Towards Thermal-Aware Workload Distribution in Cloud Data Centers Based on Failure Models

Increasing workload conditions lead to a significant surge in power consumption and computing node failures data centers. The existing distribution strategies focused on either thermal awareness or failure mitigation, overlooking the impact of energy efficiency cloud To address this issue, new holistic model is built characterize impacts workloads, cooling costs, heat recirculation, Leveraging such model, we propose novel thermal-aware strategy called HGSA that takes into accountand can improve Our empirical findings confirm (i) faulty nodes large rise consumption, (ii) locations play vital role Experimental results unveil HGSA adroit at making near-optimal decisions strategies. In particular, cuts down minimum inlet temperature by 5.2 $\%$ -15 , improves maximum air Computer Room Air Conditioner (CRAC) 4.2 -26.5 lowers cost 15.4 -50 compared solutions. Furthermore, back total 0.65 -78 .