CN110705763A - Ultra-short-term load prediction method and system with error correction - Google Patents
Ultra-short-term load prediction method and system with error correction Download PDFInfo
- Publication number
- CN110705763A CN110705763A CN201910900793.5A CN201910900793A CN110705763A CN 110705763 A CN110705763 A CN 110705763A CN 201910900793 A CN201910900793 A CN 201910900793A CN 110705763 A CN110705763 A CN 110705763A
- Authority
- CN
- China
- Prior art keywords
- prediction
- predictor
- error
- training
- holt
- 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.)
- Granted
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
- 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
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
Abstract
The invention discloses a method and a system for predicting ultra-short-term load with error correction, wherein the method comprises the following steps: acquiring user load historical data, wherein the user load historical data comprises a training data set and a test set in a specified time period; training a Holt-Winter predictor based on a training data set, and predicting the user load in the specified time period based on the Holt-Winter predictor; obtaining an error prediction training set according to the predicted value and the test set of the specified time interval; training an error predictor based on an overrun learning machine based on an error prediction training set; and obtaining a combined prediction model based on the Holt-Winter predictor and the error predictor, and performing load prediction. The invention comprehensively considers the periodicity rule of the conforming data and the uncertainty of the power utilization, and ensures the prediction precision.
Description
Technical Field
The invention belongs to the technical field of power load prediction, and particularly relates to an ultra-short-term load prediction method and system with error correction.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The multi-energy complementary comprehensive energy system integrates various renewable energy sources such as wind, light and terrestrial heat, adopts a distributed energy supply mode, can effectively improve the consumption rate of the renewable energy sources and the comprehensive utilization rate of the energy sources, and is an important means for supplying energy sources in the future of cities.
The accurate load prediction can inhibit the adverse effect of load uncertainty, better support the planning, operation and service of the comprehensive energy system, and is an important basis for realizing the optimized operation of the comprehensive energy system. Therefore, the research on the ultra-short-term load prediction method and the improvement on the load prediction precision have important significance on the economic, efficient and stable operation of the system. However, the comprehensive energy system no longer only takes electric energy as a research object, and covers a wider variety of energy forms such as heat (cold), gas, oil and the like, so that diversified energy requirements of different users need to be directly met, and the randomness of various load changes provides a greater challenge for accurate prediction of loads.
The existing load prediction methods are mainly divided into two types, namely a statistical model and a machine learning model, linear regression (such as ARIMA, Holt-Winter) and Kalman filtering in the statistical model are applied more generally, the methods can summarize more regular changes (such as periodicity, seasonality and the like) of a load curve, but an accurate mathematical model is difficult to establish for various influences on the load, such as price, weather, policy and the like, so that a satisfactory result is difficult to obtain. The machine learning method does not need to establish an accurate model of an object in the analysis process, can abstract the internal relation between a plurality of external influence factors and the load, and is increasingly applied to load prediction. Common methods are Support Vector Machines (SVMs), Convolutional Neural Networks (CNNs), long short term memory networks (LSTM), and the like. Although the machine learning method is adopted to predict the load, a good result is obtained, the method ignores the periodicity and seasonal characteristics of the load, and the prediction precision is difficult to further improve.
The search shows that Chinese patent CN109615117A 'coal-to-electricity power load prediction method based on ARIMA model' utilizes the ARIMA model to realize load prediction, thereby being beneficial to the balance of power grid load and avoiding the waste of energy. The Chinese patent CN103295075B ultra-short-term power load prediction and early warning method provides an ultra-short-term load prediction and early warning method based on Kalman filtering and wavelet echo state network, and realizes large-scale enterprise load prediction. Chinese patent CN109934392A short-term load prediction method of micro-grid based on deep learning proposes a machine learning prediction method based on Convolutional Neural Network (CNN) and long-term short-term memory network (LSTM), and deeply excavates the characteristics and relationship of load data to improve prediction accuracy and reliability. However, the above inventions realize load prediction by singly adopting a statistical model or a machine learning model, and the advantages of the two models cannot be effectively combined.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides the ultra-short-term load prediction method and the ultra-short-term load prediction system containing error correction, which comprehensively consider the periodicity rule of the conforming data and the uncertainty of power utilization, and ensure the prediction precision.
