Federated Learning (FL) is a promising machine learning paradigm to cooperatively train a global model with highly distributed data located on mobile devices. Aiming to optimize the communication efficiency for gradient aggregation and model synchronization among large-scale devices, we propose a relay-assisted FL framework. By breaking the traditional transmission-order constraint and exploiting the broadcast characteristic of relay nodes, we design a novel synchronization scheme named Partial Synchronization Parallel (PSP), in which models and gradients are transmitted simultaneously and aggregated at relay nodes, resulting in traffic reduction. We prove that PSP has the same convergence rate as the sequential synchronization approaches via rigorous analysis. To further accelerate the training process, we integrate PSP with any unbiased and error-bounded compression technologies and prove that the convergence properties of the resulting scheme still hold. Extensive experiments are conducted in a distributed cluster environment with real-world datasets and the results demonstrate that our proposed approach reduces the training time up to 37 percent compared to state-of-the-art methods.

As a variation of random linear network coding, segmented network coding (SNC) has attracted great interest in data dissemination over lossy networks due to its low computational cost. In order to guarantee the success of decoding, SNC can adopt a feedbackless forward error correction (FEC) approach by applying a linear block code to the input packets before segmentation at the source node. In particular, if the empirical rank distribution of transfer matrices of segments is known in advance, several classes of coded SNC can achieve close-to-optimal decoding performance. However, the empirical rank distribution in the absence of feedback has been little investigated yet, making the whole performance of the FEC approach unknown. To close this gap, in this paper, we present the first comprehensive study on the transmission scheduling issue for the FEC approach, aiming at optimizing the rank distribution of transfer matrices with little control overhead. We propose an efficient adaptive scheduling framework for coded SNC in lossy unicast networks. This framework is one-sided (i.e., each network node forwards the segments adaptively only according to its own state) and scalable (i.e., its buffer cost will not keep on growing when the number of input packets goes to infinity). The performance of the framework is further optimized based on a linear programming approach. Extensive numerical results show that our framework performs near-optimally with respect to the empirical rank distribution.

Caching popular videos at mobile edge servers (MESs) has been confirmed as a promising method to improve mobile users (MUs) perceived quality of experience (QoE) and to alleviate the server load. However, with the multiple bitrate encoding techniques prevalently employed in modern streaming services, caching deployment is challenging for the following three facts: (1) cooperative caching should be explored for MUs located at overlapped coverage areas of MESs; (2) there exists tradeoff consideration for caching either high bitrate videos or high diversity videos; and (3) the relationship between MU perceived QoE and MU received bitrate, known as QoE function, varies in different services. Aiming to maximize the MU perceived QoE, we formulate the multiple bitrate video caching problem, and prove this problem is NP-hard for any given positive and strictly increasing QoE function. We then propose a polynomial complexity algorithm based on a general QoE function, which can achieve an approximate ratio arbitrarily close to 1/2. Specifically, for a linear QoE function, we explore useful property of optimal solutions, based on which more efficient algorithms are proposed. We demonstrate the effectiveness of our solutions via both theoretical analysis and extensive simulations.

Efficient communication through a multi-hop network with packet loss requires random linear network coding schemes with low computation cost and high throughput. In this paper, we propose a low-density parity-check (LDPC)-based framework for constructing chunked code, a variation of random linear network code with low encoding/decoding computational cost and small coefficient vector overhead. Two classes of chunked codes with LDPC structures, named uniform LDPC-chunked codes and overlapped LDPC-chunked (OLC) codes, are studied under a general chunk transfer matrix model. ULC codes achieve rates close to the optimum and perform better than existing chunked codes that employ parity-check constraints. OLC codes are overlapped chunked codes, where it is not necessary to generate new packets for encoding, and demonstrate much higher rates in certain scenarios than the state-of-the-art designs of overlapped chunked codes. These results justifies the feasibility of this LDPC approach for communication through multi-hop networks with packet loss.

As a key enabling technology for 5G, network function virtualization abstracts services into software-based service function chains (SFCs), facilitating mission-critical services with high-reliability requirements. However, it is challenging to cost-effectively provide reliable SFCs in dynamic environments due to delayed rewards caused by future SFC requests, limited infrastructure resources, and heterogeneity in hardware and software reliability. Although deep reinforcement learning (DRL) can effectively capture delayed rewards in dynamic environments, its trial-and-error exploration in a vast solution space with massive infeasible solutions may lead to frequent constraint violations and traps in poor local optima. To address these challenges, we propose a RuleDRL algorithm that combines the capability of DRL to capture delayed rewards and the strength of rule-based schemes to explore high-quality solutions without violating constraints. Specifically, we first formulate the reliable SFC provision problem as an integer nonlinear programming problem, which is proven to be NP-hard. Then, we jointly design DRL and rule-based schemes that are coupled to make the final decision and establish a bounded approximation ratio in general cases. Extensive trace-driven simulations show that RuleDRL can save the total cost by up to 65.67% and improve the SFC acceptance ratio by up to 82%, compared to the state-of-the-art solution.

Lightweight and layered structure containers in serverless edge computing (SEC) provide flexible service configurations and computing for vehicles with diverse service requests in the Vehicle-Infrastructure Collaboration (VIC) environment. Despite progress in service request scheduling for the VIC system, the effect of layer sharing between different service images on request scheduling has not been fully explored. Additionally, the cold-start latency of service containers in SEC can significantly degrade the responsiveness of vehicle services, and container retention is proposed to minimize its impact and improve overall system performance. However, the existing research neglects the complex coupling relationship between request scheduling and container retention decisions, while focusing on the single decision optimization problem. Consequently, minimizing system costs by single decision optimization may not achieve the effect of joint decision optimization. To bridge this gap, we study the joint service request scheduling and container retention problem based on layer sharing and container caching. First, we model the joint decision problem with specific constraints and aim to minimize the long-term system cost while considering vehicle mobility. Second, an online co-decision scheme called Onco is proposed to solve the problem, which incorporates request scheduling and container retention for multiple vehicle services. Finally, both synthetic and real trace-driven simulation experiments have been conducted to evaluate the performance of Onco. The experimental results show that Onco outperforms state-of-the-art baselines in terms of system cost reduction and response time improvement.