Article

1. Volume : 2
2. Issue : 1
3. Month : January - March (2025)

Smart Electricity Price Predection using a Deep Learning

Author : Kotamsetty Geethika Devi

Electricity price prediction plays a crucial role in energy markets, where accurate forecasts can help stakeholders optimize decision-making, reduce operational costs, and enhance market efficiency. Traditional forecasting models often fall short when faced with the complex, nonlinear nature of electricity price fluctuations. This study proposes a hybrid deep learning model combining ALEXNET and LSTM for accurate electricity price prediction. ALEXNET, a convolutional neural network, is used for feature extraction from historical price data, while LSTM captures the temporal dependencies in the price fluctuations. The integration of these models allows for effective learning of both spatial and sequential patterns, improving forecasting accuracy. Experimental results show that the hybrid approach outperforms traditional and standalone LSTM models, offering a promising solution for electricity price prediction. This method provides a more robust framework for optimizing energy market strategies and enhancing forecasting reliability. The model is built on the past data, which has been supplied with the most significant elements like demand, temperature, sunlight, and rain. The proposed model applies to analysis on exact minimum-maximum scaling and a time window to predict the electricity prices for the upcoming too. Based on analysis and computational analysis to simulate the results, it gives far better than the traditional way for an exact accuracy rating of 97.08 calculations with comparison to earlier RNN and ANN calculations with accuracies of 96.64 % and 96.63% respectively. This research work is useful for smart Cities and Smart Villages too operational modes.