Task allocation in distributed computing systems

In this paper, we investigate the static task allocation problem for heterogeneous distributed computing systems with the goal of minimizing total execution and communication time (i.e. task completion time). An objective function is formulated to evaluate the optimality of mapping modules of a task to a set of heterogeneous processors connected with some communication links of varying transmission rates. We present three algorithms: one to obtain optimal task allocation and other two to obtain suboptimal allocation. The accuracy and efficiency of the proposed algorithms are demonstrated through a simulation study and results are reported.