Potential of three variant machine-learning models for forecasting district level medium-term and long-term energy demand in smart grid environment

Tanveer Ahmad and Huanxin Chen

Energy, 2018, vol. 160, issue C, 1008-1020

Abstract: Medium-term and long-term energy prediction is essential for the planning and operations of the smart grid eco-system. The prediction of next year and next month energy demand of grid station, independent power producers, commercial, domestic and industrial consumers are allowed administrators to optimize and plan their resources. To address the forecasting problems, the basic intention of this study is to propose an accurate and precise medium and long-term district level energy prediction models employing the machine learning based models which are: 1) artificial neural network with nonlinear autoregressive exogenous multivariable inputs model; 2) multivariate linear regression model; and 3) adaptive boosting model. Based on environmental and aggregated energy consumption data as the model's input and output, the load prediction interval is further classified into three main parts, 1-month ahead forecasting, seasonally ahead forecasting and 1-year ahead forecasting. Feature extraction, data transformation and outlier detection are performed through different data tests. The prediction results intimate that the intended models cannot only increase the forecasting accuracy contrasted with previous forecasting models but also produce adequate forecasting intervals in the smart grid environment. Additionally, these techniques describe an essential step-forward, consolidating the spatiotemporal use of energy inconstancies and variations of district level and strong forecasting capabilities of energy usage requirement in future perceptive.

Keywords: ANN-NAEMI; MLRM; AdaBoost; Energy prediction; Machine learning models (search for similar items in EconPapers)
Date: 2018
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (16)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544218313811
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:160:y:2018:i:c:p:1008-1020

DOI: 10.1016/j.energy.2018.07.084

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().