Design of an Interconnection Architecture and Sizing of Two (2) EPC Core Networks: The Case of Orange-Guinea

With the arrival of the 4G and 5G,the telecommunications networks have experienced a large expansion of these networks.That enabled the integration of many services and adequate flow,thus enabling the operators to respond to the growing demand of users.This rapid evolution has given the operators to adapt,their methods to the new technologies that increase.This complexity becomes more important,when these networks include several technologies to access different from the heterogeneous network like in the 4G network.The dimensional new challenges tell the application and the considerable increase in demand for services and the compatibility with existing networks,the management of mobility intercellular of users and it offers a better quality of services.Thus,the proposed solution to meet these new requirements is the sizing of the EPC(Evolved Packet Core)core network to support the 5G access network.For the case of Orange Guinea,this involves setting up an architecture for interconnecting the core networks of Sonfonia and Camayenne.The objectives of our work are of two orders:(1)to propose these solutions and recommendations for the heart network EPC sizing and the deployment to be adopted;(2)supply and architectural interconnection in the heart network EPC and an existing heart network.In our work,the model of traffic in communication that we use to calculate the traffic generated with each technology has link in the network of the heart.

A UAV-Assisted V2X Network Architecture with Separated Data Transmission and Network Control

With the explosive increasing number of connecting devices such as smart phones, vehicles,drones, and satellites in the wireless networks, how to manage and control such a huge number of networking nodes has become a great challenge. In this paper, we combine the advantages of centralized networks and distributed networks approaches for vehicular networks with the aid of Unmanned Aerial Vehicle(UAV), and propose a Center-controlled Multihop Wireless(CMW) networking scheme consisting of data transmission plane performed by vehicles and the network control plane implemented by the UAV.Besides, we jointly explore the advantages of Medium Access Control(MAC) protocols in the link layer and routing schemes in the network layer to facilitate the multi-hop data transmission for the ground vehicles.Particularly, the network control plane in the UAV can manage the whole network effectively via fully exploiting the acquired network topology information and traffic requests from each vehicle, and implements various kinds of control based on different traffic demands, which can enhance the networking flexibility and scalability significantly in vehicular networks.Simulation results validate the advantages of the proposed scheme compared with existing methods.

An evaluation method of contribution rate based on fuzzy Bayesian networks for equipment system-of-systems architecture

The contribution rate of equipment system-of-systems architecture(ESoSA)is an important index to evaluate the equipment update,development,and architecture optimization.Since the traditional ESoSA contribution rate evaluation method does not make full use of the fuzzy information and uncertain information in the equipment system-of-systems(ESoS),and the Bayesian network is an effective tool to solve the uncertain information,a new ESoSA contribution rate evaluation method based on the fuzzy Bayesian network(FBN)is proposed.Firstly,based on the operation loop theory,an ESoSA is constructed considering three aspects:reconnaissance equipment,decision equipment,and strike equipment.Next,the fuzzy set theory is introduced to construct the FBN of ESoSA to deal with fuzzy information and uncertain information.Furthermore,the fuzzy importance index of the root node of the FBN is used to calculate the contribution rate of the ESoSA,and the ESoSA contribution rate evaluation model based on the root node fuzzy importance is established.Finally,the feasibility and rationality of this method are validated via an empirical case study of aviation ESoSA.Compared with traditional methods,the evaluation method based on FBN takes various failure states of equipment into consideration,is free of acquiring accurate probability of traditional equipment failure,and models the uncertainty of the relationship between equipment.The proposed method not only supplements and improves the ESoSA contribution rate assessment method,but also broadens the application scope of the Bayesian network.

