Edge computing is pushing the frontier of computing applications, data, and services away from centralized nodes to the logical extremes of a network. A major technological challenge for workflow scheduling in the edge computing environment is cost reduction with service-level-agreement (SLA) constraints in terms of performance and quality-of-service requirements because real-world workflow applications are constantly subject to negative impacts (e.g., network congestions, unexpected long message delays, shrinking coverage, range of edge servers due to battery depletion. To address the above concern, we propose a novel approach to location-aware and proximity-constrained multi-workflow scheduling with edge computing resources). The proposed approach is capable of minimizing monetary costs with user-required workflow completion deadlines. It employs an evolutionary algorithm (i.e., the discrete firefly algorithm) for the generation of near-optimal scheduling decisions. For the validation purpose, the authors show that our proposed approach outperforms traditional peers in terms multiple metrics based on a real-world dataset of edge resource locations and multiple well-known scientific workflow templates.
A Hybrid Algorithm for Multi-Objective Scientific Workflow Scheduling in IaaS Cloud
