IoT and LSTM-MLP Integration for Efficient Waste-to-Energy Power Generation in Smart Cities

Waste-to-energy power generation plays a vital role in the advancement of sustainable smart cities. Nevertheless, current models sometimes struggle to efficiently include the vast quantities of Internet of Things (IoT) data necessary for precise energy forecasts. This study aims to overcome the difficulty by suggesting a hybrid model that integrates LSTM and MLP neural networks in order to improve forecast precision. The LSTM component is utilized to capture temporal relationships in sequential IoT data, while the MLP layers carry out intricate feature extraction. The system under consideration was assessed using a dataset obtained from Kaggle, demonstrating exceptional performance with an accuracy rate of 97.6%, a recall rate of 96.8%, and an F1-score of 97.5%. Our technique demonstrated a substantial enhancement in all indicators when compared to traditional approaches. The results indicate that combining IoT with sophisticated neural networks might enhance waste-to-energy operations, hence improving the efficiency and dependability of energy management in smart cities. The exceptional performance of the suggested model renders it a highly attractive alternative for real-time implementation, providing significant environmental and operational advantages compared to current approaches.