Scale adaptive fitness evaluation‐based particle swarm optimisation for hyperparameter and architecture optimisation in neural networks and deep learning

Research into automatically searching for an optimal neural network(NN)by optimi-sation algorithms is a significant research topic in deep learning and artificial intelligence.However,this is still challenging due to two issues:Both the hyperparameter and ar-chitecture should be optimised and the optimisation process is computationally expen-sive.To tackle these two issues,this paper focusses on solving the hyperparameter and architecture optimization problem for the NN and proposes a novel light‐weight scale‐adaptive fitness evaluation‐based particle swarm optimisation(SAFE‐PSO)approach.Firstly,the SAFE‐PSO algorithm considers the hyperparameters and architectures together in the optimisation problem and therefore can find their optimal combination for the globally best NN.Secondly,the computational cost can be reduced by using multi‐scale accuracy evaluation methods to evaluate candidates.Thirdly,a stagnation‐based switch strategy is proposed to adaptively switch different evaluation methods to better balance the search performance and computational cost.The SAFE‐PSO algorithm is tested on two widely used datasets:The 10‐category(i.e.,CIFAR10)and the 100−cate-gory(i.e.,CIFAR100).The experimental results show that SAFE‐PSO is very effective and efficient,which can not only find a promising NN automatically but also find a better NN than compared algorithms at the same computational cost.

Deep Neural Network Architecture Search via Decomposition-Based Multi-Objective Stochastic Fractal Search

Deep neural networks often outperform classical machine learning algorithms in solving real-world problems.However,designing better networks usually requires domain expertise and consumes significant time and com-puting resources.Moreover,when the task changes,the original network architecture becomes outdated and requires redesigning.Thus,Neural Architecture Search(NAS)has gained attention as an effective approach to automatically generate optimal network architectures.Most NAS methods mainly focus on achieving high performance while ignoring architectural complexity.A myriad of research has revealed that network performance and structural complexity are often positively correlated.Nevertheless,complex network structures will bring enormous computing resources.To cope with this,we formulate the neural architecture search task as a multi-objective optimization problem,where an optimal architecture is learned by minimizing the classification error rate and the number of network parameters simultaneously.And then a decomposition-based multi-objective stochastic fractal search method is proposed to solve it.In view of the discrete property of the NAS problem,we discretize the stochastic fractal search step size so that the network architecture can be optimized more effectively.Additionally,two distinct update methods are employed in step size update stage to enhance the global and local search abilities adaptively.Furthermore,an information exchange mechanism between architectures is raised to accelerate the convergence process and improve the efficiency of the algorithm.Experimental studies show that the proposed algorithm has competitive performance comparable to many existing manual and automatic deep neural network generation approaches,which achieved a parameter-less and high-precision architecture with low-cost on each of the six benchmark datasets.

SIMULATION AND PERFORMANCE ANALYSIS OF NETWORK ON CHIP ARCHITECTURES

The network on chip（NoC）is used as a solution for the communication problems in a complex system on chip（SoC）design.To further enhance performances,the NoC architectures,a high level modeling and an evaluation method based on OPNET are proposed to analyze their performances on different injection rates and traffic patterns.Simulation results for general NoC in terms of the average latency and the throughput are analyzed and used as a guideline to make appropriate choices for a given application.Finally,a MPEG4 decoder is mapped on different NoC architectures.Results prove the effectiveness of the evaluation method.

Architecture for Cellular Enabled Integrated Communication and Sensing Services

There is growing interest in the integrated sensing and communication(ISAC)to extend the 5G+/6G network capabilities by introducing sensing capability.While the solutions for mono-static or bi-static ISAC have shown feasibility and benefits based on existing 5G physical layer design,whether and how to coordinate multiple ISAC devices to better exert networking performance are rarely discussed.3 rd Partnership Project(3GPP)has initiated the ISAC use cases study,and the follow-up studies for network architecture could be anticipated.In this article,we focus on gNB-based sensing mode and propose ISAC functional framework with given of highlevel service procedures to enable cellular based ISAC services.In the proposed ISAC framework,three types of network functions for sensing service as Sensing Function(SF),lightweight-Edge Sensing Function(ESF)and full-version-ESF are designed with interaction with network nodes to fulfill the latency requirements of ISAC use cases.Finally,with simulation evaluations and hardware testbed results,we further verify the performance benefit and feasibility to enable ISAC in 5G for the gNB-based sensing mode with new design on SF and related signaling protocols.

