Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devices

Today, deep learning optimization is primarily driven by research focused on achieving high inference accuracy and reducing latency. However, the energy efficiency aspect is often overlooked, possibly due to a lack of sustainability mindset in the field and the absence of a holistic energy dataset. In this paper, we conduct a threefold study, including energy measurement, prediction, and efficiency scoring, with an objective to foster transparency in power and energy consumption within deep learning across various edge devices. Firstly, we present a detailed, first-of-its-kind measurement study that uncovers the energy consumption characteristics of on-device deep learning. This study results in the creation of three extensive energy datasets for edge devices, covering a wide range of kernels, state-of-the-art DNN models, and popular AI applications. Secondly, we design and implement the first kernel-level energy predictors for edge devices based on our kernel-level energy dataset. Evaluation results demonstrate the ability of our predictors to provide consistent and accurate energy estimations on unseen DNN models. Lastly, we introduce two scoring metrics, PCS and IECS, developed to convert complex power and energy consumption data of an edge device into an easily understandable manner for edge device end-users. We hope our work can help shift the mindset of both end-users and the research community towards sustainability in edge computing, a principle that drives our research. Find data, code, and more up-to-date information at https://amai-gsu.github.io/DeepEn2023.

Software-Defined MIMO OFDM Joint Radar-Communication Platform with Fully Digital mmWave Architecture

Large-scale deployment of connected vehicles with cooperative sensing and maneuvering technologies increases the demand for vehicle-to-everything communication (V2X) band in 5.9 GHz. Besides the V2X spectrum, the under-utilized millimeter-wave (mmWave) bands at 24 and 77 GHz can be leveraged to supplement V2X communication and support high data rates for emerging broadband applications. For this purpose, joint radar-communication (JRC) systems have been proposed in the literature to perform both functions using the same waveform and hardware. In this work, we present a software-defined multiple-input and multiple-output (MIMO) JRC with orthogonal frequency division multiplexing (OFDM) for the 24 GHz mmWave band. We implement a real-time operating full-duplex JRC platform using commercially available software-defined radios and custom-built mmWave front-ends. With fully digital MIMO architecture, we demonstrate simultaneous data transmission and high-resolution radar imaging capabilities of MIMO OFDM JRC in the mmWave band.

Optimal Precoder Design for MIMO-OFDM-based Joint Automotive Radar-Communication Networks

Large-scale deployment of connected vehicles with cooperative awareness technologies increases the demand for vehicle-to-everything (V2X) communication spectrum in 5.9 GHz that is mainly allocated for the exchange of safety messages. To supplement V2X communication and support the high data rates needed by broadband applications, the millimeter-wave (mmWave) automotive radar spectrum at 76-81 GHz can be utilized. For this purpose, joint radar-communication systems have been proposed in the literature to perform both functions using the same waveform and hardware. While multiple-input and multiple-output (MIMO) communication with multiple users enables independent data streaming for high throughput, MIMO radar processing provides high-resolution imaging that is crucial for safety-critical systems. However, employing conventional precoding methods designed for communication generates directional beams that impair MIMO radar imaging and target tracking capabilities during data streaming. In this paper, we propose a MIMO joint automotive radar-communication (JARC) framework based on orthogonal frequency division multiplexing (OFDM) waveform. First, we show that the MIMO-OFDM preamble can be exploited for both MIMO radar processing and estimation of the communication channel. Then, we propose an optimal precoder design method that enables high accuracy target tracking while transmitting independent data streams to multiple receivers. The proposed methods provide high-resolution radar imaging and high throughput capabilities for MIMO JARC networks. Finally, we evaluate the efficacy of the proposed methods through numerical simulations.

Cooperative Perception with Deep Reinforcement Learning for Connected Vehicles

Sensor-based perception on vehicles are becoming prevalent and important to enhance the road safety. Autonomous driving systems use cameras, LiDAR, and radar to detect surrounding objects, while human-driven vehicles use them to assist the driver. However, the environmental perception by individual vehicles has the limitations on coverage and/or detection accuracy. For example, a vehicle cannot detect objects occluded by other moving/static obstacles. In this paper, we present a cooperative perception scheme with deep reinforcement learning to enhance the detection accuracy for the surrounding objects. By using the deep reinforcement learning to select the data to transmit, our scheme mitigates the network load in vehicular communication networks and enhances the communication reliability. To design, test, and verify the cooperative perception scheme, we develop a Cooperative & Intelligent Vehicle Simulation (CIVS) Platform, which integrates three software components: traffic simulator, vehicle simulator, and object classifier. We evaluate that our scheme decreases packet loss and thereby increases the detection accuracy by up to 12%, compared to the baseline protocol.