Open Access
ANN Based Model for Prediction of Energy Requirement for Water-Energy Nexus Studies
Author(s) -
S. Chandrasekaran,
Balakrishnan Baranitharan,
Rajesh Krishnasamy
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/955/1/012067
Subject(s) - energy (signal processing) , nexus (standard) , artificial neural network , water energy nexus , computer science , work (physics) , water resources , engineering , artificial intelligence , statistics , mathematics , mechanical engineering , ecology , biology , embedded system
Water and energy are intricately connected. In order to have systematic planning of water resources to meet the future energy demands in a region, it is necessary to forecast the energy requirements appropriately. This work proposes development of an effective forecasting model. At the first level, forecasting of energy requirement is done with energy availability as the input information. At the second level, it is desired to forecast the energy requirement with weather parameters such as temperature and rainfall as the inputs. The variation in these parameters has a significant influence on the energy requirements. The proposed models are developed for 2 States in India with monthly data on energy requirement, energy availability and weather parameters for 11 years. Artificial Neural Network (ANN) is used as the forecasting tool because of its wide usage and acceptability by various researchers as an effective modelling tool and is implemented using MATLAB platform in this study. The results indicate that the propose ANN models are able to predict the energy requirements for two states with a CC of about 0.70, but fails to predict the peak, which needs further investigations. The importance of considering weather parameter changes as important source of information for planning water and energy related studies is found to be necessary.