Introducing AI-Driven IoT Energy Management Framework
Shivani Mruthyunjaya, Anandi Dutta, Kazi Sifatul Islam
TL;DR
The paper addresses IoT-driven energy management by integrating long-term and short-term power forecasting, anomaly detection, and qualitative contextual integration into a unified framework. It implements LSTM for long-horizon forecasts, SVR for short-horizon predictions, and k-NN for anomaly detection, with a theoretical decision-tree contextual module, evaluated on a high-resolution Kaggle power dataset. Results show strong short-term accuracy and reasonable long-term forecasting, plus detectable anomalies, demonstrating the framework's feasibility for proactive, scalable energy management in smart grids. The work provides a foundation for standardized, connected IoT energy systems aimed at reducing consumption and improving grid reliability.
Abstract
Power consumption has become a critical aspect of modern life due to the consistent reliance on technological advancements. Reducing power consumption or following power usage predictions can lead to lower monthly costs and improved electrical reliability. The proposal of a holistic framework to establish a foundation for IoT systems with a focus on contextual decision making, proactive adaptation, and scalable structure. A structured process for IoT systems with accuracy and interconnected development would support reducing power consumption and support grid stability. This study presents the feasibility of this proposal through the application of each aspect of the framework. This system would have long term forecasting, short term forecasting, anomaly detection, and consideration of qualitative data with any energy management decisions taken. Performance was evaluated on Power Consumption Time Series data to display the direct application of the framework.