CAROL: Confidence-Aware Resilience Model for Edge Federations
This work addresses service resilience for edge federations in IoT, offering improvements over existing schemes, though it appears incremental as it builds on prior fault-tolerance methods with specific enhancements.
The paper tackles the problem of service resilience in edge federations for IoT applications by proposing CAROL, a confidence-aware model that predicts QoS and uses confidence scores to optimize recovery and fine-tuning, resulting in reductions of up to 16% in energy consumption, 17% in deadline violations, and 36% in resilience overheads.
In recent years, the deployment of large-scale Internet of Things (IoT) applications has given rise to edge federations that seamlessly interconnect and leverage resources from multiple edge service providers. The requirement of supporting both latency-sensitive and compute-intensive IoT tasks necessitates service resilience, especially for the broker nodes in typical broker-worker deployment designs. Existing fault-tolerance or resilience schemes often lack robustness and generalization capability in non-stationary workload settings. This is typically due to the expensive periodic fine-tuning of models required to adapt them in dynamic scenarios. To address this, we present a confidence aware resilience model, CAROL, that utilizes a memory-efficient generative neural network to predict the Quality of Service (QoS) for a future state and a confidence score for each prediction. Thus, whenever a broker fails, we quickly recover the system by executing a local-search over the broker-worker topology space and optimize future QoS. The confidence score enables us to keep track of the prediction performance and run parsimonious neural network fine-tuning to avoid excessive overheads, further improving the QoS of the system. Experiments on a Raspberry-Pi based edge testbed with IoT benchmark applications show that CAROL outperforms state-of-the-art resilience schemes by reducing the energy consumption, deadline violation rates and resilience overheads by up to 16, 17 and 36 percent, respectively.