Impact of channel state information on wireless computing network control

Abstract

We consider the problem of efficient delivery of real-time computation services over wireless computing networks in which nodes are equipped with both communication and computation resources. We investigate the impact of channel state information (CSI) knowledge on the capacity of wireless computing networks, and design a distributed control policy that jointly schedules network flows for both routing and service processing, along with the corresponding allocation of communication and computation resources, using precise CSI knowledge at the transmitters. Compared to previous results, where only statistical CSI knowledge is considered, our results show that the availability of precise CSI at the transmitters increases the wireless computing network stability region, and that properly designed schemes that exploit such knowledge can support higher input rates and improve the overall cost-delay tradeoff.