Lyapunov-Based Optimization of Edge Resources for Energy-Efficient Adaptive Federated Learning

Battiloro, Claudio; Lorenzo, Paolo Di; Merluzzi, Mattia; Barbarossa, Sergio

doi:10.1109/tgcn.2022.3186879

Cited by 21 publications

(9 citation statements)

References 50 publications

(92 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indeed, we do not formulate a problem in which communication KPIs are explicitly taken into account, but they are rather controlled by learning and adaptation to communication policies that achieve target levels of goal-effectiveness. In this context, let us denote by π comm a communication policy entailing, in the most general case: i) source encoding (e.g., data compression schemes) [22], [23]; ii) modulation and channel coding [36]; iii) wireless channel scheduling, including node participation selection [37] and association [38] ; iv) multiple antenna transmission scheme, devising power allocation and precoding [39]. Moreover, let us denote by π comp a computation policy entailing, in the most general case: i) local computing resource scheduling at each device/agent; ii) computation resource scheduling at shared computing units (e.g., in MEHs) [40]- [42]; iii) selection of a single one or multiple collaborative AI agents containing relevant ML models for ensemble-based inferencing [21], [43] or federated learning [37].…”

Section: Identifying Goal-achieving Communication Kpismentioning

confidence: 99%

6G goal-oriented communications: How to coexist with legacy systems?

Merluzzi¹,

Filippou²,

Baltar³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>6G will connect heterogeneous intelligent agents to make them natively operate complex cooperative tasks. When connecting intelligence, two main research questions arise to identify how artificial intelligence and machine learning models behave depending on: i) their input data quality, affected by errors induced by interference and additive noise during wireless communication; ii) their contextual effectiveness and resilience to interpret and exploit the meaning behind the data. Both questions are within the realm of semantic and goal-oriented communications. With this paper we investigate on how to effectively share communication spectrum resources between a legacy communication systems (i.e., data-oriented) and a new goal-oriented edge intelligence one. Specifically, we address the scenario of an enhanced Mobile Broadband (eMBB) service, i.e., a user uploading a video stream to a radio access point, interfering with an edge inference system, in which a user uploads images to a Mobile Edge Host that runs a classification task. Our objective is to achieve, through cooperation, the eMBB service highest data rate, subject to a target goal-effectiveness of the edge inference service, namely the probability of confident inference on time. We first formalize a general definition of goal in the context of wireless communications. This includes the goal-effectiveness, (i.e., the goal achievability rate, or the probability of achieving the goal), as well as that of goal cost (i.e., the network resource consumption needed to achieve the goal with target effectiveness). We argue and show, through numerical evaluations, that communication reliability and goal-effectiveness are not straightforwardly linked. Then, after a performance evaluation aiming to clarify the difference between communication performance and goal-effectiveness, a long-term optimization problem is formulated and solved via Lyapunov stochastic network optimization tools, to guarantee the desired target performance. Finally, our numerical results assess the advantages of the proposed optimization, and the superiority of the goal-oriented strategy against baseline 5G compliant legacy approaches, under both stationary and non-stationary communication (and computation) environments. </p>

show abstract

Section: Identifying Goal-achieving Communication Kpismentioning

confidence: 99%

6G goal-oriented communications: How to coexist with legacy systems?

Merluzzi¹,

Filippou²,

Baltar³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…However, moving towards millimeter-wave and THz communications, poor channel conditions due to mobility, dynamics of the environment, and blocking events, might severely hinder the performance of MEC systems. In this context, a strong performance boost can be achieved with the advent of RISs, which enable programmability and adaptivity of the wireless propagation environment, by dynamically creating service boosted areas where EE, latency, and reliability can be traded to meet temporary and location-dependent requirements of MEC systems [21], [22], [23]. Figure 3 depicts an RIS-enabled MEC system, where RISs are deployed to establish the wireless connections of two UEs with the edge server, via a BS which is backhaul connected with it.…”

Section: ) Ris-empowered Multi-access Edge Computingmentioning

confidence: 99%

RIS-Enabled Smart Wireless Environments: Deployment Scenarios, Network Architecture, Bandwidth and Area of Influence

Alexandropoulos¹,

Phan-Huy²,

Katsanos³

et al. 2023

Preprint

View full text Add to dashboard Cite

Reconfigurable Intelligent Surfaces (RISs) constitute the key enabler for programmable electromagnetic propagation environments, and are lately being considered as a candidate physical-layer technology for the demanding connectivity, reliability, localization, and sustainability requirements of next generation wireless networks. In this paper, we first present the deployment scenarios for RISenabled smart wireless environments that have been recently designed within the ongoing European Union Horizon 2020 RISE-6G project, as well as a network architecture integrating RISs with existing standardized interfaces. We identify various RIS deployment strategies and sketch the core architectural

show abstract

“…At the server side, let

denote the latency of the server in global iteration t , which can be written as:

where

is the quantity of processing cycles required to carry out a single summation operation [ 16 ].…”

Section: System Model and Problem Formulationmentioning

confidence: 99%

“…Hence, the need for long-term optimization that accounts for the interconnectedness of global iterations becomes evident. Numerous research efforts [ 14 , 15 , 16 , 17 , 18 ] have targeted long-term optimization in federated learning, focusing on various aspects of the problem. For instance, Ref.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Joint Client Selection and CPU Frequency Control in Wireless Federated Learning Networks with Power Constraints

Zhou

Shi

Wang

et al. 2023

Entropy

View full text Add to dashboard Cite

Federated learning (FL) represents a distributed machine learning approach that eliminates the necessity of transmitting privacy-sensitive local training samples. However, within wireless FL networks, resource heterogeneity introduces straggler clients, thereby decelerating the learning process. Additionally, the learning process is further slowed due to the non-independent and identically distributed (non-IID) nature of local training samples. Coupled with resource constraints during the learning process, there arises an imperative need for optimizing client selection and resource allocation strategies to mitigate these challenges. While numerous studies have made strides in this regard, few have considered the joint optimization of client selection and computational power (i.e., CPU frequency) for both clients and the edge server during each global iteration. In this paper, we initially define a cost function encompassing learning latency and non-IID characteristics. Subsequently, we pose a joint client selection and CPU frequency control problem that minimizes the time-averaged cost function subject to long-term power constraints. By utilizing Lyapunov optimization theory, the long-term optimization problem is transformed into a sequence of short-term problems. Finally, an algorithm is proposed to determine the optimal client selection decision and corresponding optimal CPU frequency for both the selected clients and the server. Theoretical analysis provides performance guarantees and our simulation results substantiate that our proposed algorithm outperforms comparative algorithms in terms of test accuracy while maintaining low power consumption.

show abstract

Lyapunov-Based Optimization of Edge Resources for Energy-Efficient Adaptive Federated Learning

Cited by 21 publications

References 50 publications

6G goal-oriented communications: How to coexist with legacy systems?

6G goal-oriented communications: How to coexist with legacy systems?

RIS-Enabled Smart Wireless Environments: Deployment Scenarios, Network Architecture, Bandwidth and Area of Influence

Joint Client Selection and CPU Frequency Control in Wireless Federated Learning Networks with Power Constraints

Contact Info

Product

Resources

About