Department of Civil Engineering, College of Engineering, Universiti Tenaga Nasional (UNITEN), 43000, Kajang, Selangor Darul Ehsan, Malaysia.
Department of Mechanical Engineering, College of Engineering, Universiti Tenaga Nasional (UNITEN), 43000, Kajang, Selangor Darul Ehsan, Malaysia.
Environ Sci Pollut Res Int. 2021 Jun;28(21):26571-26583. doi: 10.1007/s11356-021-12435-6. Epub 2021 Jan 23.
Reliable and accurate prediction model capturing the changes in solar radiation is essential in the power generation and renewable carbon-free energy industry. Malaysia has immense potential to develop such an industry due to its location in the equatorial zone and its climatic characteristics with high solar energy resources. However, solar energy accounts for only 2-4.6% of total energy utilization. Recently, in developed countries, various prediction models based on artificial intelligence (AI) techniques have been applied to predict solar radiation. In this study, one of the most recent AI algorithms, namely, boosted decision tree regression (BDTR) model, was applied to predict the changes in solar radiation based on collected data in Malaysia. The proposed model then compared with other conventional regression algorithms, such as linear regression and neural network. Two different normalization techniques (Gaussian normalizer binning normalizer), splitting size, and different input parameters were investigated to enhance the accuracy of the models. Sensitivity analysis and uncertainty analysis were introduced to validate the accuracy of the proposed model. The results revealed that BDTR outperformed other algorithms with a high level of accuracy. The funding of this study could be used as a reliable tool by engineers to improve the renewable energy sector in Malaysia and provide alternative sustainable energy resources.
可靠且准确的太阳辐射变化预测模型，对于发电和可再生无碳能源产业至关重要。马来西亚地处赤道带，拥有丰富的太阳能资源，其气候特点也有利于太阳能的开发，因此具备发展此类产业的巨大潜力。然而，太阳能在总能源利用中仅占 2-4.6%。最近，在发达国家，各种基于人工智能 (AI) 技术的预测模型已被应用于太阳辐射预测。在这项研究中，应用了一种最新的 AI 算法，即增强决策树回归 (BDTR) 模型，根据在马来西亚收集的数据来预测太阳辐射的变化。然后，将所提出的模型与其他传统回归算法（如线性回归和神经网络）进行比较。研究了两种不同的归一化技术（高斯归一化器和分箱归一化器）、分割大小以及不同的输入参数，以提高模型的准确性。引入了敏感性分析和不确定性分析来验证所提出模型的准确性。结果表明，BDTR 算法的准确性高于其他算法。这项研究的资金可作为工程师的可靠工具，以改善马来西亚的可再生能源部门，并提供替代可持续能源资源。
