To meet the requirements of the artificial internet of things (AIoT), decentralization is essential to provide wide coverage, trustworthiness, and low-latency communication. For this purpose, decentralized federated learning (DFL) has rapidly evolved and gained popularity in recent years by reducing reliance on a central server and promoting a more robust, scalable, and privacy-preserving system. Nevertheless, the exchange of model updates and gradients in peer-to-peer (P2P) wireless communication systems introduces new vulnerabilities that threaten both model performance and data security, while frequent P2P communication among clients can lead to high communication costs. To address these issues, in this work, we develop a communicationefficient and security-enhanced DFL algorithm, which integrates the fast incremental alternating direction method of multipliers (FI-ADMM) algorithm with parameter-selective additively homomorphic encryption. Additionally, by introducing a first-order approximation for primal updates and rearranging the update order in FI-ADMM, the proposed method is superior to the other benchmarks in terms of computational and time complexity, which is validated by theoretical analysis and simulations.

Machine learning (ML) is a key technique for big-data-driven modelling and analysis of massive Internet of Things (IoT) based intelligent and ubiquitous computing. For fast-increasing applications and data amounts, distributed learning is a promising emerging paradigm since it is often impractical or inefficient to share/aggregate data to a centralized location from distinct ones. This paper studies the problem of training an ML model over decentralized systems, where data are distributed over many user devices and the learning algorithm run on-device, with the aim of relaxing the burden at a central entity/server. Although gossip-based approaches have been used for this purpose in different use cases, they suffer from high communication costs, especially when the number of devices is large. To mitigate this, incremental-based methods are proposed. We first introduce incremental block-coordinate descent (I-BCD) for the decentralized ML, which can reduce communication costs at the expense of running time. To accelerate the convergence speed, an asynchronous parallel incremental BCD (API-BCD) method is proposed, where multiple devices/agents are active in an asynchronous fashion. We derive convergence properties for the proposed methods. Simulation results also show that our API-BCD method outperforms state of the art in terms of running time and communication costs.

Edge computing provides a promising paradigm to support the implementation of Internet of Things (IoT) by offloading tasks to nearby edge nodes. Meanwhile, the increasing network size makes it impractical for centralized data processing due to limited bandwidth, and consequently a decentralized learning scheme is preferable. Reinforcement learning (RL) has been widely investigated and shown to be a promising solution for decision-making and optimal control processes. For RL in a decentralized setup, edge nodes (agents) connected through a communication network aim to work collaboratively to find a policy to optimize the global reward as the sum of local rewards. However, communication costs, scalability, and adaptation in complex environments with heterogeneous agents may significantly limit the performance of decentralized RL. Alternating direction method of multipliers (ADMM) has a structure that allows for decentralized implementation and has shown faster convergence than gradient descent-based methods. Therefore, we propose an adaptive stochastic incremental ADMM (asI-ADMM) algorithm and apply the asI-ADMM to decentralized RL with edge-computing-empowered IoT networks. We provide convergence properties for the proposed algorithms by designing a Lyapunov function and prove that the asI-ADMM has$\mathcal {O}(1/k) + \mathcal {O}(1/M)$convergence rate, where$k$and$M$are the number of iterations and batch samples, respectively. Then, we test our algorithm with two supervised learning problems. For performance evaluation, we simulate two applications in decentralized RL settings with homogeneous and heterogeneous agents. The experimental results show that our proposed algorithms outperform the state of the art in terms of communication costs and scalability and can well adapt to complex IoT environments.

Big data, including applications with high security requirements, are often collected and stored on multiple heterogeneous devices, such as mobile devices, drones, and vehicles. Due to the limitations of communication costs and security requirements, it is of paramount importance to analyze information in a decentralized manner instead of aggregating data to a fusion center. To train large-scale machine learning models, edge/fog computing is often leveraged as an alternative to centralized learning. We consider the problem of learning model parameters in a multiagent system with data locally processed via distributed edge nodes. A class of minibatch stochastic alternating direction method of multipliers (ADMMs) algorithms is explored to develop the distributed learning model. To address two main critical challenges in distributed learning systems, i.e., communication bottleneck and straggler nodes (nodes with slow responses), error-control-coding-based stochastic incremental ADMM is investigated. Given an appropriate minibatch size, we show that the minibatch stochastic ADMM-based method converges in a rate of O(1/√k), where k denotes the number of iterations. Through numerical experiments, it is revealed that the proposed algorithm is communication efficient, rapidly responding, and robust in the presence of straggler nodes compared with state-of-the-art algorithms.