In order to achieve the above object, one or more embodiments of the present invention provide the following technical solutions:
an ultra-short term load prediction method including error correction, comprising the steps of:
acquiring user load historical data, wherein the user load historical data comprises a training data set and a test set in a specified time period;
training a Holt-Winter predictor based on a training data set, and predicting the user load in the specified time period based on the Holt-Winter predictor;
obtaining an error prediction training set according to the predicted value and the test set of the specified time interval;
training an error predictor based on an overrun learning machine based on an error prediction training set;
and obtaining a combined prediction model based on the Holt-Winter predictor and the error predictor, and performing load prediction.
After the user load historical data is obtained, data stability verification, data cleaning and data normalization preprocessing are carried out on the user load historical data.
Further, training the Holt-Winter predictor based on the training data set includes:
and optimizing parameters of the Holt-Winter predictor by using a particle swarm algorithm and aiming at the minimum root mean square error of the prediction result to obtain the Holt-Winter predictor.
Further, the load prediction based on the combined prediction model comprises:
receiving data required by load prediction, performing load prediction based on a Holt-Winter predictor, and obtaining a prediction error;
taking the prediction error as the input of an error predictor to obtain an error prediction result of a Holt-Winter predictor;
and carrying out weighted combination on the prediction results of the Holt-Winter predictor and the error predictor to obtain a final prediction result.
Further, the user load history data further includes a test set for testing the combined predictive model.
One or more embodiments provide an ultra-short term load prediction system including error correction, comprising:
the data acquisition module is used for acquiring user load historical data, wherein the user load historical data comprises a training data set and a test set in a specified time period;
the Holt-Winter predictor construction module is used for training the Holt-Winter predictor based on a training data set;
the error predictor construction module is used for predicting the user load in the specified time interval based on the Holt-Winter predictor and obtaining an error prediction training set according to the predicted value and the test set in the specified time interval; training an error predictor based on an overrun learning machine based on an error prediction training set;
and the load prediction module is used for obtaining a combined prediction model based on the Holt-Winter predictor and the error predictor and carrying out load prediction.
One or more embodiments provide an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for ultra-short term load prediction including error correction when executing the program.
One or more embodiments provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the ultra-short term load prediction method including error correction.
The above one or more technical solutions have the following beneficial effects:
the invention provides a comprehensive energy system load ultra-short-term prediction method based on Holt-Winter and ELM, which can add prediction error correction while considering the periodicity and the seasonality of load change, thereby further improving the prediction precision. The method changes the idea that the traditional linear regression method or machine learning method is singly used for load prediction, combines the advantages of the two methods, and takes HW (linear regression method) as a main predictor and ELM (machine learning method) as an error predictor for correcting the prediction error of the HW; the advantages of different methods are fully exerted, and higher prediction precision is achieved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a flow diagram of a method for ultra-short term load prediction including error correction in one or more embodiments of the invention;
FIG. 2 is a graph of the load change at 15 months per year;
fig. 3 is a load change curve for three consecutive days.
Detailed Description
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
Example one
The embodiment discloses an ultra-short-term load prediction method including error correction, which comprises the following steps:
step 1: acquiring user load historical data;
collecting user load data historical data, and dividing the data into three parts: the HW training set is used for obtaining a Holt-Winter prediction model; the error test set is used for obtaining a training set of error prediction; and combining the test sets for verifying the prediction accuracy of the method. Taking the seasonal and periodic load data into consideration, taking 1-6 months of data in one year as an HW training set, taking 7-9 months of data as an error test set, taking 10-12 months of data as a combined test set, and taking the data interval as 15 min.
Step 2: preprocessing the load historical data;
data stability: the data stability was verified using the elementary root (ADF) to ensure that the Holt-Winter method is applicable.
