This paper investigates the network slicing in virtualized wireless network. We consider a downlink orthogonal frequency division multiple access system which physical resources of base stations are and divided into enhanced mobile broadband (eMBB) ultrareliable low latency communication (URLLC) slices. take technology to solve problems spectral efficiency URLLC reliability. A mixed-integer programming problem is formulated by maximizing constraint users’ requirements for two slices, i.e.,...

In this paper, multi-cell power allocation approach is researched. Different from the traditional optimization decomposition method, Deep Reinforcement Learning (DRL) method employed to solve issue which an NP-hard problem. The objective of our work maximize overall capacity entire network in scenario where base stations are randomly and densely distributed. We propose a wireless resource mapping deep neural for named as Deep-Q-Full-Connected-Network (DQFCNet). Compared with water-filling...

With the development of wireless communication technology, requirement for data rate is growing rapidly. Mobile system faces problem shortage spectrum resources. Cognitive radio technology allows secondary users to use frequencies authorized primary user with permission user, which can effectively improve utilization In this article, we establish a cognitive network model based on underlay and propose resource allocation algorithm DDQN (Double Deep Q Network). The jointly optimizes...

Abstract Nowadays, wireless communication system is facing the problems of spectrum resource shortage. Cognitive radio technology allows cognitive users to use spectrums authorized primary improve utilization. In this paper, a network model based on hybrid overlay–underlay access mode established. To solve allocation problem, multi‐agent algorithm graph convolution reinforcement learning which combines deep Q (DQN) and attention proposed. DQN used for action selection obtain information...

To solve the contradiction between limited spectrum resources and increasing communication demand, this paper proposes a wireless resource allocation scheme based on Deep Q Network (DQN) to allocate radio in downlink multi-user cognitive (CR) network with slicing. Secondary users (SUs) are multiplexed using non-orthogonal multiple access (NOMA). The SUs use hybrid mode improve spectral efficiency (SE). Considering demand for services, enhanced mobile broadband (eMBB) slice ultrareliable...

The cognitive network has become a promising method to solve the spectrum resources shortage problem. Especially for optimization of slicing in radio access (RAN), we are interested profit mobile virtual operator (MVNO) and utility secondary users (SUs). In RAN, aim find optimal scheme MVNO efficiently allocate slice SUs. Since SUs selfish game between is difficult reach equilibrium, consider modeling this as Stackelberg game. Leveraging mathematical programming with equilibrium constraints...

Abstract Network slicing and mobile edge computing are key technologies in 5G/6G networks. Stable allocation of resources is a challenge while communication computation offloading coexist. To meet the service requirements offloading, radio access network model which consists enhanced broadband (eMBB) users, ultra‐reliable low latency (URLLC) base stations integrated with MEC servers, fog nodes power proposed. By employing Lyapunov optimisation technique, resource algorithm proposed to...

Abstract Network slicing is considered to be a key feature of the 5th generation mobile networks. It permits multiple tenants, i.e. virtual network operators, share resources. However, each tenant only considers individual slice utility, which leads unfair resource allocation among tenants. To achieve aim that infrastructure provider can fairly allocate resources two‐layer architecture in heterogeneous radio access (RAN) proposed and it formulated as mathematical program with equilibrium...

Social media platforms such as Twitter and Facebook play a pivotal role in companies' strategy of engaging customers. How to target potential customers on social effectively efficiently is an important yet unsolved question. Predicting customer engagement facing several challenges that cannot be solved by traditional methods. In this work, we design framework leverages individual behavior together with network contextual information predict (like/comment/share) brand's posts. We first build...

In this paper, we use the Linking theorem, Clark theorem and Fountain to obtain existence of solutions discrete boundary value problem involving p-Laplacian on simple, connected, undirected weighted graphs. We three solutions, infinitely many or a number depending parameter λ vertices. The eigenvalues nonlinear operator -Δp,ω+q are concerned in study.

Making full use of bus dedicated lanes can not only ensure the priority public transportation and enhance attractiveness ground transportation, but also make road resources to achieve purpose intensive resources. This paper establishes a comprehensive evaluation method system based on multi-source big data. Using method, from angles physical network lanes, degree matching between passenger flow, utilization evaluates Beijing’s main flow channels, analyzes problems, gives corresponding...

We numerically studied the terahertz wave generation in quasi phase matched Gallium Arsenide (QPM-GaAs) based on difference frequency (DFG) process between resonating signal and idler waves of type-IIphase periodically poled LiNbO3 (PPLN) optical parametric oscillator (OPO). The optimal GaAs length for maximum conversion efficiency was obtained considering propagation loss crystal by adding a term coupled equations.

Heterogeneous base station deployment enables to provide high capacity and wide area coverage. Network slicing makes it possible allocate wireless resource for heterogeneous services on demand. These two promising technologies contribute the unprecedented service in 5G. We establish a multiservice network model, which aims raise transmission rate under delay constraints active control terminals, optimize energy efficiency passive terminals. A policy-gradient-based deep reinforcement learning...

There is no measurable and evaluable index system for cloud-network convergence that provides guidance reference the subsequent construction development of convergence. It a big project to select evaluate indexes convergence, which requires suitable selection evaluation schemes. Based on analytic hierarchy process (AHP) entropy weight method, this paper proposes an improved AHP (i-AHP) scheme leveraging years experts' experience, geometric mean least square method. The weighted method (WLSM)...

Using the low earth orbit (LEO) satellite technology to provide high capacity and speed data service for users, has been one of most popular research hotspots in LEO communication system. Whereas, traditional researches field mainly focus on optimization channel resource allocation, which is based improvement transmission rate reliability. Different from research, this paper considers popularity content different station (ES) user's perspective. Then we optimize resources allocation between...