Bi-level decision tree-based smart electricity analysis framework for sustainable city

Abstract

The revolutionizing influence of the Internet of Things (IoT) paradigm has greatly enhanced the service-delivery aspects of electricity consumption, allowing for smart energy distribution and trustworthy electric appliances. The current research presents a novel technique for detecting electricity usage in smart homes using IoT technology. Poor electricity distribution has greatly impacted daily life along with inefficient power resource allocation. This research assesses the spatial–temporal efficiency with which power grid operators distribute electrical energy resources. The efficient distribution of energy resources is achieved by calculating the spatial–temporal utilization measure for each residence of a geographical region. Also, to help power grid managers optimize the spatial–temporal allocation of energy resources, a two-level threshold-based decision-tree model is presented. For performance assessment, four smart homes are tracked for 2 months in a simulated environment. Statistical results acquired for Delay (119.61s), Reliability (82.23%), Stability (71.12%), Classification Effectiveness (Precision (95.56%), Sensitivity (95.96%), and Specificity (95.25%)), and Decision-making Efficiency (92.21%) show that the presented approach significantly outperforms state-of-the-art data analysis techniques.