Energy pricing optimization by using Neural Network (NN) for demand site tariff strategy: Peninsular Malaysia case study

Abu Hanipah, Siti Aishah (2016) Energy pricing optimization by using Neural Network (NN) for demand site tariff strategy: Peninsular Malaysia case study. Project Report. Universiti Teknikal Malaysia Melaka, Melaka, Malaysia. (Submitted)

Preview

Text (Full Text) Energy pricing optimization by using Neural Network (NN) for demand site tariff strategy Peninsular Malaysia case study.pdf - Submitted Version Download (1MB) | Preview

Abstract

In regards to Malaysia environment, the demand of electricity is affected and rapidly rising as the population of human being is increasing and industries that fast developed. Due to this constrain, Tenaga Nasional Berhad (TNB) has introduced Enhance Time of Use (ETOU) tariff in planning to replace Time of Use (TOU) tariff for demand side benefits. Unsuitable tariff with load profile will give the big impact to demand side pricing. The objectives of this project are to model the equation of TOU and ETOU for optimum industrial demand-site tariff selection, analyze the best potential energy profile for ETOU tariff via Neural Network (NN) and compare the cost saving for optimal load profile with TOU and ETOU tariff. The demand side pricing optimization will be conduct via forecasting the energy profile for suitable tariff selection that correlate to the peninsular Malaysia energy scenario. Neural Networks method will be implement in order to validate the proposed model. Energy profiles of industry sector will be used as case study environment in order to determine the demand side pricing patent. It is hoped that, the result of this project will benefit the energy authority and consumers of the electricity energy in the future action respectively.

Actions (login required)

View Item