In the ongoing 5G and upcoming 6G eras, the intelligent Internet of Things (IoT) network will take increasingly important responsibility for industrial production, daily life and so on. The IoT devices with limited battery size and computing ability cannot meet many applications brought out by the data-driven artificial intelligence technique. The combination of wireless power transfer (WPT) and edge computing is regarded as an effective solution to this dilemma. IoT devices can collect radio frequency energy provided by hybrid access points (HAPs) to process data locally or offload data to the edge servers of HAPs. However, how to efficiently make offloading decisions and allocate resource is challenging, especially for the networks with multiple HAPs. In this paper, we consider the sum computation rate maximization problem for a WPT empowered IoT network with multiple HAPs and IoT devices. The problem is formulated as a mixed-integer nonlinear programming problem. To solve this problem efficiently, we decompose it into a top-problem of optimizing offloading decisions and a sub-problem of optimizing time allocation under the given offloading decisions. We propose a deep reinforcement learning (DRL) based algorithm to output the near-optimal offloading decision and design an efficient algorithm based on Lagrangian duality method to obtain the consequent optimal time allocation. Simulations verified that the proposed DRL-based algorithm can achieve more than 95 percent of the maximal computation rate with low complexity. Compared with the common actor-critic algorithm, the proposed algorithm has the substantial advantage in convergence speed, achieved computation rate and running time.

With the development of hardware and communication technology, IoT (Internet of Things) devices become more powerful on computing, caching and communication. The enhancement of equipments makes it possible for IoT devices to act as caching helpers in cache-enabled networks to address the conflict between the limited caching resources and the sharply increasing data traffic. However, how to efficiently utilize the caching resources of IoT devices and edge servers is a challenging problem especially when contents are of different sizes. In this paper we focus on the probabilistic caching for contents of different sizes in heterogeneous IoT networks, aiming at improving the offloading rate for backhaul links. We present a mathematical framework to formulate hit probability of cache-enabled IoT networks based on stochastic geometry and propose an improved caching probability conversion (CPC) algorithm to derive the closed-form solutions of optimal caching probabilities. Moreover, we further extend the network model with serving capacity constraint, i.e., caching devices can only serve limited number of users simultaneously, and solve the corresponding non-convex problem by difference of convex (DC) programming. We validate our analytical framework by Monte Carlo method and give extensive numerical results to compare the performance of the proposed strategy with that of two existing caching strategies.

The rapid advancement of sixth-generation (6G) networks and artificial intelligence technologies is leading to the emergence of collaborative intelligent transportation systems (C-ITS), which is regarded as an essential trend in the future of transportation. Integrating Internet of Things (IoT) with C-ITS is an efficient solution to provide real-time data collection and status monitoring for vehicles and infrastructures to improve the intelligence and reliability of C-ITS. In order to address the challenges of limited battery energy and low computing power of IoT nodes, integrating wireless power transfer (WPT) with mobile edge computing (MEC) is considered as a promising solution to improve their lifetime and computational capability for IoT nodes. In this paper, we investigate a distributed dynamic computing offloading model for an MEC-enabled C-ITS, where multiple roadside units (RSUs) collaborate to provide offloading services to wireless devices (WDs). We formulate the task offloading and bandwidth resource allocation as a distributed Stackelberg game. The WDs act as leaders, aiming to maximize their computing rate by offloading tasks to RSU or performing local computing. The RSUs act as followers, optimizing their bandwidth allocation based on the WDs’ offloading decisions, thereby improving the overall system computing rate. We prove the existence of a Stackelberg equilibrium (SE) and propose a multi-agent reinforcement learning algorithm to enable WDs to select offloading decisions and help RSUs optimize bandwidth allocation. Numerical simulation results demonstrate that the proposed scheme offers significant performance improvements over existing methods.

Compromised by the ever increasing amount of mobile data traffic generated by mobile devices, edge servers are expected to provide caching resources for users so as to enable low-latency content delivery and release the burden on backhaul network. Considering the limited caching capacities of edge servers, it is essential to design an efficient content placement strategy to increase the data offloading ratio, i.e., the proportion of requested contents that are delivered via edge caching rather than backhaul links. In this paper, we propose a spatially cooperative caching strategy for a two-tier heterogeneous network consisting of edge servers and caching helpers aiming at reducing the storage space taken by duplicate contents on caching helpers and increasing hit probability. We develop an analysis framework for the proposed spatially cooperative caching strategy by using tools from stochastic geometry and maximize the hit probability by optimizing the caching probabilities of contents on edge servers and caching helpers. Particular, we derive the closed-form solution of the optimization problem for unit cache size. The simulation results are identical with the analytical ones and the outperformance is observed with the optimal caching probability derived in this paper compared with the existing caching strategies.

Edge caching is proposed to offload traffic from backhaul links by storing popular contents on edge servers and reusing these pre-cached contents to meet the frequent requests from local users. Due to the limited computing and caching resources of edge servers, the traditional encryption and decryption technologies, deployed in the upper layers of protocol stacks, appeared difficult in providing secure content delivery for the growing number of mobile users. In this letter, we consider the physical layer security issues for the popular probabilistic caching. Unlike most prior works which are concentrated on maximizing achievable transmission rate, we analyze the average secure delivery probability of the caching network and jointly optimize the redundant rate and caching probabilities. The simulation results are identical with the theoretical ones and the outperformance over existing caching strategies is observed with the optimal caching probability derived in this letter.