:
δi＝(|Xi(1)-X0(1)|,…,|Xi(n)-X0(n)|)(i＝1,…,m)
and 3, determining the weight of each feature, analyzing the similarity error of the daily feature vector of the historical day and the daily feature vector of the forecast day, and selecting a load similarity day.
According to the day feature vectors of the predicted day and the historical day, a feature evaluation matrix is constructed, and a feature evaluation standard matrix R is obtained through standardizationij]m×nThen, the specific gravity P of the ith historical day under the jth characteristic is calculatedij：
Calculating the information entropy H of the jth featurej：
Suppose PijWhen equal to 0, Pij ln Pij＝0。
Calculating the weight w of the jth featurej：
In the formula (I), the compound is shown in the specification,
is the average of all information entropies other than 1.
Multiplying each characteristic weight by the absolute value vector of the characteristic error, summing, and calculating the similar error xi of each history day and each prediction dayi：
ξi＝w1|Xi(1)-X0(1)|+…+wn|Xi(n)-X0(n)|(i＝1,…,m)
Selecting k days with the minimum similarity error as k load similarity days of the prediction day, wherein the hourly loads of the similarity days are respectively L1，…，Lk。
And 4, calculating the weight of each load similar day, multiplying the weight by the hourly load of the similar day respectively, calculating the weighted sum to obtain the hourly load of the forecast day, and adjusting the scheduling plan according to the hourly load of the forecast day.
The loads of the similar day and the predicted day have great similarity, the similarity error represents the difference degree between the similar day and the predicted day, and the smaller the similarity error is, the more similar the loads of the similar day and the predicted day are, the more weight is given to the prediction. According to the similarity error, the similar daily weight W of each load can be determined by using the similar method described in step 31，…，WkAnd the hourly load L of the days similar to the load respectively1，…，LkMultiplying to obtain weighted sum to obtain time-by-time load L of predicted day0：
L0＝W1×L1+…+Wk×Lk
The invention also provides a system for predicting short-term load of cooling, heating and power at a distributed energy user side, as shown in fig. 1, comprising: the system comprises a load influence factor analysis module 1, a daily feature vector construction module 2, a load similarity day selection module 3 and a short-term load prediction module 4.
The load influence factor analysis module is used for carrying out correlation analysis on the cold, heat and power load characteristic influence factors and determining correlation coefficients between the influence factors and the load;
the daily feature vector construction module is used for constructing a daily feature vector of a forecast date such as a historical date according to a plurality of influence factors with stronger correlation coefficients and determining a feature error absolute value vector;
the load similarity day selection module is used for determining the weight of each day characteristic vector, analyzing the similarity error of the day characteristic vectors of the historical day and the predicted day and selecting a load similarity day;
and the short-term load prediction module is used for determining the weight of each load similar day and obtaining the hourly load of the predicted day by combining the hourly load of the similar day.
Example 1
In this embodiment, a distributed energy user side in the beijing area is taken as a research object to explain a specific embodiment of the present invention, and fig. 3 is a hourly cooling, heating, and power load curve of the energy user side all the year around.
TABLE 1 correlation coefficient of maximum and minimum daily cold and heat load, maximum and minimum daily temperature, and maximum daily moisture content
According to the correlation coefficient, the maximum and minimum cold loads of the user side have strong correlation with the daily minimum temperature and the daily maximum moisture content, and the maximum and minimum heat loads have strong correlation with the daily maximum temperature and the daily minimum temperature.
TABLE 2 thermal load forecast daily eigenvectors
TABLE 3 Heat load prediction eigen-error absolute value vector
And 3, constructing a feature evaluation matrix according to the daily feature vector, and calculating to obtain each feature information entropy and entropy weight after standardization, wherein the entropy and entropy weight are shown in a table 4. Multiplying each feature entropy weight by the feature error absolute value vector, summing, and calculating the similar error of each history day and each prediction day, as shown in table 5. Selecting 3 days with the minimum similarity error as 3 load similarity days of the prediction days 2, 21 and 21: 20 days in 2 months, 12 days in 12 months and 3 days in 1 month.
