Learning Centric Power Allocation for Edge Intelligence

Wang, Shuai; Wang, Rui; Hao, Qi; Wu, Yik Chung; Poor, H. Vincent

doi:10.1109/icc40277.2020.9148872

Cited by 13 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It performs dataset collection which gathers sensing data in various scenarios using dedicated vehicles, dataset annotation which labels the data manually, and model pretraining which outputs initial model parameters w [0] ∈ R W . The number of samples in each scenario is determined via learning curves [20], [21]. The cloud server will transmit w [0] to edge server via the Internet and the edge server further broadcasts w [0] n (t)} either via teacher-student distillation [22] (e.g., road-side units provide labels) or ensemble distillation [23] (e.g., global fusion provides labels).…”

Section: System Architecture and Algorithm Designmentioning

confidence: 99%

Distributed Dynamic Map Fusion via Federated Learning for Intelligent Networked Vehicles

Zhang,

Wang,

Hong

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

The technology of dynamic map fusion among networked vehicles has been developed to enlarge sensing ranges and improve sensing accuracies for individual vehicles. This paper proposes a federated learning (FL) based dynamic map fusion framework to achieve high map quality despite unknown numbers of objects in fields of view (FoVs), various sensing and model uncertainties, and missing data labels for online learning. The novelty of this work is threefold: (1) developing a three-stage fusion scheme to predict the number of objects effectively and to fuse multiple local maps with fidelity scores; (2) developing an FL algorithm which fine-tunes feature models (i.e., representation learning networks for feature extraction) distributively by aggregating model parameters; (3) developing a knowledge distillation method to generate FL training labels when data labels are unavailable. The proposed framework is implemented in the Car Learning to Act (CARLA) simulation platform. Extensive experimental results are provided to verify the superior performance and robustness of the developed map fusion and FL schemes. I. INTRODUCTIONThe intelligent networked vehicle system (INVS) is an emerging vehicle-edge-cloud system that accomplishes cooperative perception, map management, planning and maneuvering tasks via vehicle-to-everything (V2X) communication [1]-[3]. Among all the tasks, distributed map management aims to enlarge sensing ranges and improve sensing accuracies for individual vehicles and plays a central role in . While static maps describe stationary objects (e.g., roads, buildings, and trees), dynamic maps emphasize updating information of mobile objects (e.g., pedestrians, cars, and animals) in real time. Fig. 1 shows the architecture of an intelligent networked vehicle system. There are three main steps for dynamic map fusion: (1) local sensing and perception, (2) local map fusion and uploading, and (3) global map fusion and broadcasting.

show abstract

Section: System Architecture and Algorithm Designmentioning

confidence: 99%

Distributed Dynamic Map Fusion via Federated Learning for Intelligent Networked Vehicles

Zhang,

Wang,

Hong

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, since the collected data samples could be imbalanced among different classes, existing learning accuracy model in [17], [18] is not applicable. To maximize the learning performance under imbalanced data, the proposed sample size model characterizes F-measure as a function of the minority class sample size.…”

Section: B Challenges Of El and Proposed El-ugvmentioning

confidence: 99%

Edge Learning with Unmanned Ground Vehicle: Joint Path, Energy and Sample Size Planning

Liú

Wang

Wen

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Edge learning (EL), which uses edge computing as a platform to execute machine learning algorithms, is able to fully exploit the massive sensing data generated by Internet of Things (IoT). However, due to the limited transmit power at IoT devices, collecting the sensing data in EL systems is a challenging task. To address this challenge, this paper proposes to integrate unmanned ground vehicle (UGV) with EL. With such a scheme, the UGV could improve the communication quality by approaching various IoT devices. However, different devices may transmit different data for different machine learning jobs and a fundamental question is how to jointly plan the UGV path, the devices' energy consumption, and the number of samples for different jobs? This paper further proposes a graph-based path planning model, a network energy consumption model and a sample size planning model that characterizes F-measure as a function of the minority class sample size. With these models, the joint path, energy and sample size planning (JPESP) problem is formulated as a large-scale mixed integer nonlinear programming (MINLP) problem, which is nontrivial to solve due to the highdimensional discontinuous variables related to UGV movement. To this end, it is proved that each IoT device should be served only once along the path, thus the problem dimension is significantly reduced. Furthermore, to handle the discontinuous variables, a tabu search (TS) based algorithm is derived, which converges in expectation to the optimal solution to the JPESP problem. Simulation results under different task scenarios show that our optimization schemes outperform the fixed EL and the full path EL schemes.

show abstract

“…To the best of the authors' knowledge, there is no exact expression of Ψ m (v m ). To this end, an inverse power law model [4], [5], [12], [13], which is supported by statistical mechanics of learning [14], is adopted to approximate Ψ m as…”

Section: System Model and Problem Formulationmentioning

confidence: 99%

“…In general, there are two ways to implement edge model training: centralized training and distributed training. Centralized training collects sensing data generated from IoT devices and trains the learning models at the edge [4], [5]. Distributed training deploys individual learning models at user terminals, and all the users upload their local model parameters periodically to the edge for model aggregation and broadcasting [6].…”

Section: Introductionmentioning

confidence: 99%

Learning Centric Wireless Resource Allocation for Edge Computing: Algorithm and Experiment

Zhou

Hong

Wang

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Edge intelligence is an emerging network architecture that integrates sensing, communication, computing components, and supports various machine learning applications, where a fundamental communication question is: how to allocate the limited wireless resources (such as time, energy) to the simultaneous model training of heterogeneous learning tasks? Existing methods ignore two important facts: 1) different models have heterogeneous demands on training data; 2) there is a mismatch between the simulated environment and the real-world environment. As a result, they could lead to low learning performance in practice. This paper proposes the learning centric wireless resource allocation (LCWRA) scheme that maximizes the worst learning performance of multiple classification tasks. Analysis shows

show abstract

Learning Centric Power Allocation for Edge Intelligence

Cited by 13 publications

References 13 publications

Distributed Dynamic Map Fusion via Federated Learning for Intelligent Networked Vehicles

Distributed Dynamic Map Fusion via Federated Learning for Intelligent Networked Vehicles

Edge Learning with Unmanned Ground Vehicle: Joint Path, Energy and Sample Size Planning

Learning Centric Wireless Resource Allocation for Edge Computing: Algorithm and Experiment

Contact Info

Product

Resources

About