How to Train Time Series Forecasting Faster Using Ray v1. Part 2 of 3.

Time Series Forecasting using Google’s Temporal Fusion Transformer LSTM version of RNN with PyTorch Forecasting and Torch Lightning

Displaying New York City Yellow Taxi ride volumes, with 1 week hourly forecast. Blue=observed, Orange=predicted, per validation dataset. Forecast generated using Google’s Temporal Fusion Transformer algorithm implemented by Pytorch forecasting, and parallelized by Ray for faster runtime, either on a laptop or on any cloud. Image by Author.

In Part 1, my previous blog explained how to apply the “ Embarrassingly Parallel “ pattern to speed up forecasting when each…