This paper investigates a computing offloading policy and the allocation of computational resource for multiple user equipments (UEs) in device-to-device (D2D)-aided fog radio access networks (F-RANs). Concerning the dynamically changing wireless environment where the channel state information (CSI) is difficult to predict and know exactly, we formulate the problem of task offloading and resource optimization as a mixed-integer nonlinear programming problem to maximize the total utility of all UEs. Concerning the non-convex property of the formulated problem, we decouple the original problem into two phases to solve. Firstly, a centralized deep reinforcement learning (DRL) algorithm called dueling deep Q-network (DDQN) is utilized to obtain the most suitable offloading mode for each UE. Particularly, to reduce the complexity of the proposed offloading scheme-based DDQN algorithm, a pre-processing procedure is adopted. Then, a distributed deep Q-network (DQN) algorithm based on the training result of the DDQN algorithm is further proposed to allocate the appropriate computational resource for each UE. Combining these two phases, the optimal offloading policy and resource allocation for each UE are finally achieved. Simulation results demonstrate the performance gains of the proposed scheme compared with other existing baseline schemes.

No abstract

No abstract

As one of the electrode materials for supercapacitor, Co 3 O 4 /graphene composite was mainly synthesized via two-steps method. Here, a facile one-pot method was used for Co 3 O 4 /graphene composite, and the performances of one-pot-synthesized Co 3 O 4 /graphene composite were carefully investigated. Liquid-phase exfoliation was used for graphene and the D-band/ G-band ratio of liquid-phase exfoliated graphene was only 0.094, which indicated that the graphene had low defect density and enhanced electrical conductivity. Morphologies investigation of Co 3 O 4 /graphene composites indicated that Co 3 O 4 nanoparticles with mean diameter of 14 nm were uniformly anchored on graphene sheets. The facile one-pot method associated with liquid-phase exfoliated graphene induced Co 3 O 4 /graphene composite with enhanced speci¯c capacitance of 392 FÁg À1 at a current density of 1 AÁg À1 . The Co 3 O 4 /graphene composite also expressed relatively small internal resistance and di®usion resistance (0.36 and 0.45 , respectively). Moreover, the synthesized Co 3 O 4 /graphene composite yielded excellent rate performances with only 9.5% capacitance loss when current density was increased by a factor of 10.

Authors' ContributionQC and MM initiated this project, performed statistical analysis and wrote the manuscript. ZT, CQ and AM procured data, constructed tables and figures and revised several parts of the manuscript.