Development Of Network Architectures Research Articles

ISAC‐oriented access point placement in cell‐free mMIMO systems

AbstractIn mobile communication networks for integrated sensing and communication, site planning of access points fundamentally determines both communication quality and sensing performance. This paper aims to tackle the AP placement problem under the setting of cell‐free massive multiple‐input multiple‐output, which represents a promising direction for network architecture evolution. Seeking a balance between the sum‐throughput of communication and the Cramér–Rao lower bound of target sensing, the access points are first pre‐placed by solving a convex optimization and further adjusted with optimal angular geometry. The final step involves employing nearest neighbour projection to refine access point positions in the cell‐free massive multiple‐input multiple‐output system, ensuring alignment with integrated sensing and communication requirements. The numerical results show that the proposed algorithm achieves 90% of the optimal communication sum‐rate and 95% of the optimal target localization accuracy.

Explore the Evolution of Computer Network Architecture

Since the invention of computer networks in the 1960s, their architecture has undergone many major innovations and evolutions. This review aims to sort out and analyze this evolution process and reveal its internal motivations and fundamental driving forces. We will analyze the development of network architecture from multiple dimensions such as network topology, protocol stack, and control mechanism, and reveal the internal logic of the architecture evolving with the times.First, the paper reviews the origins of computer network development, explains the original packet switching ideas and ARPANET architecture, and analyzes its influence on later generations. Then it focuses on the birth of the TCP/IP protocol family and its architecture, analyzing its design concepts and innovations. Subsequently, the paper will explore the rise of the Internet and the formation of its layered architecture model, commenting on the advantages and disadvantages of this model. We will also examine the ideas and attempts of the next generation Internet architecture, such as active networks and content-centric networks, and analyze their challenges and limitations.In addition, the paper will explore the new changes brought about by emerging network paradigms such as software-defined networking (SDN) and network function virtualization (NFV) to network architecture, and comment on their advantages and impacts. We will also focus on the driving role of emerging paradigms such as cloud computing and edge computing on network architecture. Finally, the paper will look forward to new trends and challenges in the development of future network architecture, such as the potential application prospects of cutting-edge technologies such as artificial intelligence, machine learning, and blockchain in network architecture. By comprehensively analyzing and summarizing the evolution of network architecture, the paper hopes to provide readers with a macro perspective and a deep understanding of the internal driving force and development logic of network architecture innovation. This will not only help us understand the past, but also provide inspiration and ideas for future network architecture innovation.

Asynchronous evolution of deep neural network architectures

Many evolutionary algorithms (EAs) take advantage of parallel evaluation of candidates. However, if evaluation times vary significantly, many worker nodes (i.e., compute clients) are idle much of the time, waiting for the next generation to be created. Evolutionary neural architecture search (ENAS), a class of EAs that optimizes the architecture and hyperparameters of deep neural networks, is particularly vulnerable to this issue. This paper proposes a generic asynchronous evaluation strategy (AES) that is then adapted to work with ENAS. AES increases throughput by maintaining a queue of up to K individuals ready to be sent to the workers for evaluation and proceeding to the next generation as soon as M<<K individuals have been evaluated. A suitable value for M is determined experimentally, balancing diversity and efficiency. To showcase the generality and power of AES, it was first evaluated in eight-line sorting network design (a single-population optimization task with limited evaluation-time variability), achieving an over two-fold speedup. Next, it was evaluated in 11-bit multiplexer design (a single-population discovery task with extended variability), where a 14-fold speedup was observed. It was then scaled up to ENAS for image captioning (a multi-population open-ended-optimization task), resulting in an over two-fold speedup. In all problems, a multifold performance improvement was observed, suggesting that AES is a promising method for parallelizing the evolution of complex systems with long and variable evaluation times, such as those in ENAS.

Generative complex networks within a dynamic memristor with intrinsic variability

Artificial neural networks (ANNs) have gained considerable momentum in the past decade. Although at first the main task of the ANN paradigm was to tune the connection weights in fixed-architecture networks, there has recently been growing interest in evolving network architectures toward the goal of creating artificial general intelligence. Lagging behind this trend, current ANN hardware struggles for a balance between flexibility and efficiency but cannot achieve both. Here, we report on a novel approach for the on-demand generation of complex networks within a single memristor where multiple virtual nodes are created by time multiplexing and the non-trivial topological features, such as small-worldness, are generated by exploiting device dynamics with intrinsic cycle-to-cycle variability. When used for reservoir computing, memristive complex networks can achieve a noticeable increase in memory capacity a and respectable performance boost compared to conventional reservoirs trivially implemented as fully connected networks. This work expands the functionality of memristors for ANN computing.

