A Thermal-Balanced Variable-Sized-Bin-Packing Approach for Energy Efficient Multi-Core Real-Time Scheduling

Shi Sha, Wujie Wen, Shaolei Ren, Gang Quan

Abstract: In this paper, we study the problem of how to schedule real-time tasks on multi-core platforms to maximize the energy efficiency under a peak temperature constraint. Different from the traditional load-balancing approach, we propose energy saving solutions under the ``thermal balancing'' heuristic, which can effectively avoid hotspots and maximize the throughput. We first establish and formally prove a lower bound of energy when scheduling a periodic task set on a multi-core platform using the thermal-balancing approach. Considering the NP-nature of this problem, we formulate the problem as a variable-sized-bin-packing~(VSBP) problem and develop a partitioning heuristic. We further introduce an enhanced algorithm to improve the quality of the solution. The experimental results show up to 256.4\%~improvement of the energy efficiency and an average 9.95\% higher feasibility than the traditional load balancing approach.