Context-for-wireless: context-sensitive energy-efficient wireless data transfer
Proceedings of the 5th international conference on Mobile systems, applications and services
Markov decision process (MDP) framework for optimizing software on mobile phones
EMSOFT '09 Proceedings of the seventh ACM international conference on Embedded software
Energy optimal transmission scheduling in wireless sensor networks
IEEE Transactions on Wireless Communications
Bartendr: a practical approach to energy-aware cellular data scheduling
Proceedings of the sixteenth annual international conference on Mobile computing and networking
Energy efficiency of mobile clients in cloud computing
HotCloud'10 Proceedings of the 2nd USENIX conference on Hot topics in cloud computing
Mobile internet in stereo: an end-to-end scenario
ETM'10 Proceedings of the Third international conference on Incentives, overlays, and economic traffic control
How hard can it be? designing and implementing a deployable multipath TCP
NSDI'12 Proceedings of the 9th USENIX conference on Networked Systems Design and Implementation
Exploring mobile/WiFi handover with multipath TCP
Proceedings of the 2012 ACM SIGCOMM workshop on Cellular networks: operations, challenges, and future design
| Hi-index | 0.00 |
Multipath TCP is a backwards-compatible TCP extension that enables using multiple network paths between two end systems for a single TCP connection, increasing performance and reliability. It can also be used to "shift" active connections from one network path to another without breakage. This feature is especially attractive on mobile devices with multiple radio interfaces, because it can be used to continuously shift active connections to the most energy-efficient network path. This paper describes a novel method for deriving such a multipath scheduler using MPTCP that maximises energy savings. Based on energy models for the different radio interfaces as well as a continuously accumulated communication history of the device user, we compute schedulers for different applications by solving a Markov decision process offline. We evaluate these schedulers for a large number of random application models and selected realistic applications derived from measurements. Evaluations based on energy models for a mobile device with Wifi and 3G radio interfaces show that it performs comparably in terms of energy efficiency to a theoretically optimal omniscient oracle scheduler.