A Deep Learning Approach for Sustainable and Secure Operations of Cloud Data Centres for Optimising the Energy Efficiency

This study focuses on enhancing the sustainability and efficiency of hospital data centers through the deployment of machine learning algorithms. Support Vector Machines (SVM), Decision Trees (DT), Artificial Neural Networks (ANN), and Recurrent Neural Networks (RNN) are applied to forecast server workloads and dynamically optimize resource allocation. SVM emerges as the most accurate model at 96.5%, leading a suite of models that effectively avoid server overloads and allow efficient load sharing. The research extends its influence to the optimization of important hardware parameters, including temperature, humidity, power consumption, and energy efficiency. Each approach contributes differently to enhance the performance of the server infrastructure reliability. The study continues with a thorough examination of energy efficiency gains over an 8-hour period, offering vital insights into the models' dynamic influence. Ultimately, this study develops a complete framework for sustainable and adaptable healthcare data management, revealing the potential of machine learning to modernize hospital infrastructure and meet increasing operational difficulties.