Simultaneous compression of makespan and number of processors using CRP

This paper presents a new 2D compression (2DC) method for solving the multiprocessor scheduling (MS) problems to simultaneously achieve both objectives of minimizing the makespan and the number of processors used. Most existing approaches tend to focus on a very specific range of the MS problems, while risking the loss of the solution quality elsewhere. 2DC synthesizes two main classes of compression approaches in both the time and resource dimensions by utilizing the constrained resource planning (CRP) paradigm to balance the resource utilization and conservation. Experimental results show that 2DC extends the range of the solution effectiveness when measured separately in terms of the time and resource dimensions. More significantly, the 2DC method exhibits a remarkable solution quality and stability when measured in terms of a 2D cost function.