基于空中协同无线网络资源人工智能分配算法的智慧乡村平台

随着人工智能技术的不断发展,智慧乡村建设占据着重要地位。为了加快智慧乡村平台网络建设,研究搭建无人机空中协同无线网络系统获取农业相关空中协同位置信息。同时结合资源人工智能分配算法,即以最佳位置匹配为主,经匈牙利算法实现系统的位置匹配,从而实现资源分配。结果表明,随着空中接入点最大连接数的增加,总时延有所减少。在地面感应节点数量在300个以内的情况下,总时延不超过600 ms。改进总时延从597 ms减少到402 ms,减少了195 ms。这说明系统提升性能,处理速度加快,响应时间缩短。改进方法可以有效地减少通信系统中的传输延迟,提高数据传输的效率,并且对于地面用户数量的增加和任务量的提升有很好的适应能力。研究设计的资源分配策略有利于实现无线网络资源的智能管理和优化分配,这为智慧乡村建设提供了有力支持。

Qo E-based resource allocation protocols in cognitive OFDMA network with hybrid model

A resource allocation protocol is presented in an orthogonal frequency division multiple access （OFDMA） cognitive radio （CR） network with a hybrid model which combines overlay and underlay models. Without disrupting the primary user （PU） transmissions, the overlay model allows the secondary user （SU） to utilize opportunistically the idle sub-channels; the underlay model allows the SU to occupy the same sub-channels with PU. The proposed protocols are designed for maximizing the quality of experience （QoE） of CR users and switching dynamically between the overlay and underlay models. QoE is measured by the mean opinion score （MOS） rather than simply fulfilling the physical and medium access control （MAC） layer requirements. The simulations considering the file transfer and video stream services show that the proposed resource allocation strategy is spectrum efficient.

A Novel Deep Learning Method for Application Identification in Wireless Network

In modern wireless communication network, the increased consumer demands for multi-type applications and high quality services have become a prominent trend, and put considerable pressure on the wireless network. In that case, the Quality of Experience(Qo E) has received much attention and has become a key performance measurement for the application and service. In order to meet the users' expectations, the management of the resource is crucial in wireless network, especially the Qo E based resource allocation. One of the effective way for resource allocation management is accurate application identification. In this paper, we propose a novel deep learning based method for application identification. We first analyse the requirement of managing Qo E for wireless communication, and review the limitation of the traditional identification methods. After that, a deep learning based method is proposed for automatically extracting the features and identifying the type of application. The proposed method is evaluated by using the practical wireless traffic data, and the experiments verify the effectiveness of our method.

Traffic Characteristics Based Dynamic Radio Resource Management in Heterogeneous Wireless Networks

The traffic with tidal phenomenon in Heterogeneous Wireless Networks(HWNs)has radically increased the complexity of radio resource management and its performance analysis.In this paper,a Simplified Dynamic Hierarchy Resource Management(SDHRM)algorithm exploiting the resources dynamically and intelligently is proposed with the consideration of tidal traffic.In network-level resource allocation,the proposed algorithm first adopts wavelet neural network to forecast the traffic of each sub-area and then allocates the resources to those sub-areas to maximise the network utility.In connection-level network selection,based on the above resource allocation and the pre-defined QoS requirement,three typical network selection policies are provided to assign traffic flow to the most appropriate network.Furthermore,based on multidimensional Markov model,we analyse the performance of SDHRM in HWNs with heavy tailed traffic.Numerical results show that our theoretical values coincide with the simulation results and the SDHRM can improve the resource utilization.

A New Power Allocation Algorithm in Cognitive Radio Networks

Most resource allocation algorithms are based on interference power constraint in cognitive radio networks.Instead of using conventional primary user interference constraint,we give a new criterion called allowable signal to interference plus noise ratio(SINR) loss constraint in cognitive transmission to protect primary users.Considering power allocation problem for cognitive users over flat fading channels,in order to maximize throughput of cognitive users subject to the allowable SINR loss constraint and maximum transmit power for each cognitive user,we propose a new power allocation algorithm.The comparison of computer simulation between our proposed algorithm and the algorithm based on interference power constraint is provided to show that it gets more throughput and provides stability to cognitive radio networks.

