Short-Term Load Forecasting for Regional Smart Energy Systems Based on Two-Stage Feature Extraction and Hybrid Inverted Transformer DOI Open Access

Zhewei Huang,

Yawen Yi

Sustainability, Journal Year: 2024, Volume and Issue: 16(17), P. 7613 - 7613

Published: Sept. 2, 2024

Accurate short-term load forecasting is critical for enhancing the reliability and stability of regional smart energy systems. However, inherent challenges posed by substantial fluctuations volatility in electricity patterns necessitate development advanced techniques. In this study, a novel approach based on two-stage feature extraction process hybrid inverted Transformer model proposed. Initially, Prophet method employed to extract essential features such as trends, seasonality holiday from original dataset. Subsequently, variational mode decomposition (VMD) optimized IVY algorithm utilized significant periodic residual component obtained Prophet. The extracted both stages are then integrated construct comprehensive data matrix. This matrix inputted into deep learning that combines an (iTransformer), temporal convolutional networks (TCNs) multilayer perceptron (MLP) accurate forecasting. A thorough evaluation proposed conducted through four sets comparative experiments using collected Elia grid Belgium. Experimental results illustrate superior performance approach, demonstrating high accuracy robustness, highlighting its potential ensuring stable operation

Language: Английский

Enhanced short-term load forecasting with hybrid machine learning models: CatBoost and XGBoost approaches DOI
Lijie Zhang, Dominik Jánošík

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 241, P. 122686 - 122686

Published: Nov. 24, 2023

Language: Английский

Citations

50
CNNs-Transformer based day-ahead probabilistic load forecasting for weekends with limited data availability DOI
Zhirui Tian, Weican Liu, Wenqian Jiang

et al.

Energy, Journal Year: 2024, Volume and Issue: 293, P. 130666 - 130666

Published: Feb. 10, 2024

Language: Английский

Citations

37
A hybrid prediction interval model for short-term electric load forecast using Holt-Winters and Gate Recurrent Unit DOI
Xin He, Wenlu Zhao, Zhijun Gao

et al.

Sustainable Energy Grids and Networks, Journal Year: 2024, Volume and Issue: 38, P. 101343 - 101343

Published: March 12, 2024

Language: Английский

Citations

12
Enhancing smart grid load forecasting: An attention-based deep learning model integrated with federated learning and XAI for security and interpretability DOI Creative Commons

Md Al Amin Sarker,

Bharanidharan Shanmugam, Sami Azam

et al.

Intelligent Systems with Applications, Journal Year: 2024, Volume and Issue: 23, P. 200422 - 200422

Published: Aug. 4, 2024

Language: Английский

Citations

11
Seq2Seq-LSTM With Attention for Electricity Load Forecasting in Brazil DOI Creative Commons
William Gouvêa Buratto, Rafael Ninno Muniz, Ademir Nied

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 30020 - 30029

Published: Jan. 1, 2024

Electricity load forecasting is important to planning the decision-making regarding use of energy resources, in which power system must be operated guarantee supply electricity future at lowest possible price. With rise ability based on deep learning, these approaches are promising this context. Considering attention mechanism capture long-range dependencies, it highly recommended for sequential data processing, where time series-related tasks stand out. a sequence-to-sequence (Seq2Seq) series Brazil, paper proposes long short-term memory (LSTM) with perform forecasting. The proposed Seq2Seq-LSTM outperforms other well-established models. Having mean absolute error equal 0.3027 method shown field applications. contributes by implementing an Seq2Seq data, therefore, more than one correlated signal can used prediction enhancing its capacity when avaliable.

Language: Английский

Citations

10
Study on deterministic and interval forecasting of electricity load based on multi-objective whale optimization algorithm and transformer model DOI
Pei Du,

Yuxin Ye,

Han Wu

et al.

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: 268, P. 126361 - 126361

Published: Jan. 2, 2025

Language: Английский

Citations

2
Enhancing Load Forecasting Accuracy in Smart Grids: A Novel Parallel Multichannel Network Approach Using 1D CNN and Bi‐LSTM Models DOI Creative Commons

Syed Muhammad Hasanat,

R. Younis, Saad Alahmari

et al.

International Journal of Energy Research, Journal Year: 2024, Volume and Issue: 2024(1)

Published: Jan. 1, 2024

Load forecasting plays a pivotal role in the efficient energy management of smart grid. However, complex, intermittent, and nonlinear grids complexity large dataset handling pose difficulty accurately loads. The important issue is considering cyclic features, which have not yet been adequately addressed through trigonometric transformations. Furthermore, using long short‐term memory (LSTM) or 1D convolution neural network (1D CNN) existing hybrid models involve stacked CNN‐LSTM architectures, employing convolutions as preprocessing step to downsample sequences extract high‐ low‐level spatial features. these often overlook temporal emphasizing higher‐level features processed by subsequent recurrent layer. Therefore, this study considers novel approach independently process for characteristics parallel multichannel comprising CNN bidirectional‐LSTM (Bi‐LSTM) models. proposed model evaluated National Transmission Dispatch Company (NTDC) load dataset, with additional assessment on two datasets, American Electric Power Commonwealth Edison, ensure its generalizability. Performance evaluation NTDC yields results 3.4% mean absolute percentage error (MAPE), 513.95 (MAE), 623.78 root square (RMSE) day‐ahead forecasting, 0.56% MAPE, 94.84 MAE, 115.67 RMSE hour‐ahead forecast. experimental demonstrate that outperforms models, particularly hour‐ Moreover, comparative analysis previous studies reveals superior performance reducing gap between predicted actual values.

Language: Английский

Citations

9
Graph Convolutional Networks based short-term load forecasting: Leveraging spatial information for improved accuracy DOI
Haris Mansoor, Muhammad Shuzub Gull, Huzaifa Rauf

et al.

Electric Power Systems Research, Journal Year: 2024, Volume and Issue: 230, P. 110263 - 110263

Published: March 5, 2024

Language: Английский

Citations

7
Data/mechanism hybrid-driven modeling of blast furnace smelting system and global sequential optimization DOI
Siwei Lou, Chunjie Yang, Xujie Zhang

et al.

Journal of Process Control, Journal Year: 2024, Volume and Issue: 139, P. 103235 - 103235

Published: May 21, 2024

Language: Английский

Citations

4
Rotation Control Method for Improving the Electrocatalytic Reduction of CO2 to Methanol under Wind Power Fluctuations DOI

Annan Hu,

Jun Cheng,

Hongkun Lv

et al.

Industrial & Engineering Chemistry Research, Journal Year: 2024, Volume and Issue: 63(10), P. 4273 - 4282

Published: March 4, 2024

Energy storage systems based on off-grid fluctuated wind power offer an attractive approach through the electrocatalytic reduction of CO2 to methanol. Potential fluctuations derived from cause various products and decrease efficiency in CO2-to-methanol system. A periodic rotation control method individual electrolyzers electrolysis cells array with rated (100%), fluctuating (0–100%), standby (0%) status is proposed solve potential fluctuation problems. O2 volume creatively used as intermediate bridge link so that a curve fitted function power–methanol Faradaic efficiency. The improves methanol by ∼18.5% compared conventional average cumulation method, while it reduces coefficient variation 67.9% method. This demonstration provides promising for efficient utilization energy systems.

Language: Английский

Citations

3