Leveraging ICN and SDN for Future Internet Architecture: A Survey

Information-Centric Networking (ICN) and Software-Defined Networking (SDN) are both new evolving network architectures that are receiving a lot of attention from researchers. ICN is a Future Internet architecture which tries to transform the current Internet architecture from location- and host-centric to content-centric, where obtaining requested data is achieved by the contents’ names regardless of the location of the data. From another angle, SDN is considered a new Internet architecture that moves the control plane management from network devices to a centralized controller. The SDN controller enhances network robustness and improves its scalability, reliability, and flexibility. The integration of ICN and SDN results in massive benefits, where SDN enhances ICN networks’ manageability, controllability, and functionality, and ICN reshapes the SDN design to make it compatible with ICN features and to enhance ICN in terms of network caching, routing, mobility, and security.. In this review paper, a comprehensive survey of the issues and challenges of integrating ICN and SDN is presented. Firstly, ICN’s main characteristics are summarized, and a short comparison between different ICN architectures is completed. Then, the key details of SDN are highlighted. Moreover, the motivation and benefits of merging ICN with SDN are summarized and the state-of-the-art work on merging ICN and SDN is reviewed and classified from several aspects. Finally, several open research issues are highlighted.

Channel Shuffle Neural Architecture Search for Key Word Spotting

The evolution of Network Architecture (NA) allowed Key-Word Spotting (KWS) to exhibit high performance. Generally, NA for KWS is required to have low parameter and computation complexity maintaining high classification performance. Most of the attempts so far have been based on manual approaches, and often the architectures developed from such efforts dwell in the balance of the performance and the network complexity. Then, several KWS models based on Neural Architecture Search (NAS) technique have been proposed. However, these methods do not consider the number of parameters and FLOPs for NA in the search process and manually adjusted the complexity of NA by reducing the number of cells. It may not produce optimized NA with a balance between network complexity and performance. To develop effective network architecture for KWS, network complexity and performance must be considered. In this paper, we propose Channel Shuffle Neural Architecture Search (CSNAS) with channel weights. CSNAS selects whether each channel of the input feature is reflected in the computation or not in the search process and simultaneously controls the number of parameters, FLOPs, and performance. Experiment results show that CSNAS can generate NA that satisfies complexity and performance conditions, and NAs generated by CSNAS outperform state-of-the-art KWS methods.

Learning From Peers: Deep Transfer Reinforcement Learning for Joint Radio and Cache Resource Allocation in 5G RAN Slicing

Network slicing is a critical technique for 5G communications that covers radio access network (RAN), edge, transport and core slicing. The evolving network architecture requires the orchestration of multiple network resources such as radio and cache resources. In recent years, machine learning (ML) techniques have been widely applied for network management. However, most existing works do not take advantage of the knowledge transfer capability in ML. In this paper, we propose a deep transfer reinforcement learning (DTRL) scheme for joint radio and cache resource allocation to serve 5G RAN slicing. We first define a hierarchical architecture for joint resource allocation. Then we propose two DTRL algorithms: Q-value-based deep transfer reinforcement learning (QDTRL) and action selection-based deep transfer reinforcement learning (ADTRL). In the proposed schemes, learner agents utilize expert agents’ knowledge to improve their performance on current tasks. The proposed algorithms are compared with both the model-free exploration bonus deep Q-learning (EB-DQN) and the model-based priority proportional fairness and time-to-live (PPF-TTL) algorithms. Compared with EB-DQN, our proposed DTRL-based method presents 21.4% lower delay for Ultra Reliable Low Latency Communications (URLLC) slice and 22.4% higher throughput for enhanced Mobile Broad Band (eMBB) slice, while achieving significantly faster convergence than EB-DQN. Moreover, 40.8% lower URLLC delay and 59.8% higher eMBB throughput are observed with respect to PPF-TTL.

