Deep Learning for Time Series Forecasting: The Electric Load Case

Gasparin, Alberto; Luković, Slobodan; Alippi, Cesare

doi:10.48550/arxiv.1907.09207

Cited by 6 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sequence to sequence models: The sequence to sequence (Seq2seq) architecture that originated in the field of natural language processing (NLP) has been applied in recent works to STLF. The authors in [47] apply different Seq2seq architectures, comparing them with other DL models based on recurrent and convolutional layers. The models are applied to two different datasets (scenarios): one for an individual household electric power consumption data set (IHEPC) located in Sceaux, France, and the other for the GEFCom2014 public dataset made available for the global energy forecasting competition 2014.…”

Section: Related Workmentioning

confidence: 99%

Novel Data-Driven Models Applied to Short-Term Electric Load Forecasting

et al. 2021

View full text Add to dashboard Cite

This work brings together and applies a large representation of the most novel forecasting techniques, with origins and applications in other fields, to the short-term electric load forecasting problem. We present a comparison study between different classic machine learning and deep learning techniques and recent methods for data-driven analysis of dynamical models (dynamic mode decomposition) and deep learning ensemble models applied to short-term load forecasting. This work explores the influence of critical parameters when performing time-series forecasting, such as rolling window length, k-step ahead forecast length, and number/nature of features used to characterize the information used as predictors. The deep learning architectures considered include 1D/2D convolutional and recurrent neural networks and their combination, Seq2seq with and without attention mechanisms, and recent ensemble models based on gradient boosting principles. Three groups of models stand out from the rest according to the forecast scenario: (a) deep learning ensemble models for average results, (b) simple linear regression and Seq2seq models for very short-term forecasts, and (c) combinations of convolutional/recurrent models and deep learning ensemble models for longer-term forecasts.

show abstract

Section: Related Workmentioning

confidence: 99%

Novel Data-Driven Models Applied to Short-Term Electric Load Forecasting

et al. 2021

View full text Add to dashboard Cite

show abstract

“…For sequence modeling problems, Seq2Seq (Sutskever et al, 2014) is the canonical deep learning framework and although applied this architecture to neural machine translation (NMT) tasks, it has since been adapted to time series forecasting (Nascimento et al, 2019;Yu et al, 2017;Gasparin et al, 2019;Mukhoty et al, 2019;Wen et al, 2017;Salinas et al, 2020;Wen and Torkkola, 2019). The MQ-Forecaster framework (Wen et al, 2017) solves (1) above by treating each series i as a sample from a joint stochastic process and feeding into a neural network which predicts Q quantiles for each horizon.…”

Section: Time Series Forecastingmentioning

confidence: 99%

“…Recent work applying deep learning to time-series forecasting focuses primarily on the use of recurrent and convolutional architectures (Nascimento et al, 2019;Yu et al, 2017;Gasparin et al, 2019;Mukhoty et al, 2019;Wen et al, 2017) 1 . These are Seq2Seq architectures (Sutskever et al, 2014) -which consist of an encoder which takes an input sequence and summarizes it into a fixed-length context vector, and a decoder which produces an output sequence.…”

Section: Introductionmentioning

confidence: 99%

MQTransformer: Multi-Horizon Forecasts with Context Dependent and Feedback-Aware Attention

Eisenach¹,

Patel²,

Madeka³

2020

Preprint

View full text Add to dashboard Cite

Recent advances in neural forecasting have produced major improvements in accuracy for probabilistic demand prediction. In this work, we propose novel improvements to the current state of the art by incorporating changes inspired by recent advances in Transformer architectures for Natural Language Processing. We develop a novel decoder-encoder attention for contextalignment, improving forecasting accuracy by allowing the network to study its own history based on the context for which it is producing a forecast. We also present a novel positional encoding that allows the neural network to learn context-dependent seasonality functions as well as arbitrary holiday distances. Finally we show that the current state of the art MQ-Forecaster (Wen et al., 2017) models display excess variability by failing to leverage previous errors in the forecast to improve accuracy. We propose a novel decoder-self attention scheme for forecasting that produces significant improvements in the excess variation of the forecast.

show abstract

“…In some application areas, these models achieve better than human level performance, such as object recognition [18,44], object detection [26,16], object tracking [23]) or games (e.g. beating AlphaGo champion [39])), predictions [24], forecasting [12,11] and health [25].…”

Section: Introductionmentioning

confidence: 99%

Explaining Deep Learning Models for Tabular Data Using Layer-Wise Relevance Propagation

et al. 2021

View full text Add to dashboard Cite

Trust and credibility in machine learning models are bolstered by the ability of a model to explain its decisions. While explainability of deep learning models is a well-known challenge, a further challenge is clarity of the explanation itself for relevant stakeholders of the model. Layer-wise Relevance Propagation (LRP), an established explainability technique developed for deep models in computer vision, provides intuitive human-readable heat maps of input images. We present the novel application of LRP with tabular datasets containing mixed data (categorical and numerical) using a deep neural network (1D-CNN), for Credit Card Fraud detection and Telecom Customer Churn prediction use cases. We show how LRP is more effective than traditional explainability concepts of Local Interpretable Model-agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP) for explainability. This effectiveness is both local to a sample level and holistic over the whole testing set. We also discuss the significant computational time advantage of LRP (1–2 s) over LIME (22 s) and SHAP (108 s) on the same laptop, and thus its potential for real time application scenarios. In addition, our validation of LRP has highlighted features for enhancing model performance, thus opening up a new area of research of using XAI as an approach for feature subset selection.

show abstract

Deep Learning for Time Series Forecasting: The Electric Load Case

Cited by 6 publications

References 0 publications

Novel Data-Driven Models Applied to Short-Term Electric Load Forecasting

Novel Data-Driven Models Applied to Short-Term Electric Load Forecasting

MQTransformer: Multi-Horizon Forecasts with Context Dependent and Feedback-Aware Attention

Explaining Deep Learning Models for Tabular Data Using Layer-Wise Relevance Propagation

Contact Info

Product

Resources

About