Noisy Chaotic Neural Network for Resource Allocation in High-Speed Train OFDMA System

High-speed train communication system is a typical high-mobility wireless communication network. Resource allocation problem has a great impact on the system performance. However, conventional resource allocation approaches in cellular network cannot be directly applied to this kind of special communication environment. A multidomain resource allocation strategy was proposed in the orthogonal frequency-division multiple access(OFDMA) of high-speed. By analyzing the effect of Doppler shift, sub-channels, antennas, time slots and power were jointly considered to maximize the energy efficiency under the constraint of total transmission power. For the purpose of reducing the computational complexity, noisy chaotic neural network algorithm was used to solve the above optimization problem. Simulation results showed that the proposed resource allocation method had a better performance than the traditional strategy.

Dynamic Resource Allocation in TDD-Based Heterogeneous Cloud Radio Access Networks

To fulfill the explosive growth of network capacity, fifth generation(5G) standard has captured the attention and imagination of researchers and engineers around the world. In particular, heterogeneous cloud radio access network(H-CRAN), as a promising network paradigm in 5G system, is a hot research topic in recent years. However, the densely deployment of RRHs in H-CRAN leads to downlink/uplink traffic asymmetry and severe inter-cell interference which could seriously impair the network throughput and resource utilization. To simultaneously solve these two problems, we proposed a dynamic resource allocation(DRA) scheme for H-CRAN in TDD mode. Firstly, we design a clustering algorithm to group the RRHs into different sets. Secondly, we adopt coordinated multipoint technology to eliminate the interference in each set. Finally, we formulate the joint frame structure, power and subcarrier selection problem as a mixed strategy noncooperative game. The simulation results are presented to validate the effectiveness of our proposed algorithm by compared with the existing work.

UTILITY OPTIMIZATION SCHEDULING FOR MULTI-POINT VIDEO SURVEILLANCE IN UBIQUITOUS NETWORK

Resource allocation is an important problem in ubiquitous network. Most of the existing resource allocation methods considering only wireless networks are not suitable for the ubiquitous network environment, and they will harm the interest of individual users with instable resource requirements. This paper considers the multi-point video surveillance scenarios in a complex network environment with both wired and wireless networks. We introduce the utility estimated by the total costs of an individual network user. The problem is studied through mathematical modeling and we propose an improved problem-specific branch-and-cut algorithm to solve it. The algorithm follows the divide-and-conquer principle and fully considers the duality feature of network selection. The experiment is conducted by simulation through C and Lingo. And it shows that compared with a centralized random allocation scheme and a cost greed allocation scheme, the proposed scheme has better per- formance of reducing the total costs by 13.0% and 30.6% respectively for the user.

Resource allocation for relay assisted cognitive radio network

Different schemes, which performed channel, power and time allocation to enhance the network performance of overall end-to-end throughput for cooperative cognitive radio network, were investigated. Interference temperature limit of corresponding primary users was considered. Due to the constraints caused by multiple dual channels, the power allocation problem is non-convex and NP-hard. Based on geometric programming (GP), a novel and general algorithm, which turned the problem into a series of GP problems by logarithm approximation (LASGP), was proposed to efficiently solve it. Numerical results verify the efficiency and availability of the LASGP algorithm. Solutions of LASGP are provably convergent and globally optimal point can be observed as well as the channel allocation always outperforms power or timeslot allocation from simulations. Compared with schemes without any allocation, the scheme with joint channel, power and timeslot allocation significantly increases the overall end-to-end throughput by no less than 70% under same simulation conditions. This scheme can not only maximize the throughput by increasing total maximum power of relay node, but also outperform other resource allocation schemes when lower total maximum power of source and relay nodes is restricted. As the total maximum power of source node increases, the scheme with joint channel and timeslot allocation performs best in all schemes.