skip to main content


Title: Optimal Policy for Deployment of Machine Learning Models on Energy-Bounded Systems
With the recent advances in both machine learning and embedded systems research, the demand to deploy computational models for real-time execution on edge devices has increased substantially. Without deploying computational models on edge devices, the frequent transmission of sensor data to the cloud results in rapid battery draining due to the energy consumption of wireless data transmission. This rapid power dissipation leads to a considerable reduction in the battery lifetime of the system, therefore jeopardizing the real-world utility of smart devices. It is well-established that for difficult machine learning tasks, models with higher performance often require more computation power and thus are not power-efficient choices for deployment on edge devices. However, the trade-offs between performance and power consumption are not well studied. While numerous methods (e.g., model compression) have been developed to obtain an optimal model, these methods focus on improving the efficiency of a single model. In an entirely new direction, we introduce an effective method to find a combination of multiple models that are optimal in terms of power-efficiency and performance by solving an optimization problem in which both performance and power consumption are taken into account. Experimental results demonstrate that on the ImageNet dataset, we can achieve a 20% energy reduction with only 0.3% accuracy drop compared to Squeeze-and-Excitation Networks. Compared to a pruned convolutional neural network for human activity recognition, while consuming 1.7% less energy, our proposed policy achieves 1.3% higher accuracy.  more » « less
Award ID(s):
1750679
PAR ID:
10222889
Author(s) / Creator(s):
;
Date Published:
Journal Name:
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
Page Range / eLocation ID:
3422 to 3429
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. The ever increasing size of deep neural network (DNN) models once implied that they were only limited to cloud data centers for runtime inference. Nonetheless, the recent plethora of DNN model compression techniques have successfully overcome this limit, turning into a reality that DNN-based inference can be run on numerous resource-constrained edge devices including mobile phones, drones, robots, medical devices, wearables, Internet of Things devices, among many others. Naturally, edge devices are highly heterogeneous in terms of hardware specification and usage scenarios. On the other hand, compressed DNN models are so diverse that they exhibit different tradeoffs in a multi-dimension space, and not a single model can achieve optimality in terms of all important metrics such as accuracy, latency and energy consumption. Consequently, how to automatically select a compressed DNN model for an edge device to run inference with optimal quality of experience (QoE) arises as a new challenge. The state-of-the-art approaches either choose a common model for all/most devices, which is optimal for a small fraction of edge devices at best, or apply device-specific DNN model compression, which is not scalable. In this paper, by leveraging the predictive power of machine learning and keeping end users in the loop, we envision an automated device-level DNN model selection engine for QoE-optimal edge inference. To concretize our vision, we formulate the DNN model selection problem into a contextual multi-armed bandit framework, where features of edge devices and DNN models are contexts and pre-trained DNN models are arms selected online based on the history of actions and users' QoE feedback. We develop an efficient online learning algorithm to balance exploration and exploitation. Our preliminary simulation results validate our algorithm and highlight the potential of machine learning for automating DNN model selection to achieve QoE-optimal edge inference. 
    more » « less
  2. Advances in integrated sensors and low-power electronics have led to an increase in the use of wearable devices for health and activity monitoring applications. These devices have severe limitations on weight, form-factor, and battery size since they have to be comfortable to wear. Therefore, they must minimize the total platform energy consumption while satisfying functionality (e.g., accuracy) and performance requirements. Optimizing the platform-level energy efficiency requires considering both the sensor and processing subsystems. To this end, this paper presents a sensor-classifier co-optimization technique with human activity recognition as a driver application. The proposed technique dynamically powers down the accelerometer sensors and controls their sampling rate as a function of the user activity. It leads to a 49% reduction in total platform energy consumption with less than 1% decrease in activity recognition accuracy. 
    more » « less
  3. Autonomous mobile robots (AMRs) have the capability to execute a wide range of tasks with minimal human intervention. However, one of the major limitations of AMRs is their limited battery life, which often results in interruptions to their task execution and the need to reach the nearest charging station. Optimizing energy consumption in AMRs has become a critical challenge in their deployment. Through empirical studies on real AMRs, we have identified a lack of coordination between computation and control as a major source of energy inefficiency. In this paper, we propose a comprehensive energy prediction model that provides real-time energy consumption for each component of the AMR. Additionally, we propose three path models to address the obstacle avoidance problem for AMRs. To evaluate the performance of our energy prediction and path models, we have developed a customized AMR called Donkey, which has the capability for fine-grained (millisecond-level) end-to-end power profiling. Our energy prediction model demonstrated an accuracy of over 90% in our evaluations. Finally, we applied our energy prediction model to obstacle avoidance and guided energy-efficient path selection, resulting in up to a 44.8% reduction in energy consumption compared to the baseline. 
    more » « less
  4. Binary neural networks (BNNs) substitute complex arithmetic operations with simple bit-wise operations. The binarized weights and activations in BNNs can drastically reduce memory requirement and energy consumption, making it attractive for edge ML applications with limited resources. However, the severe memory capacity and energy constraints of low-power edge devices call for further reduction of BNN models beyond binarization. Weight pruning is a proven solution for reducing the size of many neural network (NN) models, but the binary nature of BNN weights make it difficult to identify insignificant weights to remove. In this paper, we present a pruning method based on latent weight with layer-level pruning sensitivity analysis which reduces the over-parameterization of BNNs, allowing for accuracy gains while drastically reducing the model size. Our method advocates for a heuristics that distinguishes weights by their latent weights, a real-valued vector used to compute the pseudogradient during backpropagation. It is tested using three different convolutional NNs on the MNIST, CIFAR-10, and Imagenette datasets with results indicating a 33%--46% reduction in operation count, with no accuracy loss, improving upon previous works in accuracy, model size, and total operation count. 
    more » « less
  5. Battery life is an increasingly urgent challenge for today's untethered VR and AR devices. However, the power efficiency of head-mounted displays is naturally at odds with growing computational requirements driven by better resolution, refresh rate, and dynamic ranges, all of which reduce the sustained usage time of untethered AR/VR devices. For instance, the Oculus Quest 2, under a fully-charged battery, can sustain only 2 to 3 hours of operation time. Prior display power reduction techniques mostly target smartphone displays. Directly applying smartphone display power reduction techniques, however, degrades the visual perception in AR/VR with noticeable artifacts. For instance, the "power-saving mode" on smartphones uniformly lowers the pixel luminance across the display and, as a result, presents an overall darkened visual perception to users if directly applied to VR content. Our key insight is that VR display power reduction must be cognizant of the gaze-contingent nature of high field-of-view VR displays. To that end, we present a gaze-contingent system that, without degrading luminance, minimizes the display power consumption while preserving high visual fidelity when users actively view immersive video sequences. This is enabled by constructing 1) a gaze-contingent color discrimination model through psychophysical studies, and 2) a display power model (with respect to pixel color) through real-device measurements. Critically, due to the careful design decisions made in constructing the two models, our algorithm is cast as a constrained optimization problem with a closed-form solution, which can be implemented as a real-time, image-space shader. We evaluate our system using a series of psychophysical studies and large-scale analyses on natural images. Experiment results show that our system reduces the display power by as much as 24% (14% on average) with little to no perceptual fidelity degradation. 
    more » « less