Data cleaning: replacing missing data and outliers (typically less than 1% of the total data volume) with the current month historical data mean;
data normalization: and for the error prediction training set, a statistical extreme value normalization method is adopted to normalize the numerical value into an interval (0, 1).
And step 3: training a Holt-Winter prediction model based on a HW training set.
Since the load changes are affected by weather, temperature, etc., there is a significant seasonality (as shown in fig. 2, the average daily power consumption of 3 to 8 months is lower than that of the other six months, the slope of the load curve becomes smaller between 15:00 and 24:00 per day, the peak becomes smaller, and the peak time is delayed). In addition, different living behavior habits of the user are also one of the main influencing factors of the load change, and the living behavior of the user often shows a change trend with a day as a cycle (as shown in fig. 3, the load mean values and peak values of adjacent cycles are different, but the difference is not obvious, and the change trends are very similar). The Holt-Winter method is used as a linear regression method and has a good prediction effect on time sequence data with periodicity and seasonality, so that the Holt-Winter method is used as a main detector by utilizing the advantages of the Holt-Winter method for processing the periodic time sequence data and the seasonal time sequence data based on a HW training set. And (3) optimizing main parameters of a Holt-Winter predictor by using a Particle Swarm Optimization (PSO) algorithm and taking the minimum root mean square error of a prediction result as a target to obtain a main prediction model.
And (3) acquiring an error prediction training set by combining an error test set based on the load of 3 months (7-9 months) after the main prediction model is predicted.
And 4, step 4: training an ELM (extreme learning machine) based error predictor model by utilizing a PSO-HW error prediction training set;
although the load change has seasonality and periodicity, due to uncertainty of user energy behavior, the load still has randomness and volatility, and the traditional method which cannot consider the long-time sequence law is difficult to meet the prediction requirement, so that the error of the main predictor is predicted by using the ELM. And obtaining an ELM error prediction model by using the error prediction training set.
And 5: and obtaining a PSO-HW-ELM combined prediction model for ultra-short-term load prediction, verifying the obtained model through a test set, and evaluating parameters by using a prediction result to realize model performance evaluation.
And combining the main prediction model and the error prediction model to obtain a final combined prediction model, verifying the prediction accuracy of the method by using the combined test set, and evaluating the performance of the prediction model by using Root Mean Square Error (RMSE), Mean Square Error (MSE) and Mean Absolute Error (MAE).
Step 6: and carrying out load prediction based on a PSO-HW-ELM combined prediction model.
Specifically, a prediction result is obtained through a main prediction model, a prediction error of the main prediction model is used as an input of an error predictor, the prediction error of the main prediction model is predicted, and then the prediction results of the two prediction models are combined in a weighting mode to obtain a final prediction result.
Example two
It is an object of the present embodiment to provide an ultra-short term load prediction system including error correction.
In order to achieve the above object, the present embodiment provides an ultra-short term load prediction system including error correction, including:
the data acquisition module is used for acquiring user load historical data, wherein the user load historical data comprises a training data set and a test set in a specified time period;
the Holt-Winter predictor construction module is used for training the Holt-Winter predictor based on a training data set;
the error predictor construction module is used for predicting the user load in the specified time interval based on the Holt-Winter predictor and obtaining an error prediction training set according to the predicted value and the test set in the specified time interval; training an error predictor based on an overrun learning machine based on an error prediction training set;
and the load prediction module is used for obtaining a combined prediction model based on the Holt-Winter predictor and the error predictor and carrying out load prediction.
EXAMPLE III
The embodiment aims at providing an electronic device.
An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the program, comprising:
acquiring user load historical data, wherein the user load historical data comprises a training data set and a test set in a specified time period;
training a Holt-Winter predictor based on a training data set, and predicting the user load in the specified time period based on the Holt-Winter predictor;
obtaining an error prediction training set according to the predicted value and the test set of the specified time interval;
training an error predictor based on an overrun learning machine based on an error prediction training set;
and obtaining a combined prediction model based on the Holt-Winter predictor and the error predictor, and performing load prediction.
