Energy Loss Impact in Electrical Smart Grid Systems in Australia

This research draws attention to the potential and contextual influences on energy loss in Australia’s electricity market and smart grid systems. It further examines barriers in the transition toward optimising the benefit opportunities between electricity demand and electricity supply. The main contribution of this study highlights the impact of individual end-users by controlling and automating individual home electricity profiles within the objective function set (AV) of optimum demand ranges. Three stages of analysis were accomplished to achieve this goal. Firstly, we focused on feasibility analysis using ‘weight of evidence’ (WOE) and ‘information value’ (IV) techniques to check sample data segmentation and possible variable reduction. Stage two of sensitivity analysis (SA) used a generalised reduced gradient algorithm (GRG) to detect and compare a nonlinear optimisation issue caused by end-user demand. Stage three of analysis used two methods adopted from the machine learning toolbox, piecewise linear distribution (PLD) and the empirical cumulative distribution function (ECDF), to test the normality of time series data and measure the discrepancy between them. It used PLD and ECDF to derive a nonparametric representation of the overall cumulative distribution function (CDF). These analytical methods were all found to be relevant and provided a clue to the sustainability approach. This study provides insights into the design of sustainable homes, which must go beyond the concept of increasing the capacity of renewable energy. In addition to this, this study examines the interplay between the variance estimation of the problematic levels and the perception of energy loss to introduce a novel realistic model of cost–benefit incentives. This optimisation goal contrasted with uncertainties that remain as to what constitutes the demand impact and individual house effects in diverse clustering patterns in a specific grid system. While ongoing effort is still needed to look for strategic solutions for this class of complex problems, this research shows significant contextual opportunities to manage the complexity of the problem according to the nature of the case, representing dense and significant changes in the situational complexity.