An Efficient Decision Support System for IoT-based smart meters with AI and Big data

Abstract

Translate Article

Abstract AIBTBF (Artificial Intelligence and Big data Techniques Based Framework) is a framework designed to enhance the DSS (Decision Support System) of MDAS (Metering Data Acquisition System) in electricity consumption for improved energy efficiency. The core processes of the Revenue Management System (RMS) i.e., Metering, Billing, and collection (Mare) are addressed in the context of the Electricity Consumption. This paper proposed an efficient framework after reviewing & analyzing various methods in practice along with their impacts on electricity consumption. The framework integrates Information Technology (IT) with Operation Technology (OT) of the electrical system to handle the challenges of high volume of data that needs velocity in processing and accumulated variety of data in structured, semi-structured, and unstructured variables. The proposed framework implemented big data analytics and artificial intelligence to enhance the decision support system with real-time accurate and effective decisions. The direct variables for energy efficiency i.e. billing efficiency and collection efficiency are minutely studied in context with IoT techniques. Key indicators for energy efficiency and demand management are also studied to achieve the primary goals of the distribution companies to provide quality supply 24X7 to their valued consumers. It introduces novel methodologies by integrating external factors like weather conditions, seasonal and geographical diversity and socio-economic indicators into predictive models, thereby addressing gaps in traditional forecasting approaches. The framework is structured into four key parts: Extraction & Preparation, Transformation, Analysis, and Suggestions & Recommendations Generation. The paper analyzes the current emerging techniques with limitations and suggested recommendations for best use case scenarios in the prediction and optimization of the existing business process. The contributions of the framework include Efficient data management and processing from diverse sources. Advanced analysis using deep learning algorithms for forecasting and optimization. Real-time decision support for energy management and operational efficiency. Reduction of commercial and technical losses in power distribution. Similarly, the proposed framework uses MapReduce and Parallelization packages. The data is stored at the data lake on HDFS. The framework is evaluated through a series of practical case studies and performance metrics, demonstrating its effectiveness in improving energy management and operational processes. AIBTBF framework not only meets the primary goals of reducing technical and commercial losses but also provides a scalable solution for modernizing legacy systems in power distribution.