Example four
An object of the present embodiment is to provide a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, performs the steps of:
acquiring user load historical data, wherein the user load historical data comprises a training data set and a test set in a specified time period;
training a Holt-Winter predictor based on a training data set, and predicting the user load in the specified time period based on the Holt-Winter predictor;
obtaining an error prediction training set according to the predicted value and the test set of the specified time interval;
training an error predictor based on an overrun learning machine based on an error prediction training set;
and obtaining a combined prediction model based on the Holt-Winter predictor and the error predictor, and performing load prediction.
The steps involved in the above second, third and fourth embodiments correspond to the first embodiment of the method, and the detailed description thereof can be found in the relevant description of the first embodiment. The term "computer-readable storage medium" should be taken to include a single medium or multiple media containing one or more sets of instructions; it should also be understood to include any medium that is capable of storing, encoding or carrying a set of instructions for execution by a processor and that cause the processor to perform any of the methods of the present invention.
One or more of the above embodiments have the following technical effects:
according to the invention, the Holt-winter model is adopted for load prediction, the periodicity and the seasonality of the load can be taken into consideration, and the particle swarm algorithm is introduced to optimize the parameters of the Holt-winter model, so that the prediction precision is ensured; the uncertainty of the energy using behavior of the user is considered, errors are inevitably generated in load prediction, the error prediction is realized based on an overrun learning machine training error prediction model, and the error prediction and the overrun learning machine training error prediction model are combined to realize accurate prediction of the load.
Those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using general purpose computer means, or alternatively, they can be implemented using program code that is executable by computing means, such that they are stored in memory means for execution by the computing means, or they are separately fabricated into individual integrated circuit modules, or multiple modules or steps of them are fabricated into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (8)
1. An ultra-short term load prediction method including error correction, comprising the steps of:
acquiring user load historical data, wherein the user load historical data comprises a training data set and a test set in a specified time period;
training a Holt-Winter predictor based on a training data set, and predicting the user load in the specified time period based on the Holt-Winter predictor;
obtaining an error prediction training set according to the predicted value and the test set of the specified time interval;
training an error predictor based on an overrun learning machine based on an error prediction training set;
and obtaining a combined prediction model based on the Holt-Winter predictor and the error predictor, and performing load prediction.
2. The ultra-short term load prediction method with error correction as claimed in claim 1, wherein after obtaining the user load historical data, the user load historical data is further subjected to data stability check, data cleaning and data normalization preprocessing.
3. The method of ultra-short term load prediction with error correction as claimed in claim 1, wherein training the Holt-Winter predictor based on the training data set comprises:
and optimizing parameters of the Holt-Winter predictor by using a particle swarm algorithm and aiming at the minimum root mean square error of the prediction result to obtain the Holt-Winter predictor.
4. The method of claim 3, wherein the load prediction based on the combined prediction model comprises:
receiving data required by load prediction, performing load prediction based on a Holt-Winter predictor, and obtaining a prediction error;
taking the prediction error as the input of an error predictor to obtain an error prediction result of a Holt-Winter predictor;
and carrying out weighted combination on the prediction results of the Holt-Winter predictor and the error predictor to obtain a final prediction result.
5. The ultra-short term load prediction method with error correction as claimed in claim 3, wherein said user load history data further comprises a test set for testing a combined prediction model.
6. An ultra-short term load prediction system including error correction, comprising:
the data acquisition module is used for acquiring user load historical data, wherein the user load historical data comprises a training data set and a test set in a specified time period;
the Holt-Winter predictor construction module is used for training the Holt-Winter predictor based on a training data set;
the error predictor construction module is used for predicting the user load in the specified time interval based on the Holt-Winter predictor and obtaining an error prediction training set according to the predicted value and the test set in the specified time interval; training an error predictor based on an overrun learning machine based on an error prediction training set;
and the load prediction module is used for obtaining a combined prediction model based on the Holt-Winter predictor and the error predictor and carrying out load prediction.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of ultra-short term load prediction including error correction as claimed in any one of claims 1-5 when executing the program.
8. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a method of ultra-short term load prediction including error correction according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910900793.5A CN110705763B (en) | 2019-09-23 | 2019-09-23 | Ultra-short-term load prediction method and system including error correction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910900793.5A CN110705763B (en) | 2019-09-23 | 2019-09-23 | Ultra-short-term load prediction method and system including error correction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110705763A true CN110705763A (en) | 2020-01-17 |
| CN110705763B CN110705763B (en) | 2022-06-14 |
Family
ID=69194937
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910900793.5A Active CN110705763B (en) | 2019-09-23 | 2019-09-23 | Ultra-short-term load prediction method and system including error correction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110705763B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111310902A (en) * | 2020-02-24 | 2020-06-19 | 石家庄铁道大学 | Training method of neural network model, slope displacement prediction method and related device |
| CN111832809A (en) * | 2020-06-19 | 2020-10-27 | 山东大学 | Building energy consumption load prediction method and system based on Holt-Winters and extreme learning machine |
| CN111967688A (en) * | 2020-09-02 | 2020-11-20 | 沈阳工程学院 | Power load prediction method based on Kalman filter and convolutional neural network |
| CN112100711A (en) * | 2020-08-10 | 2020-12-18 | 南昌大学 | ARIMA and PSO-ELM-based concrete dam deformation combined forecasting model construction method |
| CN112926807A (en) * | 2021-04-15 | 2021-06-08 | 德州欧瑞电子通信设备制造有限公司 | Ultra-short-term prediction method and system for heat productivity of cabinet equipment by considering prediction error |
| CN113131476A (en) * | 2021-04-28 | 2021-07-16 | 南方电网科学研究院有限责任公司 | Power load prediction method |
| CN116245221A (en) * | 2023-01-09 | 2023-06-09 | 上海玫克生储能科技有限公司 | Load real-time prediction method and device and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140156322A1 (en) * | 2012-08-10 | 2014-06-05 | Itron, Inc. | Unified Framework for Electrical Load Forecasting |
| CN104008432A (en) * | 2014-06-03 | 2014-08-27 | 华北电力大学 | Micro-grid short-term load forecasting method based on EMD-KELM-EKF |
| CN104820876A (en) * | 2015-05-21 | 2015-08-05 | 国家电网公司 | Short-term load forecasting method and system |
| CN107590562A (en) * | 2017-09-05 | 2018-01-16 | 西安交通大学 | A kind of Short-Term Load Forecasting of Electric Power System based on changeable weight combination predicted method |
| CN108038568A (en) * | 2017-12-05 | 2018-05-15 | 国家电网公司 | A kind of changeable weight combination Short-Term Load Forecasting of Electric Power System based on particle cluster algorithm |
-
2019
- 2019-09-23 CN CN201910900793.5A patent/CN110705763B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140156322A1 (en) * | 2012-08-10 | 2014-06-05 | Itron, Inc. | Unified Framework for Electrical Load Forecasting |
| CN104008432A (en) * | 2014-06-03 | 2014-08-27 | 华北电力大学 | Micro-grid short-term load forecasting method based on EMD-KELM-EKF |
| CN104820876A (en) * | 2015-05-21 | 2015-08-05 | 国家电网公司 | Short-term load forecasting method and system |
| CN107590562A (en) * | 2017-09-05 | 2018-01-16 | 西安交通大学 | A kind of Short-Term Load Forecasting of Electric Power System based on changeable weight combination predicted method |
| CN108038568A (en) * | 2017-12-05 | 2018-05-15 | 国家电网公司 | A kind of changeable weight combination Short-Term Load Forecasting of Electric Power System based on particle cluster algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 张明光等: "基于Holt-Winter超短期负荷预测的配电网状态估计算法", 《兰州理工大学学报》 * |
| 王惠中等: "电网供电系统短期电力负荷预测优化仿真", 《计算机系统应用》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111310902A (en) * | 2020-02-24 | 2020-06-19 | 石家庄铁道大学 | Training method of neural network model, slope displacement prediction method and related device |
| CN111310902B (en) * | 2020-02-24 | 2023-09-29 | 石家庄铁道大学 | Training method of neural network model, slope displacement prediction method and related devices |
| CN111832809A (en) * | 2020-06-19 | 2020-10-27 | 山东大学 | Building energy consumption load prediction method and system based on Holt-Winters and extreme learning machine |
