Cyclic electric load forecasting by seasonal SVR with chaotic genetic algorithm

Hong, Wei‐Chiang; Dong, Yucheng; Zhang, Wen Yu; Chen, Li-Yueh; Panigrahi, B. K.

doi:10.1016/j.ijepes.2012.08.010

Cited by 177 publications

(64 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…How to effectively improve the accuracy of electricity demand prediction has become a major challenge to researchers [8]. At present, the methods used for short-term electricity demand prediction mainly include time series [9][10][11], Regression Analysis [12,13], Support Vector Regression [14][15][16], Neural Network [17][18][19][20], Bayes [21], Fuzzy Theory [20,22], and Wavelet Echo State Network [23]. Each kind of method has its own applicable scenario, and no model can achieve desired satisfying result alone.…”

Section: Related Workmentioning

confidence: 99%

Predicting Short‐Term Electricity Demand by Combining the Advantages of ARMA and XGBoost in Fog Computing Environment

Zheng

Yang

et al. 2018

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

With the rapid development of IoT, the disadvantages of Cloud framework have been exposed, such as high latency, network congestion, and low reliability. Therefore, the Fog Computing framework has emerged, with an extended Fog Layer between the Cloud and terminals. In order to address the real-time prediction on electricity demand, we propose an approach based on XGBoost and ARMA in Fog Computing environment. By taking the advantages of Fog Computing framework, we first propose a prototypebased clustering algorithm to divide enterprise users into several categories based on their total electricity consumption; we then propose a model selection approach by analyzing users' historical records of electricity consumption and identifying the most important features. Generally speaking, if the historical records pass the test of stationarity and white noise, ARMA is used to model the user's electricity consumption in time sequence; otherwise, if the historical records do not pass the test, and some discrete features are the most important, such as weather and whether it is weekend, XGBoost will be used. The experiment results show that our proposed approach by combining the advantage of ARMA and XGBoost is more accurate than the classical models.

show abstract

Section: Related Workmentioning

confidence: 99%

Predicting Short‐Term Electricity Demand by Combining the Advantages of ARMA and XGBoost in Fog Computing Environment

Zheng

Yang

et al. 2018

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…The forecasting values could also be received, then, the forecasting error is calculated as the fitness value for each bat by the mean absolute percentage error (MAPE), as shown in Equation (33).…”

Section: Implementation Steps Of Cqbamentioning

confidence: 99%

Hybrid Chaotic Quantum Bat Algorithm with SVR in Electric Load Forecasting

Geng

Wang

et al. 2017

Energies

Self Cite

View full text Add to dashboard Cite

Abstract:Hybridizing evolutionary algorithms with a support vector regression (SVR) model to conduct the electric load forecasting has demonstrated the superiorities in forecasting accuracy improvements. The recently proposed bat algorithm (BA), compared with classical GA and PSO algorithm, has greater potential in forecasting accuracy improvements. However, the original BA still suffers from the embedded drawbacks, including trapping in local optima and premature convergence. Hence, to continue exploring possible improvements of the original BA and to receive more appropriate parameters of an SVR model, this paper applies quantum computing mechanism to empower each bat to possess quantum behavior, then, employs the chaotic mapping function to execute the global chaotic disturbance process, to enlarge bat's search space and to make the bat jump out from the local optima when population is over accumulation. This paper presents a novel load forecasting approach, namely SVRCQBA model, by hybridizing the SVR model with the quantum computing mechanism, chaotic mapping function, and BA, to receive higher forecasting accuracy. The numerical results demonstrate that the proposed SVRCQBA model is superior to other alternative models in terms of forecasting accuracy.

show abstract

“…Support vector regression (SVR) is the most common application form of support vector machine (SVM). An overview of the basic ideas underlying SVM for regression and function estimation has been given in [48], and its use in load forecasting is reported in literatures [49][50][51][52][53].…”

Section: Definition References For Mtlf and Ltlf Are Elaborated In Dmentioning

confidence: 99%

Forecasting the load of electrical power systems in mid‐ and long‐term horizons: a review

Khuntia

Rueda

Meijden

2016

IET Generation, Transmission & Distribution

134

View full text Add to dashboard Cite

Load forecasting has always been an important part in the planning and operation of electric utilities, i.e., both transmission and distribution companies. With technological advancement, change in economic condition and many other factors (to be discussed in this work), load forecasting is becoming more important. The forecast affects as well as gets affected because of the load impacting factors and actions taken in different time horizons. However, due to its stochastic and uncertainty characteristics, it has been one challenging problem for electrical utilities to accurately forecast future load demand. This paper aims at reviewing the different load forecasting techniques developed for the mid-and long-term horizons of electrical power systems. Since there has never been an explicit literature study of the various forecasting techniques for mid-and long-term horizons, this paper reviews techniques for each of the forecasting horizons, citing various methodologies developed so far supported by published literature. The study is concluded with discussion on future research directions.

show abstract

Cyclic electric load forecasting by seasonal SVR with chaotic genetic algorithm

Cited by 177 publications

References 76 publications

Predicting Short‐Term Electricity Demand by Combining the Advantages of ARMA and XGBoost in Fog Computing Environment

Predicting Short‐Term Electricity Demand by Combining the Advantages of ARMA and XGBoost in Fog Computing Environment

Hybrid Chaotic Quantum Bat Algorithm with SVR in Electric Load Forecasting

Forecasting the load of electrical power systems in mid‐ and long‐term horizons: a review

Contact Info

Product

Resources

About