Cloud-Cluster Architecture for Detection in Intermittently Connected Sensor Networks

Abstract

We consider a centralized detection problem where sensors experience noisy measurements and intermittent connectivity to a centralized fusion center. The sensors may collaborate locally within predefined sensor clusters and fuse their noisy sensor data to reach a common local estimate of the detected event in each cluster. The connectivity of each sensor cluster is intermittent and depends on the available communication opportunities of the sensors to the fusion center. Upon receiving the estimates from all the connected sensor clusters the fusion center fuses the received estimates to make a final determination regarding the occurrence of the event across the deployment area. We refer to this hybrid communication scheme as a cloud-cluster architecture. We propose a method for optimizing the decision rule for each cluster and analyzing the expected detection performance resulting from our hybrid scheme.Our method is tractable and addresses the high computational complexity caused by heterogeneous sensors' and clusters' detection quality, heterogeneity in their communication opportunities, and nonconvexity of the loss function. Our analysis shows that clustering the sensors provides resilience to noise in the case of low sensor communication probability with the cloud. For larger clusters, a steep improvement in detection performance is possible even for a low communication probability by using our cloud-cluster architecture. I. INTRODUCTIONThe next generation of wireless infrastructure enables cloud connectivity, and with it, powerful centralized decision making based on sensor data. However, cloud connectivity of sensors cannot M. Yemini and A. J. Goldsmith are with the Electrical and

Robust Federated Learning with Connectivity Failures: A Semi-Decentralized Framework with Collaborative Relaying

“…Relaying, also referred to as cooperative communication, has been widely studied in the literature in order to improve the coverage [21], diversity [22], end-to-end signal quality, [23,24] as well as connectivity [25,26] of wireless terminals. In FEEL, relaying has been considered previously in the context of hierarchical FL [27] to bring the clients closer to the PS with the aim of reducing the latency and interference.…”

“…In FEEL, relaying has been considered previously in the context of hierarchical FL [27] to bring the clients closer to the PS with the aim of reducing the latency and interference. In this paper, motivated by our prior works [25,26], where client cooperation is used to improve the connectivity to the cloud and to reduce the latency and scheduling overhead, we propose and analyze a new FEEL paradigm, where the clients cooperate to mitigate the detrimental effects of communication stragglers. In the proposed method, clients share their current updates with each other so that each client can send to the PS, a weighted average of its own current update and those of its neighbors.…”