The remote processing framework for portable computer power saving
Proceedings of the 1999 ACM symposium on Applied computing
Understanding code mobility (tutorial session)
Proceedings of the 22nd international conference on Software engineering
Computation offloading to save energy on handheld devices: a partition scheme
CASES '01 Proceedings of the 2001 international conference on Compilers, architecture, and synthesis for embedded systems
Power conservation strategy for mobile computers using load sharing
ACM SIGMOBILE Mobile Computing and Communications Review
Task Allocation for Distributed Multimedia Processing on Wirelessly Networked Handheld Devices
IPDPS '02 Proceedings of the 16th International Symposium on Parallel and Distributed Processing
Studying Energy Trade Offs in Offloading Computation/Compilation in Java-Enabled Mobile Devices
IEEE Transactions on Parallel and Distributed Systems
Power and Energy Profiling of Scientific Applications on Distributed Systems
IPDPS '05 Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS'05) - Papers - Volume 01
Multiprocessor Scheduling with the Aid of Network Flow Algorithms
IEEE Transactions on Software Engineering
Energy saving of mobile devices based on component migration and replication in pervasive computing
UIC'06 Proceedings of the Third international conference on Ubiquitous Intelligence and Computing
| Hi-index | 0.00 |
The ever-changing context and resource limitation of mobile devices and wireless network are two challenges in the development of pervasive computing application. In this paper, we present a generic optimal partitioning algorithm of mobile applications which tries to overcome the two obstacles. The algorithm can reallocate the components of an application among machines for saving resources according to the environment variations. For each resource, we construct a corresponding cost graph, involving computation cost, communication cost and migration cost, in the foundation of the software architecture. Based on the network flow theory, we transform the cost graph into an equivalent flow network that can be optimally cut by well-known Max-flow Min-cut algorithm. As a generic algorithm, the proposed algorithm can be applied to save network bandwidth, time or energy. In addition, it can elegantly allocate the software components among the two machines so as to balance multiple resource consumptions. The simulation results demonstrate the validity and effectiveness of the proposed algorithm.