Space-Air-Ground Integrated Network (SAGIN) for 6G: Requirements, Architecture and Challenges

As the fifth-generation(5G)mobile communication network may not meet the requirements of emerging technologies and applications,including ubiquitous coverage,industrial internet of things(IIoT),ubiquitous artificial intelligence(AI),digital twins(DT),etc.,this paper aims to explore a novel space-air-ground integrated network(SAGIN)architecture to support these new requirements for the sixth-generation(6G)mobile communication network in a flexible,low-latency and efficient manner.Specifically,we first review the evolution of the mobile communication network,followed by the application and technology requirements of 6G.Then the current 5G non-terrestrial network(NTN)architecture in supporting the new requirements is deeply analyzed.After that,we proposes a new flexible,low-latency and flat SAGIN architecture,and presents corresponding use cases.Finally,the future research directions are discussed.

The SOLIDS 6G Mobile Network Architecture:Driving Forces,Features,and Functional Topology

With the large-scale commercial launch of fifth generation(5G)mobile network,the development of new services and applications catering to the year 2030,along with the deep convergence of information,communication,and data technologies(ICDT),and the lessons and experiences from 5G practice will drive the evolution of the next generation of mobile networks.This article surveys the history and driving forces of the evolution of the mobile network architecture and proposes a logical function architecture for sixth generation(6G)mobile network.The proposed 6G network architecture is termed SOLIDS(related to the following basic features:soft,on-demand fulfillment,lite,native intelligence,digital twin,and native security),which can support self-generation,self-healing,self-evolution,and self-immunity without human involvement and address the primary issues in the legacy 5G network(e.g.,high cost,high power consumption,and highly complicated operation and maintenance),significantly well.

A Flexible Three Clouds 5G Mobile Network Architecture Based on NFV & SDN

Along with the completion of the development of 4G technologies, the global mobile community starts the study of the next generation technologies, i.e. 5G technologies. This paper proposes a new flexible architecture for 5G mobile networks based on Network Function Virtualization(NFV) and Software Defined Network(SDN) technologies, which is adaptable to use cases and scenarios. Then implementation reference architecture and some typical 5G network deployment cases are discussed. Besides, some key issues for further study are also indicated at the end.

Effective distributed convolutional neural network architecture for remote sensing images target classification with a pre-training approach

How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classification due to the powerful feature representation ability and better performance. However,the training and testing of CNN mainly rely on single machine.Single machine has its natural limitation and bottleneck in processing RSIs due to limited hardware resources and huge time consuming. Besides, overfitting is a challenge for the CNN model due to the unbalance between RSIs data and the model structure.When a model is complex or the training data is relatively small,overfitting occurs and leads to a poor predictive performance. To address these problems, a distributed CNN architecture for RSIs target classification is proposed, which dramatically increases the training speed of CNN and system scalability. It improves the storage ability and processing efficiency of RSIs. Furthermore,Bayesian regularization approach is utilized in order to initialize the weights of the CNN extractor, which increases the robustness and flexibility of the CNN model. It helps prevent the overfitting and avoid the local optima caused by limited RSI training images or the inappropriate CNN structure. In addition, considering the efficiency of the Na¨?ve Bayes classifier, a distributed Na¨?ve Bayes classifier is designed to reduce the training cost. Compared with other algorithms, the proposed system and method perform the best and increase the recognition accuracy. The results show that the distributed system framework and the proposed algorithms are suitable for RSIs target classification tasks.

Service Customized Space-Air-Ground Integrated Network for Immersive Media: Architecture, Key Technologies, and Prospects

The space-air-ground integrated network(SAGIN) is regarded as the key approach to realize global coverage in future network and it reaches broad access for various services. Being the new paradigm of service, immersive media(IM) has attracted users’ attention for its virtualization, but it poses challenges to network performance, e.g. bandwidth, rate, latency. However, the SAGIN has limitations in supporting IM services, such as 4 K/8 K video, virtual reality, and interactive games. In this paper, a novel service customized SAGIN architecture for IM applications(SAG-IM) is proposed, which achieves content interactive and real-time communication among terminal users. State-of-the-art research is investigated in detail to facilitate the combination of SAGIN and service customized technology, which provides endto-end differentiated services for users. Besides, the functional components of SAG-IM contain the infrastructure layer, perception layer, intelligence layer, and application layer, reaching the capabilities of intelligent management of the network. Moreover, to provide IM content with ultra-high-definition and high frame rate for the optimal user experience, the promising key technologies on intelligent routing and delivery are discussed. The performance evaluation shows the superiority of SAG-IM in supporting IM service.Finally, the prospects in practical application are high-lighted.

