Workflow scheduling in e-Science networks

We solve workflow scheduling problems in e-Science networks, whose goal is minimizing either makespan or network resource consumption by jointly scheduling heterogeneous resources such as compute and network resources. We formulate the workflow scheduling problem incorporating multiple paths as a mixed integer linear programming (MILP) and develop several linear programming relaxation heuristics based on this formulation. Our algorithms allow dynamic multiple paths for data transfer between tasks and more flexible resource allocation that may vary over time. We evaluate our algorithms against a well-known list scheduling algorithm in e-Science networks whose size is relatively small. Our simulation results show that our heuristics are fast and work well when communication-to-computation ratios (CCRs) are small. Also, these results show that use of dynamic multiple paths and malleable resource allocation is useful for data intensive applications.