We study a problem of optimizing the sampling interval in an edge-based feedback system, where sensor samples are offloaded to a back-end server which process them and generates a feedback that is fed-back to a user. Sampling the system at maximum frequency results in the detection of events of interest with minimum delay but incurs higher energy costs due to the communication and processing of some redundant samples. On the other hand, lower sampling frequency results in a higher delay in detecting an event of interest thus increasing the idle energy usage and degrading the quality of experience. We propose a method to quantify this trade-off and compute the optimal sampling interval, and use simulation to demonstrate the energy savings.

We study the problem of finding efficient sampling policies in an edge-based feedback system, where sensor samples are offloaded to a back-end server that processes them and generates feedback to a user. Sampling the system at maximum frequency results in the detection of events of interest with minimum delay but incurs higher energy costs due to the communication and processing of redundant samples. On the other hand, lower sampling frequency results in higher delay in detecting the event, thus increasing the idle energy usage and degrading the quality of experience. We quantify this trade-off as a weighted function between the number of samples and the sampling interval. We solve the minimisation problem for exponential and Rayleigh distributions, for the random time to the event of interest. We prove the convexity of the objective functions by using novel techniques, which can be of independent interest elsewhere. We argue that adding an initial offset to the periodic sampling can further reduce the energy consumption and jointly compute the optimum offset and sampling interval. We apply our framework to two practically relevant applications and show energy savings of up to 36% when compared to an existing periodic scheme. 

We study the problem of optimal sampling in an edge-based video analytics system (VAS), where sensor samples collected at a terminal device are offloaded to a back-end server that processes them and generates feedback for a user. Sampling the system with the maximum allowed frequency results in the timely detection of relevant events with minimum delay. However, it incurs high energy costs and causes unnecessary usage of network and compute resources via communication and processing of redundant samples. On the other hand, an infrequent sampling result in a higher delay in detecting the relevant event, thus increasing the idle energy usage and degrading the quality of experience in terms of responsiveness of the system. We quantify this sampling frequency trade-off as a weighted function between the number of samples and the responsiveness. We propose an energy-optimal aperiodic sampling policy that improves over the state-of-the-art optimal periodic sampling policy. Numerically, we show the proposed policy provides a consistent improvement of more than 10% over the state-of-the-art.

We consider a resource-constrained Edge Device (ED), such as an IoT sensor or a microcontroller unit, embedded with a small-size ML model (S-ML) for a generic classification application and an Edge Server (ES) that hosts a large-size ML model (L-ML). Since the inference accuracy of S-ML is lower than that of the L-ML, offloading all the data samples to the ES results in high inference accuracy, but it defeats the purpose of embedding S-ML on the ED and deprives the benefits of reduced latency, bandwidth savings, and energy efficiency of doing local inference. In order to get the best out of both worlds, i.e., the benefits of doing inference on the ED and the benefits of doing inference on ES, we explore the idea of Hierarchical Inference (HI), wherein S-ML inference is only accepted when it is correct, otherwise the data sample is offloaded for L-ML inference. However, the ideal implementation of HI is infeasible as the correctness of the S-ML inference is not known to the ED. We thus propose an online meta-learning framework that the ED can use to predict the correctness of the S-ML inference. In particular, we propose to use the probability corresponding to the maximum probability class output by S-ML for a data sample and decide whether to offload it or not. The resulting online learning problem turns out to be a Prediction with Expert Advice (PEA) problem with continuous expert space. For a full feedback scenario, where the ED receives feedback on the correctness of the S-ML once it accepts the inference, we propose the HIL-F algorithm and prove a sublinear regret bound √ n ln(1/λ min )/2 without any assumption on the smoothness of the loss function, where n is the number of data samples and λ min is the minimum difference between any two distinct maximum probability values across the data samples. For a no-local feedback scenario, where the ED does not receive the ground truth for the classification, we propose the HIL-N algorithm and prove that it has O ( n 2/3 ln 1/3 (1/λ min )) regret bound. We evaluate and benchmark the performance of the proposed algorithms for image classification application using four datasets, namely, Imagenette and Imagewoof [1], MNIST [2], and CIFAR-10 [3].

We investigate a binary classification problem in an edge intelligence system where false negatives are more costly than false positives. The system features a compact, locally deployed model, supplemented by a larger, remote model that is accessible via the network, albeit at an offloading cost. For each sample, our system first uses the locally deployed model for inference. Based on the output of the local model, the sample may be offloaded to the remote model. This work aims to understand the fundamental trade-off between classification accuracy and the offloading costs within such a hierarchical inference (HI) system. To optimise this system, we propose an online learning framework that continuously adapts a pair of thresholds on the local model's confidence scores. These thresholds determine the prediction of the local model and whether a sample is classified locally or offloaded to the remote model. We present a closed-form solution for the setting where the local model is calibrated. For the more general case of uncalibrated models, we introduce H2T2, an online two-threshold hierarchical inference policy, and prove it achieves sublinear regret. H2T2 is model-agnostic, requires no training, and learns during the inference phase using limited feedback. Simulations on real-world datasets show that H2T2 consistently outperforms naive and single-threshold HI policies, sometimes even surpassing single-threshold offline optima. The policy also demonstrates robustness to distribution shifts and adapts effectively to mismatched classifiers.