Deep Learning for Time Series Forecasting: The Electric Load Case (2019-07-22T00:00:00.000000Z)

TL;DR

This work focuses on feedforward and recurrent neural networks, sequence to sequence models and temporal convolutional neural networks along with architectural variants, which are known in the signal processing community but are novel to the load forecasting one.

Abstract

Management and efficient operations in critical infrastructure such as Smart Grids take huge advantage of accurate power load forecasting which, due to its nonlinear nature, remains a challenging task. Recently, deep learning has emerged in the machine learning field achieving impressive performance in a vast range of tasks, from image classification to machine translation. Applications of deep learning models to the electric load forecasting problem are gaining interest among researchers as well as the industry, but a comprehensive and sound comparison among different architectures is not yet available in the literature. This work aims at filling the gap by reviewing and experimentally evaluating on two real-world datasets the most recent trends in electric load forecasting, by contrasting deep learning architectures on short term forecast (one day ahead prediction). Specifically, we focus on feedforward and recurrent neural networks, sequence to sequence models and temporal convolutional neural networks along with architectural variants, which are known in the signal processing community but are novel to the load forecasting one.

Authors

C. Alippi

5 papers

Alberto Gasparin

1 papers

S. Lukovic

1 papers

TL;DR

Abstract

Authors

References98 items

Short-Term Load Forecasting Using Encoder-Decoder WaveNet: Application to the French Grid

Deep-Learning Forecasting Method for Electric Power Load via Attention-Based Encoder-Decoder with Bayesian Optimization

Deep Learning for Load Forecasting: Sequence to Sequence Recurrent Neural Networks With Attention

Forecasting Building Energy Consumption with Deep Learning: A Sequence to Sequence Approach

Probabilistic Forecasting with Temporal Convolutional Neural Network

Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network

A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural Network

Combining auto-regression with exogenous variables in sequence-to-sequence recurrent neural networks for short-term load forecasting

Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches †

Short-Term Load Forecasting With Deep Residual Networks

Deep Reinforcement Learning for Sequence-to-Sequence Models

Short-Term Load Forecasting with Multi-Source Data Using Gated Recurrent Unit Neural Networks

An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling

A High Precision Artificial Neural Networks Model for Short-Term Energy Load Forecasting

A Review of Deep Learning Methods Applied on Load Forecasting

PowerLSTM: Power Demand Forecasting Using Long Short-Term Memory Neural Network

Deep neural networks for energy load forecasting

Recurrent Neural Networks for Short-Term Load Forecasting

Convolutional Sequence to Sequence Learning

Conditional Time Series Forecasting with Convolutional Neural Networks

Comparative Study of CNN and RNN for Natural Language Processing

Pixel Recursive Super Resolution

Demystifying ResNet

Building energy load forecasting using Deep Neural Networks

Professor Forcing: A New Algorithm for Training Recurrent Networks

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

WaveNet: A Generative Model for Raw Audio

Probabilistic energy forecasting: Global Energy Forecasting Competition 2014 and beyond

Deep learning for estimating building energy consumption

A guide to convolution arithmetic for deep learning

Deep Residual Learning for Image Recognition

Sequence Level Training with Recurrent Neural Networks

Short-Term Electric Load Forecasting Using Echo State Networks and PCA Decomposition

End-to-end attention-based large vocabulary speech recognition

Attention-Based Models for Speech Recognition

Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks

Spatial Transformer Networks

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Fast R-CNN

LSTM: A Search Space Odyssey

Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Adam: A Method for Stochastic Optimization

Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

Going deeper with convolutions

Sequence to Sequence Learning with Neural Networks

Very Deep Convolutional Networks for Large-Scale Image Recognition

Neural Machine Translation by Jointly Learning to Align and Translate

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

Global Energy Forecasting Competition 2012

How to Construct Deep Recurrent Neural Networks

Residential electrical demand forecasting in very small scale: An evaluation of forecasting methods

Speech recognition with deep recurrent neural networks

ADADELTA: An Adaptive Learning Rate Method

ImageNet classification with deep convolutional neural networks

On the difficulty of training recurrent neural networks

A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition

A methodology for Electric Power Load Forecasting

Building-level occupancy data to improve ARIMA-based electricity use forecasts

Electricity Short Term Load Forecasting Using Elman Recurrent Neural Network

Long-term prediction of time series by combining direct and MIMO strategies

A particle swarm optimization to identifying the ARMAX model for short-term load forecasting

Short-term load forecasting via ARMA model identification including non-Gaussian process considerations

Neural networks for short-term load forecasting: a review and evaluation

Short-term load forecasting with local ANN predictors

Long Short-Term Memory

Analysis of an adaptive time-series autoregressive moving-average (ARMA) model for short-term load forecasting

Identification of ARMAX model for short term load forecasting: an evolutionary programming approach

Learning long-term dependencies with gradient descent is difficult

Weather sensitive short-term load forecasting using nonfully connected artificial neural network

Learning Complex, Extended Sequences Using the Principle of History Compression

Short-term load forecasting using an artificial neural network

Electric load forecasting using an artificial neural network

An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories

Backpropagation Through Time: What It Does and How to Do It