A novel error-output recurrent neural network model for time series forecasting

Waheeb, Waddah; Ghazali, Rozaida

doi:10.1007/s00521-019-04474-5

Cited by 31 publications

(7 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, deep learning techniques are acquiring a great relevance nowadays to solve a large number of applications in multiple areas due to the enhancements in computational capabilities [ 33 , 40 , 41 ]. In particular, specific deep learning models such as Long Short-Term Memory (LSTM) networks have shown its effectiveness to deal with time series [ 11 , 37 , 42 ].…”

Section: Introductionmentioning

confidence: 99%

A deep LSTM network for the Spanish electricity consumption forecasting

Torres

Martínez‐Álvarez

Troncoso

2022

Neural Comput & Applic

View full text Add to dashboard Cite

Nowadays, electricity is a basic commodity necessary for the well-being of any modern society. Due to the growth in electricity consumption in recent years, mainly in large cities, electricity forecasting is key to the management of an efficient, sustainable and safe smart grid for the consumer. In this work, a deep neural network is proposed to address the electricity consumption forecasting in the short-term, namely, a long short-term memory (LSTM) network due to its ability to deal with sequential data such as time-series data. First, the optimal values for certain hyper-parameters have been obtained by a random search and a metaheuristic, called coronavirus optimization algorithm (CVOA), based on the propagation of the SARS-Cov-2 virus. Then, the optimal LSTM has been applied to predict the electricity demand with 4-h forecast horizon. Results using Spanish electricity data during nine years and half measured with 10-min frequency are presented and discussed. Finally, the performance of the proposed LSTM using random search and the LSTM using CVOA is compared, on the one hand, with that of recently published deep neural networks (such as a deep feed-forward neural network optimized with a grid search) and temporal fusion transformers optimized with a sampling algorithm, and, on the other hand, with traditional machine learning techniques, such as a linear regression, decision trees and tree-based ensemble techniques (gradient-boosted trees and random forest), achieving the smallest prediction error below 1.5%.

show abstract

Section: Introductionmentioning

confidence: 99%

A deep LSTM network for the Spanish electricity consumption forecasting

Torres

Martínez‐Álvarez

Troncoso

2022

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…Non-linear methods can be used to address many issues as powerful predictive tools. Neural Networks (NN) are one method of modeling nonlinear (accommodating multivariate) and nonparametric data with a model-free estimation (Harahap and Lubis, 2018;Waheeb and Ghazali, 2019). Exploratory research on artificial intelligence has revealed that little has been done on oil palm yield (Khamis et al, 2006;Zuhaimy and Azme, 2011).…”

Section: Introductionmentioning

confidence: 99%

Neural Networks Method in Predicting Oil Palm FFB Yields for the Peninsular States of Malaysia

Hilal¹

2020

JOPR

View full text Add to dashboard Cite

Reliable and accurate predictions in oil palm production can provide the basis for management decisions of budgeting, storage, distribution, and marketing. Artificial Neural Network (ANN) and Non-linear Autoregressive Exogenous Neural Network (NARX) models were developed based on 19 440 data set of 15 inputs variables, namely, percentage of mature area and percentage of immature area, rainfall, rainy days, humidity, radiation, temperature, surface wind speed, evaporation and cloud cover, ozone (O 3), carbon monoxide (CO), nitrogen dioxide (NO 2), sulphur dioxide (SO 2), and particulate matter of less than 10 microns in size (PM 10) for predicting oil palm fresh fruit bunch (FFB). The results were validated with an independent validation dataset. Results showed that NARX models performed more accurately with multiple coefficients of determination (R 2) reached 97% and mean square errors (MSE) between 0.0104%-0.0665%, besides being an easy-to-use tool. Generally, NARX models proved to give more accurate predictions than the predictions of common ANN and Multi Linear Regression (MLR) models. Finally, 15-10-4-1 is chosen as the architecture of NARX for the states of Kedah,

show abstract

“…The difference between RNN and LSTM [13] is that RNN is used in places where the retention of memory is short, whereas LSTM is capable of connecting events that happened way earlier and the events that followed them. LSTM [14] may be one of the best choices for analysing and predicting temporal-dependent phenomena that span over a long period or multiple instances in the past. In LSTM, each node is used as a memory cell that can store other information in contrast to simple neural networks, where each node is a single activation function.…”

mentioning

confidence: 99%

Day-ahead Electricity Price Forecasting using Long-short Term Memory Recurrent Neural Network

Popovska¹,

Georgieva-Tsaneva²

2022

STEM

View full text Add to dashboard Cite

The availability of accurate day-ahead electricity price forecasts is very important for electricity market participants and it is an essential challenge to accurately forecast the electricity price. Therefore, this study proposes an efficient method suitable for electricity price forecasting (EPF) and processing time-series data from the Bulgarian day-ahead market based on a long-short term memory (LSTM) recurrent neural network model. The LSTM model is used to forecast the day-ahead electricity price for the Bulgarian day-ahead market. As inputs to the model are used historical hourly prices for the period between 20.01.2016 and 05.03.2022. The output is the electricity price forecasts for hours and days ahead. The future values of prices are forecasted recursively. LSTM can model temporal dependencies in larger Time Series set horizons without forgetting the short-term patterns. LSTM networks are composed of units that are called LSTM memory cells and these cells contain some gates that process the inputs. Since electricity price is affected by various seasonal effects, the model is trained for several years. The effectiveness of the proposed method is verified using real market data.

show abstract

A novel error-output recurrent neural network model for time series forecasting

Cited by 31 publications

References 79 publications

A deep LSTM network for the Spanish electricity consumption forecasting

A deep LSTM network for the Spanish electricity consumption forecasting

Neural Networks Method in Predicting Oil Palm FFB Yields for the Peninsular States of Malaysia

Day-ahead Electricity Price Forecasting using Long-short Term Memory Recurrent Neural Network

Contact Info

Product

Resources

About