A Survey of Accelerator Architectures for Deep Neural Networks

Recently,due to the availability of big data and the rapid growth of computing power,artificial intelligence(AI)has regained tremendous attention and investment.Machine learning(ML)approaches have been successfully applied to solve many problems in academia and in industry.Although the explosion of big data applications is driving the development of ML,it also imposes severe challenges of data processing speed and scalability on conventional computer systems.Computing platforms that are dedicatedly designed for AI applications have been considered,ranging from a complement to von Neumann platforms to a“must-have”and stand-alone technical solution.These platforms,which belong to a larger category named“domain-specific computing,”focus on specific customization for AI.In this article,we focus on summarizing the recent advances in accelerator designs for deep neural networks(DNNs)-that is,DNN accelerators.We discuss various architectures that support DNN executions in terms of computing units,dataflow optimization,targeted network topologies,architectures on emerging technologies,and accelerators for emerging applications.We also provide our visions on the future trend of AI chip designs.

Data Center Network Architecture

1 Introduction The history of data centers can be traced back to the 1960s. Early data centers were deployed on main- frames that were time-shared by users via remote terminals. The boom in data centers came duringthe internet era. Many companies started building large inter- net-connected facililies,

The determination of the link with the smallest end-to-end network latency in ethernet architecture

Ethernet fundamental and its data transmission model are introduced in brief and end-to-end network latency was analyzed in this paper. On the premise of not considering transmission quality and transmission cost, latency was the function of the rest of network resource parameter (NRP). The relation between the number of nodes and that of end-to-end links was presented. In ethernet architecture, the algorithm to determine the link with the smallest latency is a polynomial issue when the number of network nodes is limited, so it can be solved by way of polynomial equations. Latency measuring is the key issue to determine the link with the smallest network latency. 3-node brigade (regiment) level network centric warfare (NCW) demonstration platform was studied and the latency between the detectors and weapon control stations was taken as an example. The algorithm of end-to-end network latency and link information in NCW was presented. The algorithm program based on Server/Client architecture was developed. The data transmission optimal link is one whose end-to-end latency is the smallest. This paper solves the key issue to determine the link whose end-to-end latency is the smallest in ethernet architecture. The study can be widely applied to determine the optimal link which is in the complex network environment of multiple service provision points.

A Double-Branch Xception Architecture for Acute Hemorrhage Detection and Subtype Classification

This study presents a deep learning model for efficient intracranial hemorrhage(ICH)detection and subtype classification on non-contrast head computed tomography(CT)images.ICH refers to bleeding in the skull,leading to the most critical life-threatening health condition requiring rapid and accurate diagnosis.It is classified as intra-axial hemorrhage(intraventricular,intraparenchymal)and extra-axial hemorrhage(subdural,epidural,subarachnoid)based on the bleeding location inside the skull.Many computer-aided diagnoses(CAD)-based schemes have been proposed for ICH detection and classification at both slice and scan levels.However,these approaches performonly binary classification and suffer from a large number of parameters,which increase storage costs.Further,the accuracy of brain hemorrhage detection in existing models is significantly low for medically critical applications.To overcome these problems,a fast and efficient system for the automatic detection of ICH is needed.We designed a double-branch model based on xception architecture that extracts spatial and instant features,concatenates them,and creates the 3D spatial context(common feature vectors)fed to a decision tree classifier for final predictions.The data employed for the experimentation was gathered during the 2019 Radiologist Society of North America(RSNA)brain hemorrhage detection challenge.Our model outperformed benchmark models and achieved better accuracy in intraventricular(99.49%),subarachnoid(99.49%),intraparenchymal(99.10%),and subdural(98.09%)categories,thereby justifying the performance of the proposed double-branch xception architecture for ICH detection and classification.