A Construction Kit for Efficient Low Power Neural Network Accelerator Designs

Implementing embedded neural network processing at the edge requires efficient hardware acceleration that combines high computational throughput with low power consumption. Driven by the rapid evolution of network architectures and their algorithmic features, accelerator designs are constantly being adapted to support the improved functionalities. Hardware designers can refer to a myriad of accelerator implementations in the literature to evaluate and compare hardware design choices. However, the sheer number of publications and their diverse optimization directions hinder an effective assessment. Existing surveys provide an overview of these works but are often limited to system-level and benchmark-specific performance metrics, making it difficult to quantitatively compare the individual effects of each utilized optimization technique. This complicates the evaluation of optimizations for new accelerator designs, slowing-down the research progress. In contrast to previous surveys, this work provides a quantitative overview of neural network accelerator optimization approaches that have been used in recent works and reports their individual effects on edge processing performance. The list of optimizations and their quantitative effects are presented as a construction kit, allowing to assess the design choices for each building block individually. Reported optimizations range from up to 10,000× memory savings to 33× energy reductions, providing chip designers with an overview of design choices for implementing efficient low power neural network accelerators.

Current trends and future perspective of designing on-chip antennas

AbstractWith the evolution of 5G and 6G network architectures, the demand for highly compact system-on-chip-based devices with high data transfer capabilities has been increased significantly. While the advancement of very large-scale integration technology with the continuous scaling of complementary metal–oxide–semiconductor nodes put forward to integrate different functional modules of a complete system on a single IC board, the antenna being the largest component still remains outside of the chip. Integration of the antenna and other functional modules of a system on the same chip leads to produce a really compact and economical design. Though on-chip antenna (OCAs) have several other advantages and emerging applications, they have some design challenges in terms of low gain due to losses in the substrate, requirement of miniaturization at lower microwave frequencies (LMFs) (particularly, below 10 GHz), unavailability of proper design rules, etc. In this paper, analyzing the design challenges of OCAs, their current research trends and future perspective applications are discussed.

Cycle and Self-Supervised Consistency Training for Adapting Semantic Segmentation of Aerial Images

Semantic segmentation is a critical problem for many remote sensing (RS) image applications. Benefiting from large-scale pixel-level labeled data and the continuous evolution of deep neural network architectures, the performance of semantic segmentation approaches has been constantly improved. However, deploying a well-trained model on unseen and diverse testing environments remains a major challenge: a large gap between data distributions in train and test domains results in severe performance loss, while manual dense labeling is costly and not scalable. To this end, we proposed an unsupervised domain adaptation framework for RS image semantic segmentation that is both practical and effective. The framework is supported by the consistency principle, including the cycle consistency in the input space and self-supervised consistency in the training stage. Specifically, we introduce cycle-consistent generative adversarial networks to reduce the discrepancy between source and target distributions by translating one into the other. The translated source data then drive a pipeline of supervised semantic segmentation model training. We enforce consistency of model predictions across target image transformations in order to provide self-supervision for the unlabeled target data. Experiments and extensive ablation studies demonstrate the effectiveness of the proposed approach on two challenging benchmarks, on which we achieve up to 9.95% and 7.53% improvements in accuracy over the state-of-the-art methods, respectively.

Holistic Network Virtualization and Pervasive Network Intelligence for 6G

In this tutorial paper, we look into the evolution and prospect of network architecture and propose a novel conceptual architecture for the 6th generation (6G) networks. The proposed architecture has two key elements, i.e., holistic network virtualization and pervasive artificial intelligence (AI). The holistic network virtualization consists of network slicing and digital twin, from the aspects of service provision and service demand, respectively, to incorporate service-centric and user-centric networking. The pervasive network intelligence integrates AI into future networks from the perspectives of networking for AI and AI for networking, respectively. Building on holistic network virtualization and pervasive network intelligence, the proposed architecture can facilitate three types of interplay, i.e., the interplay between digital twin and network slicing paradigms, between model-driven and data-driven methods for network management, and between virtualization and AI, to maximize the flexibility, scalability, adaptivity, and intelligence for 6G networks. We also identify challenges and open issues related to the proposed architecture. By providing our vision, we aim to inspire further discussions and developments on the potential architecture of 6G.

Software-Defined Networking: An Evolving Network Architecture—Programmability and Security Perspective

Software-defined networking is an evolving network architecture beheading the traditional network architecture focusing its disadvantages in a limited perspective. A couple of decades before, programming and networking were viewed as different domains which today with the lights of SDN bridging themselves together. This is to overcome the existing challenges faced by the networking domain and an attempt to propose cost-efficient effective and feasible solutions. Changes to the existing network architecture are inevitable considering the volume of connected devices and the data being held together. SDN introduces a decoupled architecture and brings customization within the network making it easy to configure, manage, and troubleshoot. This paper focuses on the evolving network architecture, the software-defined networking. Unlike a generic view on the evolving network, which makes work as a review, this work addresses various perspectives of the architecture leaving it an intermediate work in between the review of the literature and implementation, contributing towards factors like the design, programmability, security, security behaviors, and security lapses. This paper also analyses various weak points of the architecture and evolves the attack vectors in each plane leaving a conclusion to further progress towards identifying the impacts of the attacks and proposing mitigation strategies.

