Constrained reinforcement learning (CRL), also termed as safe learning, is a promising technique enabling the deployment of RL agent in real-world systems. In this paper, we propose successive convex approximation based off-policy optimization (SCAOPO) algorithm to solve general CRL problem, which formulated constrained Markov decision process (CMDP) context average cost. The SCAOPO on solving ...

With the rapid development of smart manufacturing, edge computing-oriented microservice platforms are emerging as an important part production control. In containerized deployment microservices, layer sharing can reduce huge bandwidth consumption caused by image pulling, and chain communication overhead between microservices. The two methods use characteristics each to share resources during de...

This paper addresses the spare capacity allocation (SCA) problem considering any single node failure in mesh networks. The SCA node failure problem aims at finding backup routes and providing sufficient spare capacity to protect traffic when any single node fails in communication network. Here, we introduce our novel matrix formulation of the arc-flow SCA node failure model. In this model, work...

This paper presents an investigation of the transmitting power consumption a base station (BS) in simultaneous wireless information and transfer (SWIPT) system enhanced by reconfigurable intelligent surface (RIS). The aim is to optimize total when sending signals energy from BS ground sensors. To this end, optimized satisfying sensor’s minimum signal-to-interference-plus-noise ratio (SINR), pha...

In this paper, we study a resource allocation problem in orthogonal frequency division multiple access (OFDMA)-based Device-to-Device (D2D) communications. To end, propose multi-objective optimization (MOOP) framework, which jointly maximizes the sum rate of D2D users (DUs) and cellular (CUs) uplink communications minimizes total transmit power. The proposed formulation takes into account minim...

Backscatter communication is a promising technology for the Internet of Things (IoT) systems with low-energy consumption, in which data transmission backscatter devices relies on reflecting incident signal. However, limited by low power characteristic reflected signal from devices, achieving efficient collection widely distributed thorny problem. Considering that unmanned aerial vehicles (UAVs)...

In this article, we investigate the energy minimization problem of an unmanned-aerial-vehicle (UAV)-assisted data collection sensor network. We jointly optimize trajectory UAV and power consumption sensors for uploading with constraints sensors. The design consists two parts: 1) serving orders 2) UAV’s hovering positions, where latter is highly coupled To find optimal sensors, formulate as a st...

Motivated by the fact that both security and energy efficiency are fundamental requirements design targets of future satellite communications, this letter investigates secure efficient beamforming in multibeam systems, where user each beam is surrounded an eavesdropper attempting to intercept confidential information. To simultaneously improve transmission reduce power consumption, our objectiv...

In this paper, we propose a cross layer energy efficient resource allocation and remote radio head (RRH) selection algorithm for heterogeneous traffic in power domain non-orthogonal multiple access (PD-NOMA) based heterogeneous cloud radio access networks (H-CRANs). The main aim is to maximize the EE of the elastic users subject to the average delay constraint of the streaming users and the con...