Chan-dre-yi / POWER-CAST

This project is a time series forecasting model using the Temporal Fusion Transformer (TFT) deep learning architecture. The model is trained and evaluated on the M4 competition dataset, achieving state-of-the-art results in multi-step forecasting tasks.

PowerCast: Energy Demand Forecast using Temporal Fusion Transformer

This project implements a deep learning model called the Temporal Fusion Transformer (TFT) for time series forecasting. The TFT model is a powerful architecture that combines the strengths of both transformers and RNNs to capture long-term dependencies and seasonal patterns in time series data. This project includes data preprocessing, model training, and hyperparameter tuning steps, and provides a comprehensive description on how to use the TFT model for time series forecasting.

It is my 8th sem Science Engineering and Technology Project. Feel free to check it out!