Exploiting Non-Causal CPU-State Information for Energy-Efficient Mobile Cooperative Computing

Scavenging the idling computation resources at the enormous number of mobile devices, ranging from small IoT devices to powerful laptop computers, can provide a powerful platform for local mobile cloud computing. The vision can be realized by peer-to-peer cooperative computing between edge devices, which is called co-computing and the theme of this paper. We consider a co-computing system where a user offloads computation of input-data to a helper. The helper controls the offloading process based on a predicted CPU-idling profile and the objective of minimizing the user’s energy consumption. Consider the scenario that the user has one-shot input-data arrival and the helper buffers offloaded bits. The derived solution for the optimal offloading control has an interesting graphical interpretation as follows. In the plane of user’s co-computable bits (by offloading) versus time, a so-called offloading feasibility tunnel can be constructed that constrains the range of offloaded bits at any time instant. The existence of the tunnel arises from the helper’s CPU-idling profile and buffer size. Given the tunnel, the optimal offloading is shown to be achieved by the well-known “string-pulling” strategy, graphically referring to pulling a string across the tunnel. Furthermore, we show that the problem of optimal data partitioning for offloading and local computing at the user is convex, admitting a simple solution using the sub-gradient method. Last, the developed design approach for co-computing is extended to the scenario of bursty data arrivals at the user. The approach is modified by defining a new offloading feasibility tunnel that accounts for bursty data arrivals. Index Terms Mobile cooperative computing, energy-efficient transmission, D2D communication, computation offloading, mobile-edge computing, fog computing. C. You and K. Huang are with the Dept. of EEE at The University of Hong Kong, Hong Kong (Email: [email protected], [email protected]). ar X iv :1 70 4. 04 59 5v 3 [ cs .I T ] 2 5 A pr 2 01 7