CARMA: Context-Aware Runtime Reconfiguration for Energy-Efficient Sensor
Fusion
- URL: http://arxiv.org/abs/2306.15748v1
- Date: Tue, 27 Jun 2023 19:00:07 GMT
- Title: CARMA: Context-Aware Runtime Reconfiguration for Energy-Efficient Sensor
Fusion
- Authors: Yifan Zhang, Arnav Vaibhav Malawade, Xiaofang Zhang, Yuhui Li,
DongHwan Seong, Mohammad Abdullah Al Faruque and Sitao Huang
- Abstract summary: We propose CARMA: a context-aware sensor fusion approach that uses context to reconfigure computation flow at runtime.
CARMA significantly reduces the energy used by a multi-sensory object detector without compromising performance.
We evaluate multiple context-identification strategies, propose a novel system-wide energy-performance joint optimization, and evaluate scenario-specific perception performance.
- Score: 11.313017866190622
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Autonomous systems (AS) are systems that can adapt and change their behavior
in response to unanticipated events and include systems such as aerial drones,
autonomous vehicles, and ground/aquatic robots. AS require a wide array of
sensors, deep-learning models, and powerful hardware platforms to perceive and
safely operate in real-time. However, in many contexts, some sensing modalities
negatively impact perception while increasing the system's overall energy
consumption. Since AS are often energy-constrained edge devices,
energy-efficient sensor fusion methods have been proposed. However, existing
methods either fail to adapt to changing scenario conditions or to optimize
energy efficiency system-wide. We propose CARMA: a context-aware sensor fusion
approach that uses context to dynamically reconfigure the computation flow on a
Field-Programmable Gate Array (FPGA) at runtime. By clock-gating unused sensors
and model sub-components, CARMA significantly reduces the energy used by a
multi-sensory object detector without compromising performance. We use a
Deep-learning Processor Unit (DPU) based reconfiguration approach to minimize
the latency of model reconfiguration. We evaluate multiple
context-identification strategies, propose a novel system-wide
energy-performance joint optimization, and evaluate scenario-specific
perception performance. Across challenging real-world sensing contexts, CARMA
outperforms state-of-the-art methods with up to 1.3x speedup and 73% lower
energy consumption.
Related papers
- Federated Learning With Energy Harvesting Devices: An MDP Framework [5.852486435612777]
Federated learning (FL) requires edge devices to perform local training and exchange information with a parameter server.
A critical challenge in practical FL systems is the rapid energy depletion of battery-limited edge devices.
We apply energy harvesting technique in FL systems to extract ambient energy for continuously powering edge devices.
arXiv Detail & Related papers (2024-05-17T03:41:40Z) - Blue and Green-Mode Energy-Efficient Chemiresistive Sensor Array
Realized by Rapid Ensemble Learning [0.5890690947925292]
This study introduces a novel optimization strategy that employs a rapid ensemble learning-based model committee approach.
The strategy identifies the most impactful sensors in a CRS array for accurate classification.
It is validated through theoretical calculations and Monte Carlo simulations, demonstrating its effectiveness and accuracy.
arXiv Detail & Related papers (2024-03-03T23:38:37Z) - Context-aware Multi-Model Object Detection for Diversely Heterogeneous
Compute Systems [0.32634122554914]
One-size-fits-all approach to object detection using deep neural networks (DNNs) leads to inefficient utilization of computational resources.
We propose SHIFT which continuously selects from a variety of DNN-based OD models depending on the dynamically changing contextual information and computational constraints.
Our proposed methodology results in improvements of up to 7.5x in energy usage and 2.8x in latency compared to state-of-the-art GPU-based single model OD approaches.
arXiv Detail & Related papers (2024-02-12T05:38:11Z) - Random resistive memory-based deep extreme point learning machine for
unified visual processing [67.51600474104171]
We propose a novel hardware-software co-design, random resistive memory-based deep extreme point learning machine (DEPLM)
Our co-design system achieves huge energy efficiency improvements and training cost reduction when compared to conventional systems.
arXiv Detail & Related papers (2023-12-14T09:46:16Z) - PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices [10.01838504586422]
The continuous operation of ML-powered systems leads to significant energy use during inference.
This paper investigates how the configuration of on-device hardware-elements such as GPU, memory, and CPU frequency, affects energy consumption for NN inference with regular fine-tuning.
We propose PolyThrottle, a solution that optimize configurations across individual hardware components using Constrained Bayesian Optimization in an energy-conserving manner.
arXiv Detail & Related papers (2023-10-30T20:19:41Z) - Multiagent Reinforcement Learning with an Attention Mechanism for
Improving Energy Efficiency in LoRa Networks [52.96907334080273]
As the network scale increases, the energy efficiency of LoRa networks decreases sharply due to severe packet collisions.
We propose a transmission parameter allocation algorithm based on multiagent reinforcement learning (MALoRa)
Simulation results demonstrate that MALoRa significantly improves the system EE compared with baseline algorithms.
arXiv Detail & Related papers (2023-09-16T11:37:23Z) - FemtoDet: An Object Detection Baseline for Energy Versus Performance
Tradeoffs [27.006082622843653]
Vision applications of convolutional neural networks, such as always-on surveillance cameras, are critical for energy constraints.
This paper aims to serve as a baseline by designing detectors to reach tradeoffs between energy and performance from two perspectives.
arXiv Detail & Related papers (2023-01-17T06:24:08Z) - Movement Penalized Bayesian Optimization with Application to Wind Energy
Systems [84.7485307269572]
Contextual Bayesian optimization (CBO) is a powerful framework for sequential decision-making given side information.
In this setting, the learner receives context (e.g., weather conditions) at each round, and has to choose an action (e.g., turbine parameters)
Standard algorithms assume no cost for switching their decisions at every round, but in many practical applications, there is a cost associated with such changes, which should be minimized.
arXiv Detail & Related papers (2022-10-14T20:19:32Z) - Multi-Point Integrated Sensing and Communication: Fusion Model and
Functionality Selection [99.67715229413986]
This paper presents a multi-point ISAC (MPISAC) system that fuses the outputs from multiple ISAC devices for achieving higher sensing performance.
We adopt a fusion model that predicts the fusion accuracy via hypothesis testing and optimal voting analysis.
arXiv Detail & Related papers (2022-08-16T08:09:54Z) - LEAF + AIO: Edge-Assisted Energy-Aware Object Detection for Mobile
Augmented Reality [77.00418462388525]
Mobile augmented reality (MAR) applications are significantly energy-guzzling.
We design an edge-based energy-aware MAR system that enables MAR devices to dynamically change their configurations.
Our proposed dynamic MAR configuration adaptations can minimize the per frame energy consumption of multiple MAR clients.
arXiv Detail & Related papers (2022-05-27T06:11:50Z) - Energy Aware Deep Reinforcement Learning Scheduling for Sensors
Correlated in Time and Space [62.39318039798564]
We propose a scheduling mechanism capable of taking advantage of correlated information.
The proposed mechanism is capable of determining the frequency with which sensors should transmit their updates.
We show that our solution can significantly extend the sensors' lifetime.
arXiv Detail & Related papers (2020-11-19T09:53:27Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.