Evolution of Deep Neural Network Architecture Using Particle Swarm Optimization to Improve the Performance in Determining the Friction Angle of Soil

This study focuses on the use of deep neural network (DNN) to predict the soil friction angle, one of the crucial parameters in geotechnical design. Besides, particle swarm optimization (PSO) algorithm was used to improve the performance of DNN by selecting the best structural DNN parameters, namely, the optimal numbers of hidden layers and neurons in each hidden layer. For this aim, a database containing 245 laboratory tests collected from a project in Ho Chi Minh city, Vietnam, was used for the development of the proposed hybrid PSO-DNN model, including seven input factors (soil state, standard penetration test value, unit weight of soil, void ratio, thickness of soil layer, top elevation of soil layer, and bottom elevation of soil layer) and the friction angle was considered as the target. The data set was divided into three parts, namely, the training, validation, and testing sets for the construction, validation, and testing phases of the model. Various quality assessment criteria, namely, the coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE), were used to estimate the performance of PSO-DNN models. The PSO algorithm showed a remarkable ability to find out an optimal DNN architecture for the prediction process. The results showed that the PSO-DNN model using 10 hidden layers outperformed the DNN model, in which the average correlation improvement increased R2 by 1.83%, MAE by 5.94%, and RMSE by 8.58%. Besides, a global sensitivity analysis technique was used to detect the most important inputs, and it showed that, among the seven input variables, the elevation of top and bottom of soil played an important role in predicting the friction angle of soil.

Hierarchical Routing and Resource Assignment in Spatial Channel Networks (SCNs): Oriented Toward the Massive SDM Era

In the past few decades, the architecture of optical networks has undergone significant evolution, from the earliest wavelength-division multiplexing (WDM) optical networks to elastic optical networks (EONs) and later to space-division multiplexing (SDM) EONs, to address the continuous growth of Internet traffic. By 2024, Pbps-level optical networks are expected, far exceeding the capacity limit of single-mode fibers. The massive SDM era is on the horizon. In this context, a newly designed architecture for optical networks called the spatial channel network (SCN) architecture, which achieves high cost efficiency by means of practical hierarchical optical cross-connects, has recently been proposed. However, the evolution of optical network architectures will simultaneously present challenges related to network optimization. For instance, with the evolution from WDM optical networks to EONs, the kernel network optimization problem was transformed from the routing and wavelength assignment (RWA) problem into the routing and spectrum assignment (RSA) problem due to the additionally introduced constraint of spectrum contiguity. Similarly, specially designed algorithms are also expected to be essential for addressing the network optimization problem in SCNs. In this paper, we define this new problem as the routing, spatial channel, and spectrum assignment (RSCSA) problem. We propose an integer linear programming (ILP) model and a heuristic algorithm to solve the RSCSA problem. We examine the performance of the proposed approaches via simulation experiments. The results show that both proposed approaches are effective in finding the optimal solutions or solutions close to the lower bounds. To the best of our knowledge, this is the first work to focus on the network optimization problem in SCNs.

Mobile neural intelligent information system based on edge computing with interactive data

With the increasing popularity of smart mobile terminals, smartphones, tablet computers and other mobile devices will gradually replace personal computers and become the most important computing platform for consumers. Mobile edge computing (MEC), as a key technology for the evolution of communication network architecture, can meet the requirements of the system for throughput, delay, network scalability and intelligence. Based on the MEC, the content and services provided by information system are closer to users to increase mobile network speed, reduce latency and improve connection reliability. In this paper, we propose an interactive data information system based on mobile edge detection, which is divided into client and server. The server mainly provides services such as content and user login and rights management for the client. The client needs to log into the server to run normally. Among them, the interactive data server is a favorable support and guarantee for the client. The experimental results show that the proposed method has higher efficiency and fault tolerance.

