{"title":"基于综合特征选择和 GA-LSTM 量化回归的短期负载概率预测","authors":"Xue Meng, Xigao Shao, Shan Li","doi":"10.1155/2024/5452005","DOIUrl":null,"url":null,"abstract":"<div>\n <p>Accurately forecasting electricity demand is crucial for maintaining the balance between supply and demand of electric energy in real-time, ensuring the reliability and cost-efficiency of power system operations. The integration of numerous active loads and distributed renewable energy sources into the grid has led to increased load variability, rendering the traditional point forecasting approach inadequate for meeting the evolving needs of the power system. Probabilistic forecasting, which predicts the complete probability distribution of loads and provides more extensive information on load uncertainty, has emerged as a key solution to address these challenges. The long short-term memory (LSTM) model, known for its strong performance in modeling long series, is commonly utilized in load forecasting. Therefore, this study focuses on short-term electric load probability forecasting for users in a specific park in Yantai. We propose a short-term load probability forecasting model based on integrated feature selection (IFS), genetic algorithm (GA) optimization of LSTM, and quantile regression (QR), referred to as the IFS-GA-QRLSTM model. Initially, the integrated feature selection method is employed to identify the most influential factors affecting electric load, optimizing the model’s input features and reducing data redundancy. To address the subjective nature of parameter selection in the LSTM model, we use a GA to optimize model parameters. The combination of optimized LSTM with QR enables direct generation of quantile load predictions, which are further used in kernel density estimation to construct the probability density distribution. We compare the proposed method with five basic models, QRLSTM, IFS-QRCNN, IFS-QRRNN, IFS-QRLSTM, and IFS-QRGRU, for point prediction, interval prediction, and probability prediction. Experimental results demonstrate that the proposed method in this paper exhibits better prediction performance, smaller prediction errors, and greater effectiveness compared to the aforementioned models.</p>\n </div>","PeriodicalId":14051,"journal":{"name":"International Journal of Energy Research","volume":null,"pages":null},"PeriodicalIF":4.3000,"publicationDate":"2024-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/2024/5452005","citationCount":"0","resultStr":"{\"title\":\"Short-Term Load Probability Prediction Based on Integrated Feature Selection and GA-LSTM Quantile Regression\",\"authors\":\"Xue Meng, Xigao Shao, Shan Li\",\"doi\":\"10.1155/2024/5452005\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div>\\n <p>Accurately forecasting electricity demand is crucial for maintaining the balance between supply and demand of electric energy in real-time, ensuring the reliability and cost-efficiency of power system operations. The integration of numerous active loads and distributed renewable energy sources into the grid has led to increased load variability, rendering the traditional point forecasting approach inadequate for meeting the evolving needs of the power system. Probabilistic forecasting, which predicts the complete probability distribution of loads and provides more extensive information on load uncertainty, has emerged as a key solution to address these challenges. The long short-term memory (LSTM) model, known for its strong performance in modeling long series, is commonly utilized in load forecasting. Therefore, this study focuses on short-term electric load probability forecasting for users in a specific park in Yantai. We propose a short-term load probability forecasting model based on integrated feature selection (IFS), genetic algorithm (GA) optimization of LSTM, and quantile regression (QR), referred to as the IFS-GA-QRLSTM model. Initially, the integrated feature selection method is employed to identify the most influential factors affecting electric load, optimizing the model’s input features and reducing data redundancy. To address the subjective nature of parameter selection in the LSTM model, we use a GA to optimize model parameters. The combination of optimized LSTM with QR enables direct generation of quantile load predictions, which are further used in kernel density estimation to construct the probability density distribution. We compare the proposed method with five basic models, QRLSTM, IFS-QRCNN, IFS-QRRNN, IFS-QRLSTM, and IFS-QRGRU, for point prediction, interval prediction, and probability prediction. Experimental results demonstrate that the proposed method in this paper exhibits better prediction performance, smaller prediction errors, and greater effectiveness compared to the aforementioned models.</p>\\n </div>\",\"PeriodicalId\":14051,\"journal\":{\"name\":\"International Journal of Energy Research\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2024-09-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1155/2024/5452005\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Energy Research\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1155/2024/5452005\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENERGY & FUELS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Energy Research","FirstCategoryId":"5","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1155/2024/5452005","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 0
