In recent years, we observe a growing trend in the area of artificial intelligence (AI) for network and service management. Approaches such as statistical analysis, data mining and machine learning have become promising to harness the immense stream of operational data and to improve the management of networks and system. Thus, CNSM 2019 was focused on what matters most to managing networks and services. Many researchers from the field of network and service management have explored how AI can help us not only sense but also shape the future of management as AI technologies have disrupted numerous industries.

To manage the configuration, performance, resilience, availability and security of the networks and services, traditional measures such as log/event analysis, intrusion detection/prevention and monitoring and deployment have taken a new dimension. New techniques and mechanisms from AI, machine learning and data mining are explored for designing, developing and operating networks and systems. In summary, there are a lot of research challenges in this emerging field of embracing the new wave of AI.

The purpose of this special issue is to explore and highlight the promising capabilities of AI in managing the operational data on the networks and services. Among the top research papers presented at the 2019 International Conference on Network and Service Management, four of them are selected and the extended versions of those papers went under extensive reviews and discussions. These four papers were finally selected for publication in this special issue. The authors of these papers were given the time to update their papers based on the review comments and suggestions provided. The selected papers address topics that play a central role in embracing the new wave of AI for network and service management and presenting novel theoretical and/or experimentation results.

The first paper, “On Accounting for Screen Resolution in Adaptive Video Streaming: QoE Driven Bandwidth Sharing Framework,” by Belmoukadam et al. analyses the problem of bandwidth allocation for multiple video streaming sessions over a shared link and proposes an optimization framework to maximize the overall quality of experience (QoE) taking into consideration terminal display capabilities. The approach relies on a Lagrangian relaxation heuristic and Karush–Kuhn–Tucker (KKT) conditions to efficiently solve the optimization problem, showing an increase of up to 20% of the overall QoE compared with an allocation with a TCP look‐alike strategy implementing max–min fairness.

The second paper, “Towards Distributed Emergency Flow Prioritization in SDN Networks,” by Moeyersons et al. proposes a microservices‐based framework, which is able to run both as a centralized and distributed system. Moreover, the proposed framework guarantees the required bandwidth for the emergency flows and maximizes the best‐effort flows over the remaining bandwidth based on their priority. The offline linear model part of the framework is evaluated through simulation, the distributed model is evaluated through emulation while the online approach is validated through physical experiments with SDN switches. Finally, as a proof of concept, a prototype with Zodiac switches validates the feasibility of the centralized framework.

The third paper, “OpenBNG: Central Office Network Functions on Programmable Data Plane Hardware,” by Kundel et al. explores to offer residential network access with programmable packet processing architectures. The authors present the design and open‐source implementation of a Broadband Network Gateway data plane using P4 programming language. Moreover, they introduce a concept of hybrid openBNG design, realizing the required hierarchical quality of service functionality in a subsequent FPGA. Evaluation results show the desired performance characteristics towards highest performance NFV network access.

Finally, the fourth paper, “De‐anonymizing Ethereum Blockchain Smart Contracts through Code Attribution,” by Linoy et al. is on analysing the pseudo‐anonymity of blockchain technologies. The paper proposes to leverage a stylometry approach to investigate the extent to which a deployed contract's source code can contribute to the affiliation of the deployers' account addresses. Authors have prepared a dataset of real‐world contract data; design and implement feature selection, extraction techniques and data refinement heuristics; and examine their effect on attribution accuracy. They further evaluate the proposed system to test the classification of real‐world scammer data.

We expect future work in the area of embracing the new wave of AI for network and service management to further explore the topics addressed by the selected papers. The guest editors of this special issue wish to acknowledge the excellent work that has been performed by the authors, who submitted papers, and by the reviewers, who have spent a considerable amount of their time providing high‐quality reviews. We would also like to extend our thanks to the editorial board of the International Journal of Network Management, in particular to editor‐in‐chief James Won‐Ki Hong and associate editor‐in‐chief Jérôme François and Lisandro Zambenedetti Granville, for the great opportunity and their support in editing this special issue. Last but not the least, we thank the editorial team of Wiley, for the support offered to the authors.

DATA AVAILABILITY STATEMENT

This is to confirm that there are no data available for this editorial paper.

