Year: 2025
Type: article
Abstract: As global energy consumption continues to rise, the demand for intelligent systems that can accurately forecast usage and suggest optimization strategies has become increasingly urgent. This research presents a novel AI-based framework that integrates Long Short-Term Memory (LSTM) networks for time series forecasting with K-Means clustering to analyze usage patterns. The proposed model processes historical energy data, predicts future consumption, and generates actionable recommendations tailored to specific user behaviors. Through effective preprocessing, deep learning modeling, and unsupervised pattern recognition, the system achieves high forecasting accuracy and enables personalized energy optimization strategies. The implementation is evaluated using real-world energy consumption data, and the results show the system’s potential for integration into smart grid and building management platforms, thereby proving their worth to sustainable energy practices. Keywords: Energy Optimization, Smart Buildings, LSTM, KMeans Clustering, AI, Forecasting, Deep Learning
DOI: 10.55041/ijsrem47702
Author: Swastik Arora
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4410380784