TABLE 4 entropy and entropy weight of each feature information
TABLE 5 similar error between historical and predicted days
And 4, according to the similarity error, calculating and determining the weight of each load similarity day by using a similar method in the step 3, multiplying the weight by the hourly load of the load similarity days 2 and 20, 12 and 1 and 3 respectively to obtain a weighted sum as shown in the table 6, so that the hourly load of the predicted day 2 and 21 is obtained as shown in the figure 4, the predicted value of the load is very close to the actual value, the curve trend is approximately the same, the average absolute percentage error MAPE is 3.89% through calculation, and the requirement of the short-term load prediction precision is met.
Table 6 entropy and entropy weight of similar day information of each load
The specific examples above show that: according to the method for predicting the short-term load of the cooling, heating and power at the user side of the distributed energy resources, the prediction precision of the short-term load can be guaranteed, and meanwhile, the operation speed is effectively increased, so that the short-term load at the user side can be rapidly predicted, the fact that the scheduling plan is adjusted by the operating personnel of the energy scheduling mechanism in time is guaranteed, the unit operation strategy is formulated, and the energy supply and demand balance is met.
In an exemplary embodiment, there is also provided a terminal system, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method for predicting short-term cooling, heating and power loads on a distributed energy resource user side when executing the computer program. The processor may be a Central Processing Unit (CPU), other general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc.
The above-mentioned contents are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modification made on the basis of the technical idea of the present invention falls within the protection scope of the claims of the present invention.
Claims (9)
1. A method for predicting short-term load of cooling, heating and power at a distributed energy user side is characterized by comprising the following steps:
step 1, dividing load characteristic influence factors of a user side, respectively carrying out correlation analysis on the cold and heat load characteristic influence factors, and determining correlation coefficients between the influence factors and loads;
step 2, selecting a plurality of influence factors with strong correlation with the cooling, heating and power loads at the user side as features according to correlation coefficients between the influence factors and the loads, constructing a daily feature vector of a historical day and a daily feature vector of a predicted day, and determining a feature error absolute value vector of the historical day and the predicted day;
step 3, calculating each characteristic information entropy, determining each characteristic weight, determining similar errors of the daily characteristic vectors of the historical days and the daily characteristic vectors of the forecast days by combining the characteristic error absolute value vectors, and selecting a plurality of load similar days of the forecast days from the historical days according to the magnitude of the similar errors;
and 4, calculating the information entropy of each load similarity day, determining the weight of each load similarity day, and calculating the hourly load of the prediction day by combining the hourly loads of the similarity days.
2. The method for predicting the short-term cooling, heating and power load at the distributed energy user side according to claim 1, wherein in step 1, quantitative analysis can be performed on the influence factors, and the correlation coefficient between each influence factor and the load is calculated, wherein the calculation formula is as follows:
in the formula, rxyThe correlation coefficient is the load x and the influencing factor y; x is the number ofi、yjThe ith and jth data points of the load x and the influencing factor y respectively;
respectively the average values of the load x and the influencing factor y; z is the number of data points.
3. The method according to claim 2, wherein the influencing factors include meteorological factors and non-meteorological factors;
the meteorological factors include: temperature, humidity, wind speed, precipitation, etc.; non-meteorological factors include: economics, policies, day types, demand side management, etc.
4. The method as claimed in claim 1, wherein in step 2, the daily eigenvectors of each historical day are respectively subtracted from the daily eigenvectors of the predicted day to obtain an absolute value vector δ of the eigenvalue erroriThe method comprises the following steps:
δi＝(|Xi(1)-X0(1)|,…,|Xi(n)-X0(n)|)(i＝1,…,m)
in the formula, X0To predict the day's day feature vector, X0＝(X0(1),…,X0(n)), n is the number of features, XiThe day feature vector of the ith historical day is Xi＝(Xi(1),…,Xi(n))。
5. The distributed energy user-side cooling, heating and power short-term load prediction according to claim 1, wherein the method for determining the feature weight in step 3 is as follows:
forming a characteristic evaluation matrix according to the day characteristic vector of the predicted day and the day characteristic vector of the historical day, and obtaining a characteristic evaluation standard matrix R ═ R through standardizationij]m×nThen, the specific gravity P of the ith historical day under the jth characteristic is determinedij：
According to specific gravity PijDetermining the information entropy H of the jth featurej：
Suppose PijWhen equal to 0, Pij ln Pij＝0。
To determine the weight w of each featurej：
In the formula (I), the compound is shown in the specification,
is the average of all information entropies other than 1.