中文翻译：

---

CNSM 2019特刊：拥抱人工智能的新潮流

近年来，我们观察到用于网络和服务管理的人工智能（AI）领域的增长趋势。统计分析，数据挖掘和机器学习之类的方法已有望利用巨大的操作数据流并改善网络和系统的管理。因此，CNSM 2019专注于管理网络和服务最重要的方面。来自网络和服务管理领域的许多研究人员探索了AI如何帮助我们不仅感知而且塑造了管理的未来，因为AI技术已经破坏了许多行业。

为了管理网络和服务的配置，性能，弹性，可用性和安全性，日志/事件分析，入侵检测/预防以及监视和部署等传统措施已采用了新的维度。探索了来自AI，机器学习和数据挖掘的新技术和机制，用于设计，开发和运营网络和系统。综上所述，在拥抱新一波AI的新兴领域中，存在许多研究挑战。

本期特刊旨在探讨并强调AI在管理网络和服务上的运营数据方面的有前途的功能。在2019年国际网络和服务管理国际会议上提交的顶级研究论文中，选择了其中的四篇，并对这些论文的扩展版本进行了广泛的审查和讨论。最终，这四篇论文最终被选中发表。这些论文的作者有时间根据所提供的评论和建议来更新其论文。所选论文的主题在拥抱AI在网络和服务管理的新潮流中发挥重要作用，并提出了新颖的理论和/或实验结果。

Belmoukadam等人的第一篇论文“关于在自适应视频流中考虑屏幕分辨率：QoE驱动的带宽共享框架”。分析了共享链接上多个视频流会话的带宽分配问题，并提出了一种优化框架，以考虑终端显示功能，从而使总体体验质量（QoE）最大化。该方法依靠拉格朗日松弛试探法和Karush-Kuhn-Tucker（KKT）条件来有效地解决优化问题，与采用TCP近似策略的方案实现最大数量分配相比，该方案显示出将总体QoE提高了20％ –最小公平。

Moeyersons等人的第二篇论文“向SDN网络中的分布式紧急流优先级迈进”。提出了一个基于微服务的框架，该框架既可以作为集中式系统又可以作为分布式系统运行。此外，提出的框架保证了紧急流所需的带宽，并根据优先级在剩余带宽上最大化了尽力而为流。框架的离线线性模型部分通过仿真进行评估，分布式模型通过仿真进行评估，而在线方法则通过使用SDN交换机的物理实验进行验证。最后，作为概念验证，带有Zodiac开关的原型验证了集中式框架的可行性。

Kundel等人撰写的第三篇论文“ OpenBNG：可编程数据平面硬件上的中心局网络功能”。致力于通过可编程的数据包处理体系结构为住宅网络提供接入。作者介绍了使用P4编程语言的宽带网络网关数据平面的设计和开源实现。此外，他们引入了混合openBNG设计的概念，在随后的FPGA中实现了所需的服务质量分层功能。评估结果显示了实现最高性能NFV网络访问所需的性能特征。

最后，Linoy等人的第四篇论文“通过代码归因对以太坊区块链智能合约进行匿名化”。正在分析区块链技术的伪匿名性。本文建议利用测度方法来调查已部署合同的源代码在多大程度上可以促进部署者帐户地址的隶属关系。作者已经准备了真实合同数据的数据集；设计和实施特征选择，提取技术和数据细化启发法；并检查它们对归因准确性的影响。他们进一步评估了提议的系统，以测试真实骗子数据的分类。

我们希望在拥抱网络和服务管理的新一波AI领域的未来工作能够进一步探索所选论文所涉及的主题。本期特刊的特邀编辑要感谢作者，提交论文的作者和审稿人所做的出色工作，他们花了大量时间提供高质量的审稿。我们还要感谢《国际网络管理杂志》的编辑委员会特别是主编James Won-Ki Hong和副主编JérômeFrançois和Lisandro Zambenedetti Granville，感谢他们为编辑本期特刊提供的巨大机会和支持。最后但并非最不重要的一点，我们感谢Wiley的编辑团队为作者提供的支持。

数据可用性声明

这是为了确认没有可用于该社论论文的数据。