Optimizing the network edge for flexible service provisioning

The virtualization of network resources provides unique flexibility in service provisioning in most levels of the network stack. Softwarization of the network control and operation (SDN) is a key enabler of that development. Starting from the network core, SDN is a dominant trend in the evolution of network architectures with increased emphasis recently on the network edge. I will present some recent results in this area starting with a study on migration from legacy networking to SDN enabled network modules. The tradeoff between the benefits of SDN upgrades and the cost of deployment is addressed and captured by an appropriate sub-modular function that allows to optimize the penetration pace of the technology. Validation on some real world network topologies and traffic matrices will be presented as well. Then we move our attention to the network periphery. A wireless multi-hop extension at the network edge is considered and the problem of enabling SDN is addressed via replication of SDN controllers. The delay constraints of the controlled data-path elements is appropriately modeled and the problem of locating the controllers is addressed via optimization and a proof-of concept implementation. An alternate approach is considered then for the wireless network where we assume coexistence of SDN enabled components with network islands operating under distributed adhoc routing protocols. The trade-off of the coexistence is studied and the impact of SDN penetration is evaluated. Some paradigms of collaborative network services are presented finally as they are enabled by the above architectural evolution.

On Orchestrating Service Function Chains in 5G Mobile Network

As two of the key technologies of 5G, fog-based radio access network and network function virtualization have become an important direction for the radio network architecture evolution. Virtual network functions (VNFs) compose the service function chain (SFC) in a particular order, and the mobile network users communicate with each other or service terminals through SFCs. For service providers, it is crucially important for efficient deploying/mapping SFCs into the 5G mobile network since the SFCs deployment problem is an NP-hard problem. In this paper, we propose the efficient SFCs deployment algorithms for solving this challenge with two main design goals: 1) minimizing the cost of link resource, i.e., minimizing the path length of the entire SFC by combining VNFs and mapping temporary links and 2) minimizing the cost of computing resources by using the existing virtual machines as much as possible while performing the same VNF. We model the SFCs deployment problem as an optimization problem by using ILP as well as devise the heuristic algorithms to make the tradeoff between these two conflicting design goals. From simulation results, we can see that the performance of our proposed algorithms is promising in terms of the total SFCs mapping cost, total links mapping cost, and blocking ratio.

The 4G to 5G Network Architecture Evolution in Australia

This paper provides a review of selected design and security aspects of 5G systems and addresses key questions about the deployment scenarios of Next Generation Radio Access Networks in Australia. The paper first presents the most relevant 5G use cases for the Australian market in 2018-19, and beyond; 5G concept and definitions; 3GPP updates, in terms of system architecture and enabling technologies and corresponding timelines; and spectrum availability, linked to possible 5G deployments in Australia. Then, the paper discusses the 5G functional architecture, possible configuration options, enabling technologies and network migration strategies and related 5G security, in Australia and globally. This is followed by a description of the possible 5G deployment scenarios in a multivendor environment and includes, as a case study, the Huawei product portfolio and site solution in Australia. The paper concludes with a discussion on the potential benefits of a telecommunications security assurance centre to improve the whole-of-life security assurance of critical telecommunications infrastructure and why it is important for the Australia telecommunications sector.

The 4G to 5G Network Architecture Evolution in Australia

This paper provides a review of selected design and security aspects of 5G systems and addresses key questions about the deployment scenarios of Next Generation Radio Access Networks in Australia. The paper first presents the most relevant 5G use cases for the Australian market in 2018-19, and beyond; 5G concept and definitions; 3GPP updates, in terms of system architecture and enabling technologies and corresponding timelines; and spectrum availability, linked to possible 5G deployments in Australia. Then, the paper discusses the 5G functional architecture, possible configuration options, enabling technologies and network migration strategies and related 5G security, in Australia and globally. This is followed by a description of the possible 5G deployment scenarios in a multivendor environment and includes, as a case study, the Huawei product portfolio and site solution in Australia. The paper concludes with a discussion on the potential benefits of a telecommunications security assurance centre to improve the whole-of-life security assurance of critical telecommunications infrastructure and why it is important for the Australia telecommunications sector.

A Systematic Literature Review on Military Software Defined Networks

Software Defined Networking (SDN) is an evolving network architecture paradigm that focuses on the separation of control and data planes. SDN receives increasing attention both from academia and industry, across a multitude of application domains. In this article, we examine the current state of obtained knowledge on military SDN by conducting a systematic literature review (SLR). Through this work, we seek to evaluate the current state of the art in terms of research tracks, publications, methods, trends, and most active research areas. Accordingly, we utilize these findings for consolidating the areas of past and current research on the examined application domain, and propose directions for future research.