6. The distributed energy user-side cooling, heating and power short-term load prediction method according to claim 1, wherein in step 3, each feature weight is multiplied by a feature error absolute value vector and summed to obtain a similarity error ξ between a day feature vector of each historical day and a day feature vector of a predicted dayi：
ξi＝w1|Xi(1)-X0(1)|+…+wn|Xi(n)-X0(n)|(i＝1,…,m)
Selecting k days with the minimum similarity error from the historical days as k load similar days of the prediction day, wherein the hourly loads of the similar days are respectively L1，…，Lk。
7. The method according to claim 1, wherein in step 4, the weight of each load similarity day is determined according to the day eigenvector similarity error of the load similarity day, the smaller the similarity error is, the larger the weight of the load similarity day is, and the weight of the load similarity day is respectively weighted with the hourly load of the similarity day to obtain the hourly load L of the prediction day0The formula is as follows:
L0＝W1×L1+…+Wk×Lk
in the formula, L1，…，LkFor hourly loads of similar days of each load, W1，…，WkA daily weight is predicted for each load.
8. A system for predicting short-term load of cooling, heating and power at the side of distributed energy users based on any one of claims 1 to 7 is characterized by comprising the following steps: the system comprises a load influence factor analysis module, a daily feature vector construction module, a load similarity day selection module and a short-term load prediction module.
The load influence factor analysis module is used for carrying out correlation analysis on the cold, heat and power load characteristic influence factors and determining correlation coefficients between the influence factors and the load;
the daily feature vector construction module is used for selecting a plurality of influence factors with stronger correlation coefficients, constructing daily feature vectors of forecast days such as historical days, and determining feature error absolute value vectors;
the load similarity day selection module is used for determining each characteristic weight, analyzing similarity errors of day characteristic vectors of the historical day and the prediction day and selecting a load similarity day;
and the short-term load prediction module is used for determining the weight of each load similar day and obtaining the hourly load of the predicted day by combining the hourly load of the similar day.
9. A terminal system comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1-7 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011334619.8A CN112465215A (en) | 2020-11-24 | 2020-11-24 | Distributed energy user side cold and heat power short-term load prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011334619.8A CN112465215A (en) | 2020-11-24 | 2020-11-24 | Distributed energy user side cold and heat power short-term load prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112465215A true CN112465215A (en) | 2021-03-09 |
Family
ID=74798888
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011334619.8A Pending CN112465215A (en) | 2020-11-24 | 2020-11-24 | Distributed energy user side cold and heat power short-term load prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112465215A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113095566A (en) * | 2021-04-08 | 2021-07-09 | 国网山东省电力公司电力科学研究院 | Multi-source coordination energy supply method and system based on energy consumption behavior hierarchical analysis |
| CN113887833A (en) * | 2021-10-28 | 2022-01-04 | 西安热工研究院有限公司 | Distributed energy user side time-by-time load prediction method and system |
| CN114094638A (en) * | 2021-11-13 | 2022-02-25 | 国网辽宁省电力有限公司沈阳供电公司 | Demand response active power adjusting method |
| CN117272121A (en) * | 2023-11-21 | 2023-12-22 | 江苏米特物联网科技有限公司 | Hotel load influence factor quantitative analysis method based on Deep SHAP |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107506843A (en) * | 2017-07-03 | 2017-12-22 | 国网上海市电力公司 | A kind of short-term load forecasting method and device |
| CN108229754A (en) * | 2018-01-31 | 2018-06-29 | 杭州电子科技大学 | Short-term load forecasting method based on similar day segmentation and LM-BP networks |
| US20200090285A1 (en) * | 2018-03-16 | 2020-03-19 | Dalian University Of Technology | Method for short-term generation scheduling of cascade hydropower plants coupling cluster analysis and decision tree |
