Multi-objective scheduling of cloud tasks with positional information-enhanced reptile search algorithm

With the proliferation of cloud services driven by accessibility, enhanced performance, and cost-effectiveness, cloud service providers continuously seek methods to expedite job completion, thereby augmenting profits and diminishing energy consumption expenditures. In pursuit of this objective, numerous scheduling algorithms have been devised. Nevertheless, many of these techniques address only one specific objective within the scheduling process. This paper introduces a novel approach founded on the Reptile Search Algorithm (RSA). The RSA, albeit effective, predominantly navigates by tracing the path of optimal individuals, often overlooking valuable insights from others. Modified RSA (MRSA) is proposed to enhance RSA by incorporating a distribution estimation methodology to harness the maximum potential of the positional knowledge embedded within the majority population. MRSA is simulated using the Cloudsim tool and evaluated under diverse test conditions. The efficacy of MRSA is assessed by employing various parameters and comparing them with existing algorithms. The findings indicate that MRSA is superior to other algorithms regarding resource utilization, energy consumption, and execution cost.