Wireless power transfer (WPT) and edge computing have been validated as effective ways to solve the energy-limited problem and computation-capacity-limited problem of wireless devices (WDs), respectively. This paper studies the wireless-powered multi-access edge computing (WP-MEC) network, where WDs conduct either local computing or task offloading for their individable computation tasks. We aim to minimize total computation delay (TCD) when each WD has a computation task to execute, referred to as the total computation delay minimization (TCDM) problem, by jointly optimizing the offloading-decision, WPT duration, and transmission durations of offloading WDs. The TCDM problem is a mixed integer programming (MIP) problem that is challenging to efficiently obtain the optimal or near-optimal solution. To tackle this challenge, we decompose the TCDM problem into the sub-problem of optimizing the WPT duration and transmission durations, and the top-problem of optimizing the offloading decision. For the nonconvex sub-problem, we design a worst-WD-adjusting (WDA) algorithm to efficiently obtain its optimal solution. For the top-problem, under the time-varying channel conditions, traditional optimization methods are hard to determine the optimal or near-optimal offloading decision within the channel coherence duration. To fast obtain the near-optimal offloading decision, we propose a deep neural networks (DNN)-based deep reinforcement learning (DRL) model, which takes the sub-problem solving as one component for utility evaluation. Finally, numerical results demonstrate that the proposed online DRL-based offloading algorithm achieves the near-minimal TCD with low computational complexity, and is suitable for the fast-fading WP-MEC network.

In this paper, we propose a novel diffusion robust variable step-size least mean square (DRVSS-LMS) algorithm that is insensitive to impulsive noise for distributed estimation in the network. Conventional diffusion least mean square algorithms are based on the assumption that the background noise obeys Gaussian distribution. However, the performances of these algorithms are severely degraded when impulsive noises occur in the network. By introducing the Huber objective function which can significantly suppress the effect of impulsive noise on estimation performances, we introduce a novel method to respectively deal with the abnormal nodes carrying data contaminated by impulsive noise and the normal nodes without being contaminated by impulsive noise. In addition, the proposed algorithm is assigned with variable step-sizes to further improve the performances of distributed estimation. Simulation results show that the proposed DRVSS-LMS algorithm can achieve both higher convergence rate and lower steady-state misadjustment than several existing robust diffusion LMS algorithms in the presence of impulsive noise.

In this paper, the maximum achievable throughput of electromagnetic nanonetworks in the Terahertz (THz) band (0.1–10 THz) is comprehensively investigated. On the one hand, the peculiarities of the THz-band channel are taken into account by capturing the impact of the molecular absorption loss on the signal propagation. On the other hand, a two-state MAC protocol is utilized to reflect the behavior of energy-harvesting nanodevices with constrained harvesting rate and maximum transmission power P0. An ad-hoc nanonetwork is considered with n identical randomly located nano-devices, and each is capable of utilizing W Hz of bandwidth. When the node density of nanonetworks is low, the achievable throughput is O ( WP0(n log n)α spr-1/2/ exp(α abs/√n log n))1/2, where αspr and αabs refer to the spreading loss coefficient and the molecular absorption loss coefficient. When the node density of nanonetworks is very high, the interference among nano-devices governs the network behavior and the achievable throughput becomes O (W²P0/I(n) (n log n) α spr-1/exp(α abs/√n log n))1/2. For both cases, the upper boundaries of the achievable throughput are analytically derived, and numerical results are provided. Numerical results illustrate that the molecular absorption loss plays the main role when the nanonetwork is sparse, and the interference dominates when the nanonetwork node density is very high.

Motivated by the benefits of cognitive radio (CR), energy harvesting (EH), and backscatter communication (BC) technologies to support Internet of Things (IoT) systems, we investigate the backscatter-aided energy harvesting cognitive radio networks (EH-CRNs) in a multi-channel scenario. To achieve high throughput on various channels, we propose a novel hybrid communication scheme that the secondary transmitter (ST) selects one channel for spectrum sensing, and performs multiple actions based on the sensing result. To be specific, if the selected channel is detected as busy, the ST potentially performs underlay mode transmission, ambient backscatter communication (AmBC), or radio frequency (RF) EH. Otherwise, the ST performs interweave mode transmission. Based on the ST’s knowledge of the channel availability and the amount of the available energy, the decisions of channel and specific action selections are made. Furthermore, the sequential decision problem is formulated as a mixed observability Markov decision process (MOMDP), and addressed by the classic value iteration algorithm. The proposed scheme could be flexibly adapted to the changes in energy and channel availabilities. Simulations demonstrate the superiority of this scheme in terms of throughput, and show that even without channel selection, the proposed scheme conducted on the channels with different idle probabilities always achieves high throughput.

Nanonetworks are composed of interacting nano-nodes, whose size ranges from several hundred cubic nanometers to several cubic micrometers. The extremely constrained computational resources of nano-nodes, the fluctuations in their energy caused by energy harvesting processes, and their very limited transmission range at Terahertz (THz)-band frequencies (0.1-10 THz), make the design of routing protocols in nanonetworks very challenging. A multi-hop deflection routing algorithm based on reinforcement learning (MDR-RL) is proposed in this paper to dynamically and efficiently explore the routing paths during packet transmissions. Firstly, new routing and deflection tables are implemented in nano-nodes, so that nano-nodes can deflect packets to other neighbors when route entries in the routing table are invalid. Secondly, one forward updating scheme and two feedback updating schemes based on reinforcement learning are designed to update the tables, namely, on-policy and off-policy updating schemes. Finally, extensive simulations in networks simulator-3 are conducted to analyze the performance of MDR-RL using different updating policies, as well as to compare the performance with other machine learning routing algorithms based on Neural Networks and Decision Tree. The results show that the MDR-RL can increase the packet delivery ratio and number of delivered packets, and can decrease the packet average hop count.

The rapid development of technology such as virtual reality and augmented reality, coupled with the reduced direct contact due to the COVID-19 pandemic, has led to the emergence of a more advanced mode of interaction: air handwriting. This new form of human-computer interaction allows users to input text by writing in the air freely. However, deploying and applying existing air handwriting recognition systems in real-world scenarios still presents challenges, particularly in real-time performance, privacy protection, and label scarcity. To address these challenges, we propose a federated active learning framework called FedAWR for air handwriting recognition tasks. FedAWR utilizes distributed learning to train a shared global model in the cloud from multiple user devices at the network's edge, while keeping the user's handwritten data local to ensure privacy. In addition, FedAWR employs an interactive active learning strategy to collect user-provided annotations for iterative training during the online federated learning process, bootstrapping personalized models for each client. To further enhance interactivity and real-time performance, we designed a lightweight recognition model, which is integrated into FedAWR. Finally, extensive experiments were conducted on real-world air handwritten datasets to validate the superiority of FedAWR.