GEFCom2012: Electric load forecasting and backcasting with semi-parametric models

Nedellec, Raphaël; Cugliari, Jairo; Goude, Yannig

doi:10.1016/j.ijforecast.2013.07.004

Cited by 76 publications

(47 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Load forecasting algorithms can be divided into three major categories: traditional methods, modern intelligent methods and hybrid algorithms [1]. The traditional method [1,2] mainly includes autoregressive (AR), autoregressive moving average (ARMA) [3], autoregressive integrated moving average (ARIMA) [4], semi-parametric [5], gray model [6,7], similar-day models [8], and Kalman filtering method [9]. Due to the theoretical limitations of the algorithms themselves, it is difficult to improve the forecasting accuracy using these forecasting approaches.…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2016

View full text Add to dashboard Cite

This paper proposes a new electric load forecasting model by hybridizing the fuzzy time series (FTS) and global harmony search algorithm (GHSA) with least squares support vector machines (LSSVM), namely GHSA-FTS-LSSVM model. Firstly, the fuzzy c-means clustering (FCS) algorithm is used to calculate the clustering center of each cluster. Secondly, the LSSVM is applied to model the resultant series, which is optimized by GHSA. Finally, a real-world example is adopted to test the performance of the proposed model. In this investigation, the proposed model is verified using experimental datasets from the Guangdong Province Industrial Development Database, and results are compared against autoregressive integrated moving average (ARIMA) model and other algorithms hybridized with LSSVM including genetic algorithm (GA), particle swarm optimization (PSO), harmony search, and so on. The forecasting results indicate that the proposed GHSA-FTS-LSSVM model effectively generates more accurate predictive results.

show abstract

Section: Introductionmentioning

confidence: 99%

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

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Reference [45] use such a way of modeling with two groups of public holidays, but the grouping itself is not reported. Also [46] …”

Section: Replacing Public Holiday Dummiesmentioning

confidence: 99%

Modeling public holidays in load forecasting: a German case study

Ziel

2018

J. Mod. Power Syst. Clean Energy

View full text Add to dashboard Cite

We address the issue of public or bank holidays in electricity load modeling and forecasting. Special characteristics of public holidays such as their classification into fixed-date and weekday holidays are discussed in detail. We present state-of-the-art techniques to deal with public holidays such as removing them from the data set, treating them as Sunday dummy or introducing separate holiday dummies. We analyze pros and cons of these approaches and provide a large load forecasting study for Germany that compares the techniques using standard performance and significance measures. Finally, we give general recommendations for the treatment of public holidays in energy forecasting to suggest how the drawbacks particular to most of the state-of-the-art methods can be mitigated. This is especially useful, as the incorporation of holiday effects can improve the forecasting accuracy during public holidays periods by more than 80%, but even for non-holidays periods, the forecasting error can be reduced by approximately 10%.

show abstract

“…In recent years, Generalized Additive Models (GAM) [17] have established themselves as state of the art tools for electricity load forecasting [15,5,26], due to the existence of efficient and scalable training algorithms and the interpretability of the model, which allows to clearly visualize the effect of individual variables on the load by means of simple longitudinal plots. Meanwhile, kernel methods have been employed with great success in the last decade.…”

Section: Introductionmentioning

confidence: 99%

Electricity Demand Forecasting by Multi-Task Learning

Fiot

Dinuzzo

2018

IEEE Trans. Smart Grid

View full text Add to dashboard Cite

We explore the application of kernel-based multi-task learning techniques to forecast the demand of electricity in multiple nodes of a distribution network. We show that recently developed output kernel learning techniques are particularly well suited to solve this problem, as they allow to flexibly model the complex seasonal effects that characterize electricity demand data, while learning and exploiting correlations between multiple demand profiles. We also demonstrate that kernels with a multiplicative structure yield superior predictive performance with respect to the widely adopted (generalized) additive models. Our study is based on residential and industrial smart meter data provided by the Irish Commission for Energy Regulation (CER).

show abstract

GEFCom2012: Electric load forecasting and backcasting with semi-parametric models

Cited by 76 publications

References 7 publications

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

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

Modeling public holidays in load forecasting: a German case study

Electricity Demand Forecasting by Multi-Task Learning

Contact Info

Product

Resources

About