Time Series Forecasting: Household Electric Power Consumption Author: Arash Sadeghzadeh
The data for this norebook can be retrieved from the following URL:
https://www.kaggle.com/datasets/uciml/electric-power-consumption-data-set
In this notebook, we consider the problem of time series forecasting using DNN, LSTM, and LSTM with CONV1D. The developed methods are evaluated using Household Electric Power Consumption dataset from Kaggle. The dataset comprises the measurements of electric power consumption in one household with a one-minute sampling rate over a period of almost 4 years.
Table of Contents
Data Exploration
Helper Functions
Prepare Train and Validation Dataset
DNN Time Series Forecasting Model
Choose Learning Rate
Train NN
LSTM Time Series Forecasting Model
LSTM-Conv1D Time Series Forecasting Model