Electric Load Forecasting Based on a Least Squares Support Vector Machine with Fuzzy Time Series and Global Harmony Search Algorithm

Chen, Yan Hong; Hong, Wei-Chiang; Shen, Wen; Huang, Ning

doi:10.3390/en9020070

Cited by 93 publications

(52 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The proposed SVR structure is actually the model proposed by Chen et al [75] and is commonly applied for the purposes of short term load forecast. To implement it we used the LibSVM library for MATLAB (see Chang C.C; Lin C. J, [125]).…”

Section: Comparison With Machine Learning Techniquesmentioning

confidence: 99%

“…SVM perform a nonlinear (kernel functions) mapping of the time series into a high dimensional (feature) space (a process which is the opposite of the ANN process). Chen et al [75] provides an updated list of SVM and its extensions applied to load forecasting. SVM use some linear functions to create linear decision boundaries in the new space.…”

Section: Introductionmentioning

confidence: 99%

“…A combination of Particle Swarm Optimization (PSO) and data mining methods in a SVM was used by Qiu [83] with improved forecasting results. In general, various optimization algorithms are extensively used in LSSVM to improve its searching performance, such as Fruit Fly Optimization (FFO) [85,88], Particle Swarm Optimization (PSO) [93], and Global Harmony Search Algorithm [75].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Analysis and Modeling for Short- to Medium-Term Load Forecasting Using a Hybrid Manifold Learning Principal Component Model and Comparison with Classical Statistical Models (SARIMAX, Exponential Smoothing) and Artificial Intelligence Models (ANN, SVM): The Case of Greek Electricity Market

et al. 2016

View full text Add to dashboard Cite

Abstract:In this work we propose a new hybrid model, a combination of the manifold learning Principal Components (PC) technique and the traditional multiple regression (PC-regression), for short and medium-term forecasting of daily, aggregated, day-ahead, electricity system-wide load in the Greek Electricity Market for the period 2004-2014. PC-regression is shown to effectively capture the intraday, intraweek and annual patterns of load. We compare our model with a number of classical statistical approaches (Holt-Winters exponential smoothing of its generalizations Error-Trend-Seasonal, ETS models, the Seasonal Autoregressive Moving Average with exogenous variables, Seasonal Autoregressive Integrated Moving Average with eXogenous (SARIMAX) model as well as with the more sophisticated artificial intelligence models, Artificial Neural Networks (ANN) and Support Vector Machines (SVM). Using a number of criteria for measuring the quality of the generated in-and out-of-sample forecasts, we have concluded that the forecasts of our hybrid model outperforms the ones generated by the other model, with the SARMAX model being the next best performing approach, giving comparable results. Our approach contributes to studies aimed at providing more accurate and reliable load forecasting, prerequisites for an efficient management of modern power systems.

show abstract

Section: Comparison With Machine Learning Techniquesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analysis and Modeling for Short- to Medium-Term Load Forecasting Using a Hybrid Manifold Learning Principal Component Model and Comparison with Classical Statistical Models (SARIMAX, Exponential Smoothing) and Artificial Intelligence Models (ANN, SVM): The Case of Greek Electricity Market

et al. 2016

View full text Add to dashboard Cite

show abstract

“…The difference could be due to the use of electrical heating equipment in Network 1 [30] and also because of the typical load profile in household customers in Spain, which corresponds to peak values at 19-22 h (evening) and at 11-14 h (morning). The load pattern of commercial customers is heavily influenced by opening and closing hours (9)(10)(11)(12)(13)(14)(15)(16)(17)(18)(19)(20)(21) and the use of cooling appliances during summer. …”

Section: Data Analysis and Pre-processingmentioning

confidence: 99%

“…In [16], a meta-learning system is proposed, which automatically selects the best load forecasting algorithm out of seven well-known options based on the similarity of the new samples with previously analyzed ones, considering not only univariate data, but also multivariate data. As an improvement to traditional forecasting algorithms, other novel hybridizations have been proposed lately, such as chaotic evolutionary algorithms hybridized with SVR [17] or least squares SVM with fuzzy time series and the global harmony search algorithm [18].…”

Section: Introductionmentioning

confidence: 99%

Assessment of an Adaptive Load Forecasting Methodology in a Smart Grid Demonstration Project

et al. 2017

View full text Add to dashboard Cite

This paper presents the implementation of an adaptive load forecasting methodology in two different power networks from a smart grid demonstration project deployed in the region of Madrid, Spain. The paper contains an exhaustive comparative study of different short-term load forecast methodologies, addressing the methods and variables that are more relevant to be applied for the smart grid deployment. The evaluation followed in this paper suggests that the performance of the different methods depends on the conditions of the site in which the smart grid is implemented. It is shown that some non-linear methods, such as support vector machine with a radial basis function kernel and extremely randomized forest offer good performance using only 24 lagged load hourly values, which could be useful when the amount of data available is limited due to communication problems in the smart grid monitoring system. However, it has to be highlighted that, in general, the behavior of different short-term load forecast methodologies is not stable when they are applied to different power networks and that when there is a considerable variability throughout the whole testing period, some methods offer good performance in some situations, but they fail in others. In this paper, an adaptive load forecasting methodology is proposed to address this issue improving the forecasting performance through iterative optimization: in each specific situation, the best short-term load forecast methodology is chosen, resulting in minimum prediction errors.

show abstract

Introduction

Hong¹

2020

Hybrid Intelligent Technologies in Energy Demand Forecasting

View full text Add to dashboard Cite

Electric Load Forecasting Based on a Least Squares Support Vector Machine with Fuzzy Time Series and Global Harmony Search Algorithm

Cited by 93 publications

References 41 publications

Analysis and Modeling for Short- to Medium-Term Load Forecasting Using a Hybrid Manifold Learning Principal Component Model and Comparison with Classical Statistical Models (SARIMAX, Exponential Smoothing) and Artificial Intelligence Models (ANN, SVM): The Case of Greek Electricity Market

Analysis and Modeling for Short- to Medium-Term Load Forecasting Using a Hybrid Manifold Learning Principal Component Model and Comparison with Classical Statistical Models (SARIMAX, Exponential Smoothing) and Artificial Intelligence Models (ANN, SVM): The Case of Greek Electricity Market

Assessment of an Adaptive Load Forecasting Methodology in a Smart Grid Demonstration Project

Introduction

Contact Info

Product

Resources

About