Predicting Electricity Bill Prices using LSTM and IoT based Sensor Data

Accurate prediction of electricity bill prices is essential for both consumers and utility providers to manage energy consumption and costs effectively. This research paper presents an innovative approach to forecast electricity bill prices using data collected directly from sensors. These sensors include SCT-013-000 for current measurement and ZMPT101B for voltage measurement, providing real-time, high-resolution data critical for precise consumption analysis. The model employs Long Short-Term Memory (LSTM) networks for temporal sequence learning, handling the time-dependent nature of electricity consumption patterns. Our methodology includes deploying these sensors in a smart home environment to gather continuous data, transmitted through an Internet of Things (IoT) network to a centralized server for processing. After preprocessing and normalization, the data is fed into the LSTM model, trained and validated using historical electricity usage and billing information. Experimental results demonstrate that our approach outperforms traditional machine learning models in terms of prediction accuracy and reliability. The integration of IoT-enabled SCT-013- 000 and ZMPT101B sensors enhances data granularity and facilitates real-time monitoring and prediction capabilities, significantly benefiting consumers and utility providers by providing insights into future electricity bills, allowing proactive adjustments in usage patterns and optimizing grid operations and dynamic pricing strategies.