Search

Federated learning (FL) has been considered as a promising paradigm for enabling distributed training/learning in many machine-learning services without revealing users’ local data. Driven by the growing interests in exploiting FL in wireless networks, this paper studies the Non-orthogonal Multiple Access (NOMA) assisted FL in which a group of end-devices (EDs) form a NOMA cluster to send their locally trained models to the cellular base station (BS) for model aggregation. In particular, we consider that the BS adopts wireless power transfer (WPT) to power the EDs (for their data transmission and local training) in each round of FL iteration, and formulate a joint optimization of the BS’s WPT for different EDs, the EDs’ NOMA-transmission for sending the local models to the BS, the BS’s broadcasting of the aggregated model to all EDs, the processing-rates of the BS and EDs, as well as the training-accuracy of the FL, with the objective of minimizing the system-wise cost accounting for the total energy consumption as well as the FL convergence latency. In spite of the strict non-convexity of the joint optimization problem, we analytically characterize the BS’s and all EDs’ optimal processing-rates, based on which we propose a layered algorithm for finding the optimal solutions for the joint optimization problem via exploiting monotonic optimization. Numerical results validate that our algorithm can achieve the optimal solution as LINGO’s global-solver (i.e., a commercial optimization package) while significantly reducing the computation-time. Moreover, the results also demonstrate that our NOMA assisted FL can reduce the system cost compared to the benchmark FL scheme with the fixed local training-accuracy by more than 70% and the conventional frequency division multiple access (FDMA) based FL by 78%. [ABSTRACT FROM AUTHOR]

Full-duplex (FD) mode has great potential in improving the spectral efficiency. Mitigating the effect of self-interference becomes one key for performance enhancement of FD system. This work proposes a novel hybrid duplex scheme where the relay receives information for a fraction of time and simultaneously transmits and receives information for the rest, following a duty cycle. First, we formulate the achievable rate maximization of the proposed scheme as a joint FD duty cycle and source power allocation optimization problem. The optimal FD duty cycle, the optimal source power allocation, and the maximal achievable rate are explicitly given for some cases and characterized in detail for other cases. Then, the proposed scheme is applied to two-hop relaying systems. Specifically, the optimal source power allocation is proved to be a water-filling solution over the FD phase and the receives-only phase on the source-relay link. By dividing the system as low-, medium-, and high-source power cases, the optimal FD duty cycle and the maximal achievable rate are obtained in (approximate) closed-form case-by-case, where the source power thresholds among cases are clearly expressed. Numerical results validate that the proposed hybrid duplex scheme outperforms other benchmark schemes and can improve the achievable rate significantly. [ABSTRACT FROM AUTHOR]

Mobile Edge Computing (MEC) is a promising architecture to reduce the energy consumption of mobile devices and provide satisfactory quality-of-service to time-sensitive services. How to jointly optimize task offloading and resource allocation to minimize the energy consumption subject to the latency requirement remains an open problem, which motivates this paper. When the latency constraint is taken into account, the optimization variables, including offloading ratio, transmission power, and subcarrier and computing resource allocation, are strongly coupled. To address this issue, we first decompose the original problem into three subproblems named as offloading ratio selection, transmission power optimization, and subcarrier and computing resource allocation. Then, we propose an iterative algorithm to deal with them in a sequence. To be specific, we derive the closed-form solution of offloading ratios, employ the equivalent parametric convex programming to obtain the optimal power allocation policy, and deal with subcarrier and computing resource allocation by the primal-dual method. Simulation results demonstrate that the proposed algorithm can save 20%–40% energy compared with the reference schemes, and can converge to local optimal solutions. [ABSTRACT FROM AUTHOR]

The combination of artificial intelligence and mobile edge computing (MEC) is considered as a promising evolution path of the future wireless networks. As a model-level coordination learning paradigm, federated learning can make full use of the distributed computation resource in the MEC systems, which allows the users to keep their private data locally. However, due to the unreliable wireless transmission circumstances and resource constraints in the MEC systems, both the performance and training efficiency of federated learning cannot be guaranteed. To solve this problem, the optimization design of federated learning in the MEC systems is studied in this paper. First, an optimization problem is formulated to manage the tradeoff between model accuracy and training cost. Second, a joint optimization algorithm is designed to optimize the model compression, sample selection, and user selection strategies, which can approach a stationary optimal solution in a computationally efficient way. Finally, the performance of our proposed optimization scheme is evaluated by numerical simulation and experiment results, which show that both the accuracy loss and the cost of federated learning in the MEC systems can be reduced significantly by employing our proposed algorithm. [ABSTRACT FROM AUTHOR]

