http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Machine-Learning-Driven Multi-Objective Optimization for IBN-Based Orchestration
Khan Talha Ahmed,Khizar Abbas,Afaq Muhammad,Wang-Cheol Song 한국통신학회 2022 한국통신학회 학술대회논문집 Vol.2022 No.2
Modern networks are aimed at offering state-of-the-art services for their users. However, each impending service requires a distinct KPI (Key Performance Indicators) and is distributed over an extensive infrastructure. Thus, requiring a complex service orchestration procedure having explicit policies throughout the low-level network infrastructure. However, the achievement of such policies at the low level over globally distributed, multi-vendor infrastructure has multi-dimensional complexity. Also, it is very challenging to perform dynamic assessment and update procedure at low-level infrastructure using traditional approaches. Hence, this manuscript, on one end, considers resolving multi-dimensional KPI achievement through Machine-Learning assisted multi-objective optimization. On the other hand, it uses the IBN approach that enables high-level service definition, and it automates the policy deployment on the low-level infrastructure.
IBN-based E2E Service Orchestration on Top of KOREN
Khan Talha Ahmed,Khizar Abbas,Afaq Muhammad,Wang-Cheol Song 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.6
The increasing number of services impacted in the rise of complexity for E2E service orchestration. The newer network requirements of bandwidth achievement and QoS requirements have forced the researcher towards innovative design of underlying networks. This work proposes an IBN-based E2E service orchestration which will automate the process of service provisioning and its dynamic management. The proposed system will ensure the service assurance while keeping the requested context of the service. In addition, the IBN platform will enable orchestration of service for UAV (Unmanned Arial Vehicles) over several underlying platforms. It also considers the orchestration of service over multiple domains and utilizes FlexRAN and OSM (OpsourceMANO) as RAN and Core orchestrators. In addition, it is based on KOREN Transport infrastructure to interconnect multiple domains.
Generic Intent-based Networking Platform for E2E Network Slice Orchestration & Lifecycle Management
Talha Ahmed Khan,Khizar Abbass,Adeel Rafique,Afaq Muhammad,Wang-Cheol Song 한국통신학회 2020 한국통신학회 APNOMS Vol.2020 No.09
5G claims the service provisioning for a variety of new applications increasing orchestration complexity. Additionally, many different orchestrators and platforms have been developed over recent years to handle and control the network infrastructures. However, each of the orchestration platforms requires different expertise for handling them. The diversity and dynamicity in terms of requirements made it very complex for the operators to handle runtime operations. As with the increasing number of devices, the amount of traffic streamed over network deviates drastically making it impossible for network operators to handle the network operations manually. Hence automated platforms are a dire need, this work proposed a generic intent-based system that can automatically orchestrate and manage network lifecycle over multiple domains, sites and orchestrators. This system will include the orchestration over multiple domains access, transport and core and it also includes the use of Machine Learning for prediction of resource status for proactive decision making to manage the slice lifecycle automatically.
5G Network Slicing and its Standards and Platforms
Khan Talha Ahmed,Wang-Cheol Song 한국통신학회 2018 정보와 통신 Vol.35 No.8
The fifth generation (5G) networks occupy a central role in providing wide range of concurrent services on demand to 5G mobile users. Slicing up the core network in multiple isolated logical networks is envisioned as the key to realize the 5G network technology. Furthermore, bonding of network function virtualization and software defined networking made network slicing in 5G a reality. In this article, along with discussing the importance and basic concepts of slicing in 5G networks, we will also summarize the efforts being made by various research groups and standard organizations to enable end-to-end slicing with its various application and use cases in a very systematic way.
IBN-based: AI-driven Multi-Domain e2e Network Orchestration Approach
Talha Ahmed Khan,AFAQ MUHAMMAD,기자르 아바쓰,송왕철 한국통신학회 2020 KNOM Review Vol.23 No.2
Networks are growing faster than ever before causing a multi-domain complexity. The diversity, variety and dynamic nature of network traffic and services require enhanced orchestration and management approaches. While many standard orchestrators and network operators are resulting in an increase of complexity for handling E2E slice orchestration. Besides, there are multiple domains involved in E2E slice orchestration including access, edge, transport and core network each having their specific challenges. Hence, handling of multi-domain, multi-platform and multi-operator based networking environments manually requires specified experts and using this approach it is impossible to handle the dynamic changes in the network at runtime. Also, the manual approaches towards handling such complexity is always error-prone and tedious. Hence, this work proposes an automated and abstracted solution for handling E2E slice orchestration using an intent-based approach. It abstracts the domains from the operators and enable them to provide their orchestration intention in the form of high-level intents. Besides, it actively monitors the orchestrated resources and based on current monitoring stats using the machine learning it predicts future utilization of resources for updating the system states. Resulting in a closed-loop automated E2E network orchestration and management system.
Faiza Khan,Talha Mubashir,Kainat Ahmed,Muhammad Shahoor,Abdul Mateen,이순일,Tauseef Ahmed 한국전기전자재료학회 2023 Transactions on Electrical and Electronic Material Vol.24 No.6
This paper investigates the electrical resistivity of piezoresistive CNT/PVAc-based nanocomposites. Different CNTs wt. % containing multi-walled carbon nanotubes (MWCNTs) dispersed in polyvinyl acetate and deposited on a flexible polymer substrate of ethylene glycol methacrylate (PVAc) matrix using conventional methods. The morphological changes were observed using SEM analysis. The resulting composites were subjected to compression by applying different values of pressure (9.3-2348.8 kPa). The results show that for lower wt. % of CNTs, the value of resistance decreased (~0.01526MΩ) with increasing applied pressure, which could be attributed to increasing the conducting paths with compression. However, increasing the concentration of CNTs to a higher value > 1.0 wt. %, results show the opposite behavior, an increase in resistance with an increase in pressure, which could be ascribed to the reorientation, bending, and entanglement of CNTs blocking the conducting paths. The percolation threshold for CNT/PVAc nanocomposite is 0.1 wt. %. This study provides valuable insights into the structural and sensing properties of CNT-based pressure Nanosensors and highlights their potential for use in various applications.
Intent-Based Network Slice Life Cycle Management
Khizar Abbas,Talha Ahmed Khan,Afaq Muhammad,Wang-Cheol Song 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.2
5G networks have to accommodate a diverse set of services with different performance, latency, bandwidth, and reliability requirements. It is not possible to handle multi-services needs with legacy cellular networks due to the same physical infrastructure. The programmable and virtualized nature of the 5G network makes it possible to manage these multi-services by providing different resources to each service. Network slicing is a promising solution to support the multi-services environment where the same physical network is partitioned into isolated multiple logical networks. This research paper has proposed an end-to-end (e2e) network slicing through an intent-based network (IBN) approach. Our system can manage the life cycle of the network slice in an automated fashion. It can also monitor, update, and manage the slices by using deep learning.