• Tayyaba Tabassum
• Mohammed Immad Hussain
• Arbaaz Khan
• Mohammed Nawaz B
• Mirza Mudassir Baig

This project focuses on developing a Long Short-Term Memory (LSTM) neural network to predict power consumption based on historical time series data. The accurate prediction of power consumption is crucial for efficient energy management, grid stability, and cost reduction. Traditional methods like ARIMA and exponential smoothing often fail to capture the nonlinear patterns in power consumption data. LSTM, a type of recurrent neural network (RNN), is well-suited for time series forecasting because it can learn long-term dependencies and patterns. This project leverages LSTM's capabilities to build a model that forecasts future power consumption based on past data, with the goal of providing utility companies and consumers with actionable insights for better energy planning.

**Keywords:** Long Short-Term Memory (LSTM), Power Consumption Prediction, Time Series Forecasting, Recurrent Neural Network (RNN), ARIMA, Exponential Smoothing, Energy Management, Grid Stability, Historical Data, Nonlinear Patterns, Deep Learning, Feature Engineering, Normalization, RMSE, MAPE, Hyperparameter Tuning, TensorFlow, PyTorch, Data Preprocessing, Real-Time Forecasting, Attention Mechanisms, Vanishing Gradient Problem, Holt-Winters, Kalman Filters, Residual Analysis, Energy Distribution, Cost Reduction.

"Electricity Power Consumption Using LSTM With Attention Mechanism", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.i239-i245, May-2025, Available :http://www.jetir.org/papers/JETIR2505923.pdf

"Electricity Power Consumption Using LSTM With Attention Mechanism", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. ppi239-i245, May-2025, Available at : http://www.jetir.org/papers/JETIR2505923.pdf