• Kushal Saraf

As the scale of distributed computing continues to expand, its impact on energy consumption and the environment is becoming increasingly evident. According to statistics, data centers' energy usage has accounted for approximately half of their operational costs. The escalating energy consumption not only demands a significant amount of energy resources but also places a substantial strain on the environment. The substantial energy consumption of cloud data centers has become a focal concern in the field of information technology, drawing significant attention and requiring urgent resolution. Presently, the high energy usage issue can be attributed to two primary factors. Firstly, the resource reservation mechanism, driven by the need to meet completion times, leads to low server utilization rates, inevitably resulting in inefficient usage for smaller tasks. Secondly, the current cooling infrastructure in data centers relies on a peak-value approach, which leads to excessive cooling supply, heightened operational costs, and a significant environmental impact.

ccloud, artifical intellegence, machine learning, green, Decision Model, LSTM, Prediitve model

"AutoML for Multi-Label Classification", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 9, page no.b313-b323, September-2023, Available :http://www.jetir.org/papers/JETIR2309136.pdf

"AutoML for Multi-Label Classification", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 9, page no. ppb313-b323, September-2023, Available at : http://www.jetir.org/papers/JETIR2309136.pdf