A comprehensive review on deep learning approaches for short-term load forecasting

Eren, Yavuz; Küçükdemiral, İbrahim

doi:10.1016/j.rser.2023.114031

Cited by 42 publications

(2 citation statements)

References 124 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In traditional STPLF for power systems, a multitude of factors including seasonal changes, weather patterns, holiday effects, economic growth levels, and consumer electricity consumption behaviors significantly impact the predictions. These factors contribute to unique characteristics such as substantial data volatility, strong nonlinearity, and high uncertainty in STPLF outcomes (Eren and Küçükdemiral, 2024). To refine prediction accuracy, it is essential to comprehensively examine the underlying laws governing load variations in power grids and meticulously analyze these influential elements.…”

Section: Selecting the Factors Influencing The Power Load Of Iesmentioning

confidence: 99%

Short-term power load forecasting for integrated energy system based on a residual and attentive LSTM-TCN hybrid network

Li,

et al. 2024

Front. Energy Res.

View full text Add to dashboard Cite

In the context of Integrated Energy System (IES), accurate short-term power demand forecasting is crucial for ensuring system reliability, optimizing operational efficiency through resource allocation, and supporting effective real-time decision-making in energy management. However, achieving high forecasting accuracy faces significant challenges due to the inherent complexity and stochastic nature of IES’s short-term load profiles, resulting from diverse consumption patterns among end-users and the intricate coupling within the network of interconnected energy sources. To address this issue, a dedicated Short-Term Power Load Forecasting (STPLF) framework for IES is proposed, which relies on a newly developed hybrid deep learning architecture. The framework seamlessly combines Long Short-Term Memory (LSTM) with Temporal Convolutional Network (TCN), enhanced by an attention mechanism module. By merging these methodologies, the network leverages the parallel processing prowess of TCN alongside LSTM’s ability to retain long-range temporal information, thus enabling it to dynamically concentrate on relevant sections of time series data. This synergy leads to improved prediction accuracy and broader applicability. Furthermore, the integration of residual connections within the network structure serves to deepen its learning capabilities and enhance overall performance. Ultimately, results from a real case study of a user-level IES demonstrate that the Mean Absolute Percentage Error (MAPE) of the proposed framework on the test set is 2.35%. This error rate is lower than the averages of traditional methods (3.43%) and uncombined single submodules (2.80%).

show abstract

Section: Selecting the Factors Influencing The Power Load Of Iesmentioning

confidence: 99%

Short-term power load forecasting for integrated energy system based on a residual and attentive LSTM-TCN hybrid network

Li,

et al. 2024

Front. Energy Res.

View full text Add to dashboard Cite

show abstract

“…There is an effort to exploit the emergent advances in deep-learning machine models (such as Transformers and GANs) for time series analysis [11,12]. Despite the great success achieved by these models in processing natural languages and generating images and videos, Long short-term memory (LSTM) and gated recurrent unit (GRU) networks still maintain their popularity for time series forecasting [13,14,15]. Their popularity could be attributed to their ability to effectively capture temporal dependencies, which is crucial for accurately predicting future values in a time series.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Multi-Step Brent Oil Price Forecasting with Ensemble Multi-Scenario Bi-GRU Networks

Alruqimi,

Persio

2024

Preprint

View full text Add to dashboard Cite

Despite numerous research efforts in applying deep learning to time series forecasting, achieving high accuracy in multi-step predictions for volatile time series like crude oil prices remains a significant challenge. Moreover, most existing approaches primarily focus on one-step forecasting, and the performance often varies depending on the dataset and specific case study. In this paper, we introduce an ensemble model to capture Brent oil price volatility and enhance the multi-step prediction. Our methodology employs a two-pronged approach. First, we assess popular deep-learning models and the impact of various external factors on forecasting accuracy. Then, we introduce an ensemble multi-step forecasting model for Brent oil prices. Our approach generates accurate forecasts by employing ensemble techniques across multiple forecasting scenarios using three BI-GRU networks. Extensive experiments were conducted on a dataset encompassing the COVID-19 pandemic period, which had a significant impact on energy markets. The proposed model's performance was evaluated using the standard evaluation metrics of MAE, MSE, and RMSE. The results demonstrate that the proposed model outperforms benchmark and established models.

show abstract

Scrutinizing the nexus: Energy, economic growth, and environmental quality: An approach toward achieving the Sustainable Development Goals (7, 13, and 8)

Fahad,

Khan,

Waqas

et al. 2024

Sustainable Development

View full text Add to dashboard Cite

This study investigates the intricate relationship between energy consumption, economic growth, and environmental quality in Pakistan from 1990 to 2022, highlighting the critical role of natural resources rent (NRR) and renewable energy consumption (REC) in shaping carbon dioxide emissions. The study aims to understand how these variables interact and influence each other, particularly focusing on the impact of NRR and REC on CO2 emissions within the context of Pakistan's economic growth and energy consumption patterns. Given the country's rapid economic growth and increasing energy demands, there is an imperative need to investigate how these factors influence environmental quality, particularly CO2 emissions employing the autoregressive distributed lag approach with structural breaks, we analyze the long‐term interactions and causality among NRR, REC, energy use (EU), gross domestic product (GDP), and CO2 emissions. Our findings demonstrate that while NRR and REC negatively correlate with CO2 emissions, a positive association exists between EU, GDP growth, and emissions. These results underscore the potential of strategic environmental policies, aligned with Sustainable Development Goals 7, 13, and 8, to foster sustainable development pathways in Pakistan. By comparing this study's approach with existing methodologies, we highlight our study's unique contribution to the literature, offering policymakers a robust foundation to formulate effective strategies for balancing economic growth with environmental sustainability.

show abstract

A comprehensive review on deep learning approaches for short-term load forecasting

Cited by 42 publications

References 124 publications

Short-term power load forecasting for integrated energy system based on a residual and attentive LSTM-TCN hybrid network

Short-term power load forecasting for integrated energy system based on a residual and attentive LSTM-TCN hybrid network

Enhancing Multi-Step Brent Oil Price Forecasting with Ensemble Multi-Scenario Bi-GRU Networks

Scrutinizing the nexus: Energy, economic growth, and environmental quality: An approach toward achieving the Sustainable Development Goals (7, 13, and 8)

Contact Info

Product

Resources

About