| US20210398048A1 (en) * | 2020-06-19 | 2021-12-23 | Shandong University | Method and system for predicting building energy consumption based on holt-winters and extreme learning machine |
| US11842306B2 (en) * | 2020-06-19 | 2023-12-12 | Shandong University | Method and system for predicting building energy consumption based on holt-winters and extreme learning machine |
| CN112100711A (en) * | 2020-08-10 | 2020-12-18 | 南昌大学 | ARIMA and PSO-ELM-based concrete dam deformation combined forecasting model construction method |
| CN111967688A (en) * | 2020-09-02 | 2020-11-20 | 沈阳工程学院 | Power load prediction method based on Kalman filter and convolutional neural network |
| CN111967688B (en) * | 2020-09-02 | 2024-02-23 | 沈阳工程学院 | Power load prediction method based on Kalman filter and convolutional neural network |
| CN112926807A (en) * | 2021-04-15 | 2021-06-08 | 德州欧瑞电子通信设备制造有限公司 | Ultra-short-term prediction method and system for heat productivity of cabinet equipment by considering prediction error |
| CN113131476A (en) * | 2021-04-28 | 2021-07-16 | 南方电网科学研究院有限责任公司 | Power load prediction method |
| CN116245221A (en) * | 2023-01-09 | 2023-06-09 | 上海玫克生储能科技有限公司 | Load real-time prediction method and device and electronic equipment |
| CN116245221B (en) * | 2023-01-09 | 2024-03-08 | 上海玫克生储能科技有限公司 | Load real-time prediction method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110705763B (en) | 2022-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110705763B (en) | Ultra-short-term load prediction method and system including error correction | |
| Goiri et al. | Matching renewable energy supply and demand in green datacenters | |
| Asgharian et al. | The importance of the macroeconomic variables in forecasting stock return variance: A GARCH‐MIDAS approach | |
| Cheng et al. | Heterogeneity-aware workload placement and migration in distributed sustainable datacenters | |
| Zhang | Optimal scheduling of critical peak pricing considering wind commitment | |
| Hargreaves et al. | REFLEX: An adapted production simulation methodology for flexible capacity planning | |
| WO2019196427A1 (en) | Method and device for optimizing backup on the basis of supporting fault event constrained unit commitment | |
| CN112801331B (en) | Shaping of computational loads with virtual capacity and preferred location real-time scheduling | |
| CN103425564A (en) | Use predication method of smartphone software | |
| Yao et al. | Management of cascading outage risk based on risk gradient and Markovian tree search | |
| Lin et al. | Reliability evaluation on a joint machine learning and optimization framework | |
| Chen et al. | Green Databases Through Integration of Renewable Energy. | |
| CN108108837B (en) | Regional new energy power supply structure optimization prediction method and system | |
| Ahmed et al. | An energy efficient demand-response model for high performance computing systems | |
| Islam et al. | Exploiting spatio-temporal diversity for water saving in geo-distributed data centers | |
| CN103246539B (en) | Based on the generalized information system module loading method of user's use habit | |
| Ahmed et al. | Enabling demand response for hpc systems through power capping and node scaling | |
| Yu et al. | Probabilistic estimation of the potentials of intervention-based demand side energy management | |
| Brolin et al. | Modeling Swedish real-time balancing power prices using nonlinear time series models | |
| CN113449933B (en) | Regional medium-term load prediction method and device based on clustering electric quantity curve decomposition | |
| Dandres et al. | Toward a smarter electricity consumption | |
| Tan et al. | Economic analysis of lifetime-constrained battery storage under dynamic pricing | |
| Zeng | A gray model for increasing sequences with nonhomogeneous index trends based on fractional‐order accumulation | |
| Jagannadharao et al. | Timeshifting strategies for carbon-efficient long-running large language model training | |
| Adnan et al. | Workload shaping to mitigate variability in renewable power use by data centers |
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 |