摘要
准确预测电力需求对于保持电力能源的实时供需平衡、确保电力系统运行的可靠性和成本效益至关重要。大量有功负载和分布式可再生能源并入电网,导致负载变异性增加,使传统的点预测方法无法满足电力系统不断变化的需求。概率预测可预测负荷的完整概率分布,并提供有关负荷不确定性的更广泛信息,已成为应对这些挑战的关键解决方案。长短期记忆(LSTM)模型以其在长序列建模方面的强大性能而著称,通常用于负荷预测。因此,本研究重点关注烟台某园区用户的短期电力负荷概率预测。我们提出了一种基于综合特征选择(IFS)、遗传算法(GA)优化 LSTM 和量化回归(QR)的短期负荷概率预测模型,简称为 IFS-GA-QRLSTM 模型。首先,采用综合特征选择方法来识别影响电力负荷的最有影响力的因素,优化模型的输入特征,减少数据冗余。针对 LSTM 模型中参数选择的主观性,我们使用 GA 来优化模型参数。优化后的 LSTM 与 QR 相结合,可直接生成量化负荷预测,并进一步用于核密度估计,以构建概率密度分布。我们将所提出的方法与 QRLSTM、IFS-QRCNN、IFS-QRRNN、IFS-QRLSTM 和 IFS-QRGRU 五种基本模型进行了比较,分别用于点预测、区间预测和概率预测。实验结果表明,与上述模型相比,本文提出的方法具有更好的预测性能、更小的预测误差和更高的有效性。
Short-Term Load Probability Prediction Based on Integrated Feature Selection and GA-LSTM Quantile Regression
Accurately forecasting electricity demand is crucial for maintaining the balance between supply and demand of electric energy in real-time, ensuring the reliability and cost-efficiency of power system operations. The integration of numerous active loads and distributed renewable energy sources into the grid has led to increased load variability, rendering the traditional point forecasting approach inadequate for meeting the evolving needs of the power system. Probabilistic forecasting, which predicts the complete probability distribution of loads and provides more extensive information on load uncertainty, has emerged as a key solution to address these challenges. The long short-term memory (LSTM) model, known for its strong performance in modeling long series, is commonly utilized in load forecasting. Therefore, this study focuses on short-term electric load probability forecasting for users in a specific park in Yantai. We propose a short-term load probability forecasting model based on integrated feature selection (IFS), genetic algorithm (GA) optimization of LSTM, and quantile regression (QR), referred to as the IFS-GA-QRLSTM model. Initially, the integrated feature selection method is employed to identify the most influential factors affecting electric load, optimizing the model’s input features and reducing data redundancy. To address the subjective nature of parameter selection in the LSTM model, we use a GA to optimize model parameters. The combination of optimized LSTM with QR enables direct generation of quantile load predictions, which are further used in kernel density estimation to construct the probability density distribution. We compare the proposed method with five basic models, QRLSTM, IFS-QRCNN, IFS-QRRNN, IFS-QRLSTM, and IFS-QRGRU, for point prediction, interval prediction, and probability prediction. Experimental results demonstrate that the proposed method in this paper exhibits better prediction performance, smaller prediction errors, and greater effectiveness compared to the aforementioned models.
期刊介绍:
The International Journal of Energy Research (IJER) is dedicated to providing a multidisciplinary, unique platform for researchers, scientists, engineers, technology developers, planners, and policy makers to present their research results and findings in a compelling manner on novel energy systems and applications. IJER covers the entire spectrum of energy from production to conversion, conservation, management, systems, technologies, etc. We encourage papers submissions aiming at better efficiency, cost improvements, more effective resource use, improved design and analysis, reduced environmental impact, and hence leading to better sustainability.
IJER is concerned with the development and exploitation of both advanced traditional and new energy sources, systems, technologies and applications. Interdisciplinary subjects in the area of novel energy systems and applications are also encouraged. High-quality research papers are solicited in, but are not limited to, the following areas with innovative and novel contents:
-Biofuels and alternatives
-Carbon capturing and storage technologies
-Clean coal technologies
-Energy conversion, conservation and management
-Energy storage
-Energy systems
-Hybrid/combined/integrated energy systems for multi-generation
-Hydrogen energy and fuel cells
-Hydrogen production technologies
-Micro- and nano-energy systems and technologies
-Nuclear energy
-Renewable energies (e.g. geothermal, solar, wind, hydro, tidal, wave, biomass)
-Smart energy system