A Prepaid Energy Billing System with Credit Shortage Forecasting


Abdul Ghani, M. F. F. and Mohd Yusoff, M. A. F. and Wong, Hwee Ling and Yip, Sook Chin and Tan, C. K. (2022) A Prepaid Energy Billing System with Credit Shortage Forecasting. Lecture Notes in Electrical Engineering, 835. pp. 299-311. ISSN 1876-1100

Full text not available from this repository.


Climate change due to greenhouse gases emission is causing adverse effects to the environment. Electricity production is one of the major causes and a large amount of electricity originates from fossil fuels. To mitigate this risk, countries are converging towards using renewable energy. However, battery storage technology still lags the advancement of energy production. Thus, some electricity produced from renewable energy resources in a local grid could be dissipated. An online-based prepaid energy billing system is proposed to enable a platform to support a marketplace for the local power generation. This allows excessive electricity produced to be traded. The system enables end users to switch electricity providers, monitor energy consumption and plan their usage. Users can choose to be connected to either a large-scale utility provider via postpaid electricity or a trading point for renewable energy through a prepaid scheme. Forecasting models and algorithms to predict the shortage of prepaid credit for individual households were evaluated for the system. The Multivariate Convolutional Long Short-Term Memory (ConvLSTM) yielded the best result with an average Mean Absolute Percentage Error (MAPE) of 25.8%. Energy consumption, temperature and humidity were the parameters used in training the model. The NodeMCU board serves as the main controller for the system. It also serves as a gateway to allow users to communicate wirelessly through a mobile app developed using the MIT App Inventor.

Item Type: Article
Uncontrolled Keywords: Electricity, Load forecasting, Neural network
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75-76.95 Calculating machines
Divisions: Faculty of Engineering (FOE)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 05 Aug 2022 07:31
Last Modified: 05 Aug 2022 07:31
URII: http://shdl.mmu.edu.my/id/eprint/10188


Downloads per month over past year

View ItemEdit (login required)