| CN111008351A (en) * | 2019-11-05 | 2020-04-14 | 新奥数能科技有限公司 | Method and system for predicting short-term load of cooling, heating and power |
-
2020
- 2020-11-24 CN CN202011334619.8A patent/CN112465215A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107506843A (en) * | 2017-07-03 | 2017-12-22 | 国网上海市电力公司 | A kind of short-term load forecasting method and device |
| CN108229754A (en) * | 2018-01-31 | 2018-06-29 | 杭州电子科技大学 | Short-term load forecasting method based on similar day segmentation and LM-BP networks |
| US20200090285A1 (en) * | 2018-03-16 | 2020-03-19 | Dalian University Of Technology | Method for short-term generation scheduling of cascade hydropower plants coupling cluster analysis and decision tree |
| CN111008351A (en) * | 2019-11-05 | 2020-04-14 | 新奥数能科技有限公司 | Method and system for predicting short-term load of cooling, heating and power |
Non-Patent Citations (1)
| Title |
|---|
| 黎灿兵等: "电力短期负荷预测相似日选取算法", 《电力系统自动化》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113095566A (en) * | 2021-04-08 | 2021-07-09 | 国网山东省电力公司电力科学研究院 | Multi-source coordination energy supply method and system based on energy consumption behavior hierarchical analysis |
| CN113887833A (en) * | 2021-10-28 | 2022-01-04 | 西安热工研究院有限公司 | Distributed energy user side time-by-time load prediction method and system |
| CN114094638A (en) * | 2021-11-13 | 2022-02-25 | 国网辽宁省电力有限公司沈阳供电公司 | Demand response active power adjusting method |
| CN117272121A (en) * | 2023-11-21 | 2023-12-22 | 江苏米特物联网科技有限公司 | Hotel load influence factor quantitative analysis method based on Deep SHAP |
| CN117272121B (en) * | 2023-11-21 | 2024-03-12 | 江苏米特物联网科技有限公司 | Hotel load influence factor quantitative analysis method based on Deep SHAP |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112465215A (en) | Distributed energy user side cold and heat power short-term load prediction method and system | |
| CN111260136A (en) | Building short-term load prediction method based on ARIMA-LSTM combined model | |
| CN111680841B (en) | Short-term load prediction method, system and terminal equipment based on principal component analysis | |
| Xuemei et al. | Building cooling load forecasting model based on LS-SVM | |
| CN114119273B (en) | Non-invasive load decomposition method and system for park comprehensive energy system | |
| CN109242169B (en) | Short-term load prediction method for large power customer | |
| CN103971175B (en) | Short-term load prediction method of multistage substations | |
| CN111260116A (en) | Time-interval refined short-term load prediction method based on BOA-SVR and fuzzy clustering | |
| Toubeau et al. | Capturing spatio-temporal dependencies in the probabilistic forecasting of distribution locational marginal prices | |
| CN113343334B (en) | Cross-building air conditioner energy consumption prediction method and device based on air conditioner energy consumption sensitive variable | |
| CN110909958A (en) | Short-term load prediction method considering photovoltaic grid-connected power | |
| CN109376911A (en) | A kind of micro-capacitance sensor short-term load forecasting method based on EMD-KELMs-SDPSO | |
| CN109583645A (en) | A kind of public building short-term load forecasting method | |
| CN115222106A (en) | User day-ahead load prediction method of self-adaptive model | |
| CN109858668B (en) | Coordination prediction method for power load region in thunder and lightning climate | |
| Tavares et al. | Comparison of PV power generation forecasting in a residential building using ANN and DNN | |
| CN115545333A (en) | Method for predicting load curve of multi-load daily-type power distribution network | |
| CN115689146A (en) | Multi-energy intelligent building load scheduling method and system | |
| CN111815039A (en) | Weekly scale wind power probability prediction method and system based on weather classification | |
| CN113887833A (en) | Distributed energy user side time-by-time load prediction method and system | |
| CN114186733A (en) | Short-term load prediction method and device | |
| CN113887809A (en) | Power distribution network supply and demand balance method, system, medium and computing equipment under double-carbon target | |
| CN113570414A (en) | Electricity price prediction method for optimizing deep neural network based on improved Adam algorithm | |
| CN109409604B (en) | Cold load prediction method based on genetic algorithm-support vector machine | |
| CN108694475A (en) | Short-term time scale photovoltaic cell capable of generating power amount prediction technique based on mixed model |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210309 |