The 4th IEEE/IFIP International Workshop on Analytics for Network and Service Management (AnNet 2019) will be held in conjunction with the IFIP/IEEE International Symposium on Integrated Network Management (IM) in Washington DC, USA on April 8, 2019.
AnNet aims to present research and experience results in data analytics and machine learning for network and service management. Approaches such as statistical analysis, data mining and machine learning are promising to harness the immense stream of operational data and to improve operations and management of IT systems and networks.
AnNet 2019 will include original full-paper presentations, a keynote, and short-paper sessions. The workshop attendees will be stimulated to participate in interesting discussions. Short papers describing late-breaking advances and work-in-progress reports from ongoing research and experimental work are also welcome.
- Paper Registration: November 16, 2018
- Paper Submission: November 20, 2018
- Acceptance Notification: December 20, 2018
- Camera-Ready Papers: January 15, 2019
- Workshop Date: April 8, 2019
TOPICS OF INTEREST
Authors are invited to submit papers that fall into or are related to one or multiple topic areas listed below:
- Analysis, modeling and visualization
- Operational analytics and intelligence
- Event, log and big data analytics
- Network traffic analysis
- Anomaly detection and prediction
- Crowd sensing
- Monitoring and measurements for management
- Predictive and real-time analytics
- Harnessing social data for management
Machine learning techniques
- Supervised, semi-supervised, and unsupervised learning
- Clustering and data mining
- Reinforcement learning
- Multi-agent based learning
- Deep learning
- Bayesian methods
- Ensemble methods
- Cognitive computing
- Mining spatiotemporal and time series data
Network management paradigms
- Autonomous and autonomic networks
- Fog/edge computing
- In-network processing
- Bio-inspired networks and self-management
- Cognitive and software defined networks
- Network function virtualization
- Security, fault, performance, and resource management
- Computer networks
- Mobile ad-hoc and wireless sensor networks
- Clouds and data centers
- Virtualized infrastructures
- Internet of Things
- Computing and network services
- IT service management, storage resource management
Paper submissions must present original, unpublished research or experiences. Only original papers that have not been published or submitted for publication elsewhere can be submitted. Each submission must be written in English, accompanied by a 75 to 200 words abstract that clearly outlines the scope and contributions of the paper. There is a length limitation of 6 pages (including title, abstract, all figures, tables, and references) for regular papers, and 4 pages for short papers describing work in progress. Submissions must be in IEEE 2-column style. Self-plagiarised papers will be rejected without further review. Authors should submit their papers via the JEMS system:
Papers accepted for AnNet 2019 will be included in the conference proceedings, IEEE Xplore, IFIP database and EI Index. IFIP and IEEE reserve the right to remove any paper from the IFIP database and IEEE Xplore if the paper is not presented by one of its authors at the workshop. