Electricity demand forecasting with hybrid classical statistical and machine learning algorithms: Case study of Ukraine DOI Creative Commons
Tatiana González Grandón, Johannes Schwenzer, Thomas Steens

et al.

Applied Energy, Journal Year: 2023, Volume and Issue: 355, P. 122249 - 122249

Published: Nov. 10, 2023

This article presents a novel hybrid approach using classic statistics and machine learning to forecast the national demand of electricity. As investment operation future energy systems require long-term electricity forecasts with hourly resolution, our mathematical model fills gap in forecasting. The proposed methodology was constructed data from Ukraine's consumption ranging 2013 2020. To this end, we analysed underlying structure hourly, daily yearly time series consumption. trend is evaluated macroeconomic regression analysis. mid-term integrates temperature calendar regressors describe structure, combines ARIMA LSTM "black-box" pattern-based approaches error term. short-term captures seasonality through multiple ARMA models for residual. Results show that best forecasting composed by combining residual prediction. Our very effective at on an resolution. In two years out-of-sample 17520 timesteps, it shown be within 96.83% accuracy.

Language: Английский

Wind power forecasting – A data-driven method along with gated recurrent neural network DOI

Adam Kisvari,

Zi Lin, Xiaolei Liu

et al.

Renewable Energy, Journal Year: 2020, Volume and Issue: 163, P. 1895 - 1909

Published: Oct. 28, 2020

Language: Английский

Citations

282
Photovoltaic power forecasting based on GA improved Bi-LSTM in microgrid without meteorological information DOI

Zhen Hao,

Dongxiao Niu, Keke Wang

et al.

Energy, Journal Year: 2021, Volume and Issue: 231, P. 120908 - 120908

Published: May 10, 2021

Language: Английский

Citations

145
Analysis of input set characteristics and variances on k-fold cross validation for a Recurrent Neural Network model on waste disposal rate estimation DOI
Lan Vu, Kelvin Tsun Wai Ng, Amy Richter

et al.

Journal of Environmental Management, Journal Year: 2022, Volume and Issue: 311, P. 114869 - 114869

Published: March 11, 2022

Language: Английский

Citations

129
Long sequence time-series forecasting with deep learning: A survey DOI

Zonglei Chen,

Minbo Ma, Tianrui Li

et al.

Information Fusion, Journal Year: 2023, Volume and Issue: 97, P. 101819 - 101819

Published: April 28, 2023

Language: Английский

Citations

115
LOWESS smoothing and Random Forest based GRU model: A short-term photovoltaic power generation forecasting method DOI

Yeming Dai,

Yanxin Wang, Mingming Leng

et al.

Energy, Journal Year: 2022, Volume and Issue: 256, P. 124661 - 124661

Published: June 28, 2022

Language: Английский

Citations

77
Trends and gaps in photovoltaic power forecasting with machine learning DOI Creative Commons
Alba Alcañiz, Daniel Grzebyk, Hesan Ziar

et al.

Energy Reports, Journal Year: 2022, Volume and Issue: 9, P. 447 - 471

Published: Dec. 10, 2022

The share of solar energy in the electricity mix increases year after year. Knowing production photovoltaic (PV) power at each instant time is crucial for its integration into grid. However, due to meteorological phenomena, PV output can be uncertain and continuously varying, which complicates yield prediction. In recent years, machine learning (ML) techniques have entered world forecasting help increase accuracy predictions. Researchers seen great potential this approach, creating a vast literature on topic. This paper intends identify most popular approaches gaps discipline. To do so, representative part consisting 100 publications classified based different aspects such as ML family, location systems, number systems considered, features, etc. Via classification, main trends highlighted while offering advice researchers interested

Language: Английский

Citations

76
Multistage spatio-temporal attention network based on NODE for short-term PV power forecasting DOI
Songtao Huang, Qingguo Zhou, Jun Shen

et al.

Energy, Journal Year: 2024, Volume and Issue: 290, P. 130308 - 130308

Published: Jan. 8, 2024

Language: Английский

Citations

22
Prediction of SOx–NOx emission from a coal-fired CFB power plant with machine learning: Plant data learned by deep neural network and least square support vector machine DOI

Derrick Adams,

Dong-Hoon Oh,

Dong‐Won Kim

et al.

Journal of Cleaner Production, Journal Year: 2020, Volume and Issue: 270, P. 122310 - 122310

Published: June 15, 2020

Language: Английский

Citations

133
An Effective Hybrid NARX-LSTM Model for Point and Interval PV Power Forecasting DOI Creative Commons
Mohamed Massaoudi, Inès Chihi, Lilia Sidhom

et al.

IEEE Access, Journal Year: 2021, Volume and Issue: 9, P. 36571 - 36588

Published: Jan. 1, 2021

This paper proposes an effective Photovoltaic (PV) Power Forecasting (PVPF) technique based on hierarchical learning combining Nonlinear Auto-Regressive Neural Networks with exogenous input (NARXNN) Long Short-Term Memory (LSTM) model. First, the NARXNN model acquires data to generate a residual error vector. Then, stacked LSTM model, optimized by Tabu search algorithm, uses correction associated original produce point and interval PVPF. The performance of proposed PVPF was investigated using two real datasets different scales locations. comparative analysis NARX-LSTM twelve existing benchmarks confirms its superiority in terms accuracy measures. In summary, has following major achievements: 1) Improves prediction models; 2) Evaluates uncertainties forecasts high accuracy; 3) Provides generalization capability for PV systems scales. Numerical results comparison method real-world Australia USA demonstrate improved accuracy, outperforming benchmark approaches overall normalized Rooted Mean Squared Error (nRMSE) 1.98% 1.33% respectively.

Language: Английский

Citations

102
A Systematic Review of Statistical and Machine Learning Methods for Electrical Power Forecasting with Reported MAPE Score DOI Creative Commons

Eliana Vivas,

Héctor Allende‐Cid, Rodrigo Salas

et al.

Entropy, Journal Year: 2020, Volume and Issue: 22(12), P. 1412 - 1412

Published: Dec. 15, 2020

Electric power forecasting plays a substantial role in the administration and balance of current systems. For this reason, accurate predictions service demands are needed to develop better programming for generation distribution reduce risk vulnerabilities integration an electric system. purposes study, systematic literature review was applied identify type model that has highest propensity show precision context forecasting. The state-of-the-art determined from results reported 257 accuracy tests five geographic regions. Two classes models were compared: classical statistical or mathematical (MSC) machine learning (ML) models. Furthermore, use hybrid have made significant contributions is identified, case study demonstrate its good performance when compared with traditional Among our main findings, we conclude errors minimized by reducing time horizon, ML consider various sources exogenous variability tend forecast accuracy, finally, significantly increased over last years.

Language: Английский

Citations

99