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

Zhou, Liangkai; Hong, Yuncong; Wang, Shuai; Han, Ruihua; Li, Dachuan; Wang, Rui; Hao, Qi

doi:10.1109/tvt.2020.3047149

Cited by 20 publications

(9 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data samples are assumed to be independent and identically distributed. Therefore, the relationship between the learning error e n and the number of data samples x n can be depicted by the widely adopted inverse power law model in [12], [31]- [34], which is supported by statistical mechanics of learning [35] and expressed as…”

Section: A Model Training Processmentioning

confidence: 99%

“…Output: the optimal transmission rates {r * i } and durations {T * i }. Update v b according to (34).…”

Section: B Objectives Merging For the Case Of Bursty Data Arrivalmentioning

confidence: 99%

“…In particular, collecting more samples for model training can improve the learning performance especially when the server is at a shortage of data, while the data transmission brings extra energy consumption. Such effects lead to a tradeoff between the learning accuracy and energy consumption, where the former is characterized as a well-known classification error model in [12], [31]- [34] supported by the learning theory [35], and the latter is based on the Shannon's theory. To achieve learningand-energy efficient (LEE) EI, the data partition and rate control for long-term transmission are jointly designed in this paper.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Data Partition and Rate Control for Learning and Energy Efficient Edge Intelligence

Li¹,

Wang²,

Zhu³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

The rapid development of artificial intelligence together with the powerful computation capabilities of the advanced edge servers make it possible to deploy learning tasks at the wireless network edge, which is dubbed as edge intelligence (EI). The communication bottleneck between the data resource and the server results in deteriorated learning performance as well as tremendous energy consumption.To tackle this challenge, we explore a new paradigm called learning-and-energy-efficient (LEE) EI, which simultaneously maximizes the learning accuracies and energy efficiencies of multiple tasks via data partition and rate control. Mathematically, this results in a multi-objective optimization problem.Moreover, the continuous varying rates over the whole transmission duration introduce infinite variables.To solve this complex problem, we consider the case with infinite server buffer capacity and oneshot data arrival at sensor. First, the number of variables are reduced to a finite level by exploiting the optimality of constant-rate transmission in each epoch. Second, the optimal solution is found by applying stratified sequencing or objectives merging. By assuming higher priority of learning efficiency in stratified sequencing, the closed form of optimal data partition is derived by the Lagrange method, while the optimal rate control is proved to have the structure of directional water filling (DWF), based on which a string-pulling (SP) algorithm is proposed to obtain the numerical values. The DWF structure of rate control is also proved to be optimal in objectives merging via weighted summation. By exploiting the optimal rate changing properties, the SP algorithm is further extended to account for the cases with limited server buffer capacity or bursty data arrival at sensor. The performance of the proposed joint data partition and rate control design is examined by extensive experiments based on public datasets.

show abstract

Section: A Model Training Processmentioning

confidence: 99%

“…Output: the optimal transmission rates {r * i } and durations {T * i }. Update v b according to (34).…”

Section: B Objectives Merging For the Case Of Bursty Data Arrivalmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Data Partition and Rate Control for Learning and Energy Efficient Edge Intelligence

Li¹,

Wang²,

Zhu³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…If local computing is available at the devices, federated learning can be adopted, where all the devices update and upload their local learning model parameters periodically to the edge server for model training [4]- [6]. On the other hand, if local computing is not available, centralized learning is required, where devices need to upload the sensing data to the edge server via wireless communications [7]- [9]. This is typically the case in sensor networks where the energy and computation resources at the devices are rather limited.…”

Section: Introductionmentioning

confidence: 99%

“…In [8], the path, power, and sample amount planning for unmanned ground vehicles were optimized to maximize the learning performance in centralized edge intelligence systems. In [9], robotic experiments were carried out to verify the effectiveness of robustness T. Zhang, S. Wang, G. Li, F. Liu, and R. Wang are with the Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China. (Email: {zhangt7, wangs3, ligl2020, liuf6, wang.r}@sustech.edu.cn.)…”

Section: Introductionmentioning

confidence: 99%

Accelerating Edge Intelligence via Integrated Sensing and Communication

Zhang¹,

Wang²,

Li³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Realizing edge intelligence consists of sensing, communication, training, and inference stages. Conventionally, the sensing and communication stages are executed sequentially, which results in excessive amount of dataset generation and uploading time. This paper proposes to accelerate edge intelligence via integrated sensing and communication (ISAC). As such, the sensing and communication stages are merged so as to make the best use of the wireless signals for the dual purpose of dataset generation and uploading. However, ISAC also introduces additional interference between sensing and communication functionalities. To address this challenge, this paper proposes a classification error minimization formulation to design the ISAC beamforming and time allocation. Globally optimal solution is derived via the rank-1 guaranteed semidefinite relaxation, and performance analysis is performed to quantify the ISAC gain. Simulation results are provided to verify the effectiveness of the proposed ISAC scheme. Interestingly, it is found that when the sensing time dominates the communication time, ISAC is always beneficial. However, when the communication time dominates, the edge intelligence with ISAC scheme may not be better than that with the conventional scheme, since ISAC introduces harmful interference between the sensing and communication signals.

show abstract

Pushing AI to wireless network edge: an overview on integrated sensing, communication, and computation towards 6G

Zhu

Lyu

Xiang

et al. 2023

Sci. China Inf. Sci.

View full text Add to dashboard Cite

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

Cited by 20 publications

References 22 publications

Data Partition and Rate Control for Learning and Energy Efficient Edge Intelligence

Data Partition and Rate Control for Learning and Energy Efficient Edge Intelligence

Accelerating Edge Intelligence via Integrated Sensing and Communication

Pushing AI to wireless network edge: an overview on integrated sensing, communication, and computation towards 6G

Contact Info

Product

Resources

About