Analysis Affect Factors of Smart Meter A PLS-SEM Neural Network

Abstract

Smart electricity meters measure, control, analyze, and predict the amount of electricity used. Do the same for water and gas power. Automatically svae this monitoring data to the energy provider, for billing and tracking services. In developed countries, there has not been a consensus to accept the use of smart electricity meters, in addition to the benefits mentioned above, there are many possible risks when using smart meters. This paper examines information technology system (IS) related factors and engineering model related factors following technical readiness such as optimism, innovation insecurity, and discomfort. Accompanying that is the expectation of a smart meter, for the Vietnamese people’s intention to continuously use smart meters. The oriented approach is applied to evaluate the intention model of continuous use of smart meters, through the survey results of 500 answer samples of Vietnamese people. We propose to use a 2-layer research model to analyze the results of the user survey about the smart meter system. Most of the previous studies on smart meter systems focused on analyzing the impact of factors affecting applications, using single-step Structure Equation Modeling (SEM). The purpose of this study based on the Technology Acceptance Method (TAM) theory, describes the Artificial Neural Network (ANN) method to perform indepth analysis, yielding more accurate results than the SEM model. The study measures the relationship between the readiness for new technologies (optimision, innovation, discomfort, and insecurity). Technology acceptance (Perceived ease of use, Perceived usefulness). Expectations confirmed and Information systems acceptance (service quality, system quality, and information quality). This paper outlines the research model of the multi-analysis approach by combining Partial Least Squares Structure Equation Modeling (PLS-SEM) and Artificial Neural Network (ANN) analysis. First, the PLS-SEM model evaluates the factors affecting the intention to use the smart meter system. Second, ANN ranks the impact factors of important predictors from the PLS-SEM model. The findings from the PLS-SEM and ANN approach research model confirm the results obtained from PLS-SEM by ANN. In addition, ANN performs linear and non-linear relational modeling with high prediction accuracy compared with the SEM model. In addition, an Importance Performance Map Analysis (IPMA) analyzes the results accurately for factors’ important performance.