arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.10663cs.LG
收藏

能源时间序列预测.常规和机器学习模型的分析和经验评估

Energy time series forecasting-Analytical and empirical assessment of conventional and machine learning models

Center for Artificial Intelligence and RObotics (CAIRO), Faculty of Science, Aswan University, Egypt(阿斯旺大学科学学院人工智能与机器人中心);Department of Computers and Systems Engineering, Faculty of Engineering, Minia University, Egypt(米尼亚大学工程学院计算机与系统工程系);College of Computer Science and Information Technology, King Faisal University, Saudi Arabia(费萨尔国王大学计算机科学与信息技术学院)

Hala Hamdoun, Alaa Sagheer, Hassan Youness

摘要:

机器学习方法已被采用在文献中作为传统方法的竞争者来解决能源时间序列预测(TSF)问题。近年来,深度学习方法已经出现在人工智能领域,在广泛的应用中取得了惊人的性能。然而,关于它们在解决能量TSF问题中的性能的证据,在精度和计算要求方面,是很少的。大部分的综述文章,处理能源TSF问题的系统评价,但是,定性和定量研究的能源TSF问题还没有在文献中。本文的目的是双重的,首先,它提供了一个全面的分析评估,传统的,机器学习,和深度学习方法,可用于解决各种能源TSF问题。其次,本文通过三个真实世界的数据集对许多选定的方法进行了实证评估。这些数据集涉及电能消耗问题、天然气问题和单个家庭的电能消耗问题,前两个问题是单变量TSF,第三个问题是多变量TSF。与传统和机器学习竞争者相比,深度学习方法在准确性和预测范围方面都有显著提高。同时,它们的计算需求明显大于其他竞争者。最后,本文确定了一些挑战,潜在的研究方向,并建议研究界可以作为进一步研究的基础,在能源预测领域。

英文摘要:

Machine learning methods have been adopted in the literature as contenders to conventional methods to solve the energy time series forecasting (TSF) problems. Recently, deep learning methods have been emerged in the artificial intelligence field attaining astonishing performance in a wide range of applications. Yet, the evidence about their performance in to solve the energy TSF problems, in terms of accuracy and computational requirements, is scanty. Most of the review articles that handle the energy TSF problem are systematic reviews, however, a qualitative and quantitative study for the energy TSF problem is not yet available in the literature. The purpose of this paper is twofold, first it provides a comprehensive analytical assessment for conventional,machine learning, and deep learning methods that can be utilized to solve various energy TSF problems. Second, the paper carries out an empirical assessment for many selected methods through three real-world datasets. These datasets related to electrical energy consumption problem, natural gas problem, and electric power consumption of an individual household problem.The first two problems are univariate TSF and the third problem is a multivariate TSF. Com-pared to both conventional and machine learning contenders, the deep learning methods attain a significant improvement in terms of accuracy and forecasting horizons examined. In the mean-time, their computational requirements are notably greater than other contenders. Eventually,the paper identifies a number of challenges, potential research directions, and recommendations to the research community may serve as a basis for further research in the energy forecasting domain.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