skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: A Short-Term and High-Resolution System Load Forecasting Approach Using Support Vector Regression with Hybrid Parameters Optimization

Abstract

This work proposes an approach for distribution system load forecasting, which aims to provide highly accurate short-term load forecasting with high resolution utilizing a support vector regression (SVR) based forecaster and a two-step hybrid parameters optimization method. Specifically, because the load profiles in distribution systems contain abrupt deviations, a data normalization is designed as the pretreatment for the collected historical load data. Then an SVR model is trained by the load data to forecast the future load. For better performance of SVR, a two-step hybrid optimization algorithm is proposed to determine the best parameters. In the first step of the hybrid optimization algorithm, a designed grid traverse algorithm (GTA) is used to narrow the parameters searching area from a global to local space. In the second step, based on the result of the GTA, particle swarm optimization (PSO) is used to determine the best parameters in the local parameter space. After the best parameters are determined, the SVR model is used to forecast the short-term load deviation in the distribution system.

Authors:
 [1]
  1. National Renewable Energy Laboratory (NREL), Golden, CO (United States)
Publication Date:
Research Org.:
National Renewable Energy Lab. (NREL), Golden, CO (United States)
Sponsoring Org.:
USDOE Office of Electricity Delivery and Energy Reliability (OE)
OSTI Identifier:
1378081
Report Number(s):
NREL/PR-5D00-68876
Journal ID: ISSN 1949--3053
DOE Contract Number:
AC36-08GO28308
Resource Type:
Conference
Resource Relation:
Conference: Presented at the 2017 IEEE Power & Energy Society General Meeting, 16-20 July 2017, Chicago, Illinois
Country of Publication:
United States
Language:
English
Subject:
24 POWER TRANSMISSION AND DISTRIBUTION; short-term load forecast; support vector regression; grid traverse algorithm; particle swarm optimization; distribution system

Citation Formats

Jiang, Huaiguang. A Short-Term and High-Resolution System Load Forecasting Approach Using Support Vector Regression with Hybrid Parameters Optimization. United States: N. p., 2017. Web. doi:10.1109/TSG.2016.2628061.
Jiang, Huaiguang. A Short-Term and High-Resolution System Load Forecasting Approach Using Support Vector Regression with Hybrid Parameters Optimization. United States. doi:10.1109/TSG.2016.2628061.
Jiang, Huaiguang. Fri . "A Short-Term and High-Resolution System Load Forecasting Approach Using Support Vector Regression with Hybrid Parameters Optimization". United States. doi:10.1109/TSG.2016.2628061. https://www.osti.gov/servlets/purl/1378081.
@article{osti_1378081,
title = {A Short-Term and High-Resolution System Load Forecasting Approach Using Support Vector Regression with Hybrid Parameters Optimization},
author = {Jiang, Huaiguang},
abstractNote = {This work proposes an approach for distribution system load forecasting, which aims to provide highly accurate short-term load forecasting with high resolution utilizing a support vector regression (SVR) based forecaster and a two-step hybrid parameters optimization method. Specifically, because the load profiles in distribution systems contain abrupt deviations, a data normalization is designed as the pretreatment for the collected historical load data. Then an SVR model is trained by the load data to forecast the future load. For better performance of SVR, a two-step hybrid optimization algorithm is proposed to determine the best parameters. In the first step of the hybrid optimization algorithm, a designed grid traverse algorithm (GTA) is used to narrow the parameters searching area from a global to local space. In the second step, based on the result of the GTA, particle swarm optimization (PSO) is used to determine the best parameters in the local parameter space. After the best parameters are determined, the SVR model is used to forecast the short-term load deviation in the distribution system.},
doi = {10.1109/TSG.2016.2628061},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Fri Aug 25 00:00:00 EDT 2017},
month = {Fri Aug 25 00:00:00 EDT 2017}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:
  • This paper proposes an approach for distribution system load forecasting, which aims to provide highly accurate short-term load forecasting with high resolution utilizing a support vector regression (SVR) based forecaster and a two-step hybrid parameters optimization method. Specifically, because the load profiles in distribution systems contain abrupt deviations, a data normalization is designed as the pretreatment for the collected historical load data. Then an SVR model is trained by the load data to forecast the future load. For better performance of SVR, a two-step hybrid optimization algorithm is proposed to determine the best parameters. In the first step of themore » hybrid optimization algorithm, a designed grid traverse algorithm (GTA) is used to narrow the parameters searching area from a global to local space. In the second step, based on the result of the GTA, particle swarm optimization (PSO) is used to determine the best parameters in the local parameter space. After the best parameters are determined, the SVR model is used to forecast the short-term load deviation in the distribution system. The performance of the proposed approach is compared to some classic methods in later sections of the paper.« less
  • In this paper, a hybrid model for short-term load forecast that integrates artificial neural networks and fuzzy expert systems is presented. The forecasted load is obtained by passing through two steps. In the first procedure, the artificial neural networks are trained with the load patterns corresponding to the forecasting hour, and the provisional forecasted load is obtained by the trained artificial neural networks. In the second procedure, the fuzzy expert systems modify the provisional forecasted load considering the possibility of load variation due to changes in temperature and the load behavior of holiday. In the test case of 1994 formore » implementation in short term load forecasting expert system of Korea Electric Power Corporation (KEPCO), the proposed hybrid model provided good forecasting accuracy of the mean absolute percentage errors below 1.3%. The comparison results with exponential smoothing method showed the efficiency and accuracy of the hybrid model.« less
  • This paper describes a new, linear regression-based model for the calculation of short-term system load forecasts. The model's most significant new aspects fall into the following areas: innovative model building, including accurate holiday modeling by using binary variables; temperature modeling by using heating and cooling degree functions; robust parameter estimation and parameter estimation under heteroskedasticity by using weighted least squares linear regression techniques; the use of reverse errors-in-variables techniques to mitigate the effects on load forecasts of potential errors in the explanatory variables; and distinction between time-independent daily peak load forecasts and the maximum of the hourly load forecasts inmore » order to prevent peak forecasts from being negatively biased. The significant impact of these issues on the accuracy of a model's results was established through testing of an existing load forecasting algorithm. The new model has been tested under a wide variety of conditions and it is shown in this paper to produce excellent results. It is also sufficiently general to be used by other electric power utilities.« less
  • A fuzzy neural network based on the multilayer perceptron and capable of fuzzy classification of patterns is presented in this paper. A hybrid learning algorithm consisting of unsupervised and supervised learning phases is used for training the network. In the supervised learning phase linear Kalman filter equations are used for tuning the weights and membership functions. Extensive tests have been performed on two-year utility data for generation of peak and average load profiles for 24- and 168-hours ahead time frames and results for winter and summer months are given to confirm the effectiveness of the new approach.
  • For the economic and secure operation of power systems, a precise short-term load forecasting technique is essential. Modern load forecasting techniques - especially artificial neural network methods - are particularly attractive, as they have the ability to handle the non-linear relationships between load, weather temperature, and the factors affecting them directly. A test of two different ANN models on data from Australia's Victoria market is promising. (author)