Fog radio access networks (F-RANs) can effectively alleviate fronthaul loads and reduce content transmission delay by migrating cloud services to the network edge. This paper addresses a cooperative caching scenario in F-RAN, where each mobile user can acquire the requested contents from any one of its associated fog-computing-based access points (F-APs). However, caching disparate contents in different F-APs will lead to different content delivery delays, since mobile users suffer from diverse channel fadings and interferences when they download contents from different F-APs. Considering limited caching storage in each F-AP, diverse user preferences, unpredictable user mobility and time-varying channel states, an average transmission delay minimization problem is formulated. With the aid of dueling deep-Q-network framework, a delay-aware cache update policy is proposed for mobile users in F-RAN. The proposed cache update policy will decide to replace the stored contents in F-APs with the proper contents at each time slot. Compared with first in first out, least recently used and least frequently used caching policies, simulation experiments are performed to evaluate the performance of the proposed algorithm. Simulation results illustrate that the proposed caching policy yields better average hit ratio and lower average transmission delay than other traditional caching policies. INDEX TERMS Caching, fog radio access network, hit ratio, mobility, reinforcement learning.

By offloading storage and computing resources to the edge of networks, mobile edge computing (MEC) is emerged as a promising architecture to reduce the transmission delay and bandwidth waste for mobile multimedia services. This paper focuses on a multi-service scenario in the MEC systems, where the MEC server can provide three multimedia services including live streaming, buffered streaming and low latency enhanced mobile broadband applications for edge users at the same time. In order to satisfy various quality of service (QoS) requirements for different multimedia applications, the 5G QoS model is applied. Notably, the packets from the multimedia applications with the same or similar requirements are mapped into the same QoS flow, and each QoS flow is processed individually. Therefore, how to effectively schedule the limited radio resource for QoS flows is an intractable problem. To address the problem above, a QoS evaluation model is designed, and a QoS maximization problem is formulated. Furthermore, a deep reinforcement learning method, deep-Q-network, is adopted to make decisions to allocate radio resource dynamically. Compared with round-robin and priority-based scheduling algorithms, the simulation results validate that the proposed algorithm outperforms other resource scheduling algorithms for multi-service scenario. INDEX TERMS Deep-Q-network, deep reinforcement learning, mobile edge computing, multimedia, quality of service.

Mobile edge computing (MEC) is considered a more effective technological solution for developing the Internet of Things (IoT) by providing cloud-like capabilities for mobile users. This article combines wireless powered communication (WPC) technology with an MEC network, where a base station (BS) can transfer wireless energy to edge users (EUs) and execute computation-intensive tasks through task offloading. Traditional numerical optimization methods are time-consuming approaches for solving this problem in time-varying wireless channels, and centralized deep reinforcement learning (DRL) is not stable in large-scale dynamic IoT networks. Therefore, we propose a federated DRL-based online task offloading and resource allocation (FDOR) algorithm. In this algorithm, DRL is executed in EUs, and federated learning (FL) uses the distributed architecture of MEC to aggregate and update the parameters. To further solve the problem of the non-IID data of mobile EUs, we devise an adaptive method that automatically adjusts the FDOR algorithm's learning rate. Simulation results demonstrate that the proposed FDOR algorithm is superior to the traditional numerical optimization method and the existing DRL algorithm in four aspects: convergence speed, execution delay, overall calculation rate and stability in large-scale and dynamic IoT.INDEX TERMS Mobile edge computing, federated learning, deep reinforcement learning, online computing offload, wireless powered communication.

The operation of multi-domain and multi-vendor EONscan be achieved by interoperable Sliceable Bandwidth Variable Transponders, a GMPLS/ BGP-LS -based control plane and a planning tool. This paper reports the first full demonstration and validation this end-to-end architecturePeer ReviewedPostprint (published version

How to support massive access efficiently is one of the challenges in the future Internet of Things (IoT) systems. To address such challenge, this paper proposes an effective preamble collision resolution scheme to sustain massive random access (RA) for an IoT system. Specifically, a new sub-preamble structure is first proposed to reduce the preamble collision probability. To identify different devices that send the same preamble to the gNB on the same physical random access channel (PRACH), a multiple timing advance (TA) capturing scheme is then proposed. Thereafter, an RA scheme is designed to sustain massive access and the performance of the scheme is studied analytically. Finally, the effectiveness of the proposed RA scheme is validated by extensive simulation experiments in terms of preamble detection probability, preamble collision probability, RA success probability, resource efficiency and TA capturing.