Design of Network Architecture Using Mobile Gateways for DLNA Devices in Wide Area Networks

The prevalence of information appliances supporting DLNA (Digital Living Network Alliance) such as televisions, recorders, and mobile phones has made it possible to share digital contents (e.g. videos, music and pictures) among appliances connected to a local network. However, DLNA does not let you share contents over different networks via the Internet. In this paper, we propose a network architecture where we adopt our SOAP method to mobile devices and use them as mobile gateways to consume digital contents from remote networks. We also confirm its practicality with a prototype.

Cognitive Intelligence Based 6G Distributed Network Architecture

5G is envisioned to guarantee high transmission rate,ultra-low latency,high reliability and massive connections.To satisfy the above requirements,the 5G architecture is designed with the properties of using service-based architecture,cloud-native oriented,adopting IT-based API interfaces and introduction of the Network Repository Function.However,with the wide commercialization of 5G network and the exploration towards 6G,the 5G architecture exposes the disadvantages of high architecture complexity,difficult inter-interface communication,low cognitive capability,bad instantaneity,and deficient intelligence.To overcome these limitations,this paper investigates 6G network architecture,and proposes a cognitive intelligence based distributed 6G network architecture.This architecture consists of a physical network layer and an intelligent decision layer.The two layers coordinate through flexible service interfaces,supporting function decoupling and joint evolution of intelligence services and network services.With the above design,the proposed 6G architecture can be updated autonomously to deal with the future unpredicted complex services.

Smart Service System(SSS)：A Novel Architecture Enabling Coordination of Heterogeneous Networking Technologies and Devices for Internet of Things

In Internet of Things(IoT), the devices or terminals are connected with each other, which can be very diverse over the wireless networks. Unfortunately, the current devices are not designed to communicate with the collocated devices which employ different communication technologies. Consequently, the communication between these devices will be realized only by using the gateway nodes. This will cause the inefficient use of wireless resources. Therefore, in this paper, a smart service system(SSS) architecture is proposed, which consists of smart service terminal(SST), and smart service network(SSN), to realize the Io T in a general environment with diverse communication networks, devices, and services. The proposed architecture has the following advantages: i) the devices in this architecture cover multiple types of terminals and sensor-actuator devices; ii) the communications network therein is a converged network, and will coordinate multiple kinds of existing and emerging networks. This converged network offers ubiquitous access for various sensors and terminals; iii) the architecture has services and applications covering all smart service areas. It also provides theadaptability to new services and applications. A SSS architecture-based smart campus system was developed and deployed. Evaluation experiments of the proposed smart campus system demonstrate the SSS's advantages over the existing counterparts, and verify the effectiveness of the proposed architecture.

An Optimized Convolution Neural Network Architecture for Paddy Disease Classification

Plant disease classification based on digital pictures is challenging.Machine learning approaches and plant image categorization technologies such as deep learning have been utilized to recognize,identify,and diagnose plant diseases in the previous decade.Increasing the yield quantity and quality of rice forming is an important cause for the paddy production countries.However,some diseases that are blocking the improvement in paddy production are considered as an ominous threat.Convolution Neural Network(CNN)has shown a remarkable performance in solving the early detection of paddy leaf diseases based on its images in the fast-growing era of science and technology.Nevertheless,the significant CNN architectures construction is dependent on expertise in a neural network and domain knowledge.This approach is time-consuming,and high computational resources are mandatory.In this research,we propose a novel method based on Mutant Particle swarm optimization(MUT-PSO)Algorithms to search for an optimum CNN architecture for Paddy leaf disease classification.Experimentation results show that Mutant Particle swarm optimization Convolution Neural Network(MUTPSO-CNN)can find optimumCNNarchitecture that offers better performance than existing hand-crafted CNN architectures in terms of accuracy,precision/recall,and execution time.