Mobile edge computing (MEC) has been envisioned as a promising approach for enabling the computation-intensive yet latency-sensitive mobile Internet services in future wireless networks. In this paper, we investigate the secrecy based energy-efficient MEC via cooperative Non-orthogonal Multiple Access (NOMA) transmission. We consider that an edge-computing device (ED) offloads its computation-workload to the edge-computing server (ECS) subject to the overhearing-attack of a malicious eavesdropper. To enhance the secrecy of the ED’s offloading transmission, a group of conventional wireless devices (WDs) are scheduled to form a NOMA-transmission group with the ED for sending data to the cellular base station (BS) while providing cooperative jamming to the eavesdropper. We formulate a joint optimization of the ED’s offloaded workload, transmit-power, NOMA-transmission duration as well as the selection of the WDs, with the objective of minimizing the total energy consumption of the ED and the selected WDs, while subject to the ED’s latency-requirement and the selected WDs’ required data-volumes to deliver. Despite the nature of mixed binary and non-convex programming of the formulated problem, we exploit the vertical decomposition and propose a three-layered algorithm for solving it efficiently. To further address the fairness among different WDs, we investigate a system-wise utility maximization problem that accounts for the fairness in the WDs’ delivered data and the total energy consumption of the ED and WDs. By exploiting our previously designed layered-algorithm, we further propose a stochastic learning based algorithm for determining each WD’s optimal data-volume delivered. Numerical results are provided to validate the effectiveness of our proposed algorithms as well as the performance advantage of the secrecy based computation offloading via NOMA. [ABSTRACT FROM AUTHOR]

By offloading tasks from the mobile device (MD) to its nearby deployed access points (APs), each of which is connected to one server for task processing, computation offloading can strike a balance between MD’s task execution delay and energy consumption in mobile edge computing (MEC) systems. Considering communication and computation dynamics in MEC systems, we aim to design online computation offloading mechanisms in this paper to minimize the time average expected task execution delay under the constraint of average energy consumption. Firstly, with known current channel gains between the MD and APs as well as available computing capability at MEC servers, we leverage the Lyapunov optimization framework to make an optimal one-slot decision on MD’s transmit power allocation and MEC server selection. On this basis, we then consider a more realistic scenario, where it is difficult to capture current available computing capability at MEC servers, and combine the multi-armed bandit framework for an online learning based MEC server selection algorithm. Finally, through theoretical analyses and extensive simulations, we demonstrate the near-optimality and feasibility of our proposed algorithms, and present that our proposed algorithms fully explore the interplay between communication and computation with enriched user experience and reduced energy consumption. [ABSTRACT FROM AUTHOR]

Based on a hierarchical cloud-fog computing-enabled paradigm, fog radio access networks (F-RANs) can provide abundant resource to support the future mobile artificial intelligent services. However, due to the differences of computation and communication capabilities at the cloud computing center, the fog computing based access points (F-APs), and the user devices, it is challenging to propose efficient computation offloading strategies to fully explore the potential of F-RANs. In this paper, we study the design of computation offloading in F-RANs to minimize the total cost with respect to the energy consumption and the offloading latency. In particular, a joint optimization problem is formulated to optimize the offloading decision, the computation and the radio resources allocation. To solve this non-linear and non-convex problem, an iterative algorithm is designed, which can be proved to converge a stationary optimal solution with polynomial computational complexity. Finally, the simulation results are provided to show the performance gains of our proposed joint optimization algorithm. [ABSTRACT FROM AUTHOR]

In 5G heterogeneous networking, it is promising to integrate different wireless networks to provide higher data rate. This paper models the integrated system as a receiver frequency division relay channel (RFDRC) and studies how to improve the transmission rate by combining decode-forward (DF), compress-forward (CF), and amplify-forward (AF) schemes. First, we establish clear criterions on how to select a relay scheme among DF, CF, and AF schemes and prove that the CF outperforms AF for all possible configurations. Based on the scheme selection criterions, we propose a hybrid DF–CF scheme which takes advantage of both DF and CF schemes in RFDRC. A near-optimal resource allocation is presented for the DF–CF-based system, leading to a new achievable rate for RFDRC. For ease of implementation, we further put forward a hybrid DF–AF scheme and reconsider the joint bandwidth and power allocation. Two suboptimal resource allocation solutions are established. In particular, when source frequency band and relay frequency band have equivalent bandwidth, we show that the proposed hybrid DF–AF scheme can achieve the concave envelope of the maximum between DF rate and AF rate. Numerical results show that the proposed schemes bring significant gains for RFDRC. [ABSTRACT FROM AUTHOR]