The alternating direction method of multipliers (ADMM) has recently been recognized as a promising approach for large-scale machine learning models. However, very few results study ADMM from the aspect of communication costs, especially jointly with privacy preservation. We investigate the communication efficiency and privacy of ADMM in solving the consensus optimization problem over decentralized networks. We first propose incremental ADMM (I-ADMM), the updating order of which follows a Hamiltonian cycle. To protect privacy for agents against external eavesdroppers, we investigate I-ADMM with privacy preservation, where randomized initialization and step size perturbation are adopted. Using numerical results from simulations, we demonstrate that the proposed I-ADMM with step size perturbation can be both communication efficient and privacy preserving.

Wireless content caching in cellular networks is an efficient way to reduce the service delay and alleviate backhaul pressure. For the benefits of sharing spectral and storage resources, clustering in cached networks has recently attracted significant research interests. Meanwhile, since the multimedia content (e.g., video) of caching networks may require a huge transmission rates, millimeter wave (mmWave) communication is considered to be an efficient transmission scheme for cache-enabled networks. We investigate the ergodic rate and average service delay for typical user terminal (UT) in the clustered cache-enabled small cell networks (SCN) and ultra dense networks (UDN) with mmWave channels. In SCN, each cluster consists of cache-enabled UTs, and in the UDN a cluster is formed by cache-enabled UTs and small base stations (SBSs) with non-uniform caching capacity. The clusters are assumed to be discs and content sharing is only possible within clusters through mmWave device-to-device (D2D) tier and SBS tier communications. With stochastic geometry methods, the distributions of content sharing distance and signal-to-interference-noise-ratio (SINR) of typical UT in a cluster are derived for both SCN and UDN scenarios. To minimize the average service delay in high SINR region, we provide an algorithm to jointly optimize caching scheme for SBSs and UTs. By simulations, we validate our theoretical analysis and the performance of proposed caching scheme. The numerical results also show that there exists best radius in the design of cluster for UDNs.

Content caching at small base stations has been considered as an efficient way to alleviate the use of expensive backhauling. In this paper, we study the caching content update for a cache- enabled heterogeneous network. Through analyzing a benchmark content update policy, the problem of content consistency, which is caused by the distinct update time at each caching entity, is firstly revealed. As well, the close form representation of the consistency probability in a mobile environment is derived. Furthermore, a deterministic content update strategy is investigated, where the trade-off between consistency probability and storage cost is characterized. Detailed simulations are provided to support our analysis, as well as present the impacts of moving speed of mobile terminals and transmission bandwidth for content delivery on the consistency performance.

We study a mobility prediction based proactive wireless caching scheme for two-tier cellular networks consisting of a base station (BS) tier and a device-to-device (D2D) tier. Two scenarios are considered: popular contents cached only at BSs, and popular contents cached at both BSs and MTs. We model user mobility as a Markov renewal process to predict user moving paths and residence time. Then we analyse the hit-rate performance to evaluate the presented schemes. By formulating content placement to maximize the hit-rate as optimization problems, we provide the optimal solution for the first scenario and develop a greedy mobility prediction based proactive wireless caching (MPPC) scheme for the second. Through analysis we show that the hit-rate achieved by MPPC is at least exp(1)-1/exp(1) of the optimal hit-rate. The numeric results show that the MPPC can dramatically improve the hit-rate performance, compared with random caching and most popular caching (MPC) schemes. We show that the hit-rate achieved by MPPC outperformances MPC by 26% at most when MTs are not able to cache. Besides we present the impact of the moving speed on the hit-rate performance of MPPC for MTs.

Wireless caching enables popular files to be stored at the base stations (BSs) in advance, which has been considered as an efficient way to reduce the service delay and alleviate heavy burdens on the backhaul links. In this paper, we study the BS clustering scheme for the cooperative wireless caching networks (CWCNs) with heterogeneous file preference among users and BSs, and propose the minimum cost (MC) based clustering scheme. We first introduce the weight-based cost function, which characterizes the trade-off between service delay and transmission cost, and then formulate the clustering as the optimization problem. Furthermore, two clustering algorithms are developed to solve the optimization problem. The results show that the proposed scheme can achieve lower cost compared with random clustering scheme.

In this letter, we present a rotation-aided arctangent phase discriminator (RaAPD) with one-bit analog-to-digital conversion. Different from the existing digital phase discriminator (DPD) and noise-balanced digital phase discriminator (NB-DPD), the proposed RaAPD can achieve higher accuracy and better noise robust features through utilizing an extra rotation channel in the arctangent phase discriminator (APD). Experimental results show that RaAPD achieves 98.3%, 79.3%, and 79.4% reduction in terms of the average root-mean-square error of phase estimation with the signal noise ratio range [-20 dB, 20 dB] and a 16.384-MHz sampling frequency comparing to DPD, NB-DPD, and APD, respectively.