Machine learning autoencoder‐based parameters prediction for solar power generation systems in smart grid

• Published in: IET smart grid 2024-06, Vol.7 (3), p.328-350
• Main Authors: Zafar, Ahsan, Che, Yanbo, Faheem, Muhammad, Abubakar, Muhammad, Ali, Shujaat, Bhutta, Muhammad Shoaib
• Format: Article
• Language: English
• Subjects: power grids; power system management; power system planning; solar power stations
• ISSN: 2515-2947; 2515-2947
• DOI: 10.1049/stg2.12153

During the fourth energy revolution, artificial intelligence implementation is necessary in all fields of technology to meet the increasing energy demands and address the diminishing fossil fuel reserves, necessitating the shift towards smart grids. The authors focus on predicting parameters accurately to minimise loss and improve power generation capacity in smart grids, given that accurate parameter prediction is essential for traditional power grid stations converting to smart grids. The authors employ an artificial intelligence‐based machine learning model, namely the long short‐term memory, to predict parameters of a solar power plant. After analysing the results obtained from the long short‐term memory model in graphical visualisation, the model is further improved using two different techniques namely, a convolutional neural network‐long short‐term memory and the authors proposed an autoencoder long short‐term memory. Comparing the results of these models, the study finds that autoencoder long short‐term memory outperforms the convolutional neural network‐long short‐term memory as well as simple long short‐term memory. Thus, the use of artificial intelligence in this study substantially enhances the precision of parameter prediction by augmenting the performance of rudimentary machine learning models, thereby facilitating the attainment of a resilient and resourceful power system that overcomes power losses and ameliorates production capacity in the context of Smart Grids. The authors address the need for accurate parameter prediction in solar power generation systems within the context of a smart grid. With the increasing integration of renewable energy sources into power grids, predicting parameters, such as daily power generation, maximum grid connected power generation, and radiance becomes crucial for optimal operation and planning. The authors utilised machine learning autoencoder techniques to develop a predictive model capable of estimating these parameters accurately.