Architectural Design of Electricity Power Consumption Misuse Detection Based on Light Gradient Boosting Machine Using Blockchain Technology

This research focuses on blockchain architecture design for Electricity misuse detection is a critical concern in contemporary energy management systems. Detecting and preventing unauthorized or improper usage poses a significant challenge due to the complex and diverse nature of energy consumption data. This research focuses on improving the accuracy of electricity misuse detection through the utilization of the LightGBM classification model in machine learning. Light Gradient Boosting Machine (LightGBM) methods are employed due to their efficiency, accuracy, and ability to handle imbalanced datasets. Evaluation metrics, such as accuracy and AUC (Area Under the Curve), are used to assess the performance of the model. The results demonstrate that the LightGBM classifier exhibits superior performance in accurately detecting instances of electricity misuse. It achieves an impressive accuracy of 84.19 % indicating its effectiveness in identifying and flagging electricity misuse events. By leveraging LightBGM algorithms, valuable insights can be obtained for energy management and decision-making processes, aiding in the improvement of strategies and overall performance. This analysis also identifies the key factors influencing electricity misuse. Block chain to assist both energy providers and policymakers in developing effective measures to curb such instances in a decentralized manner so that security is guaranteed.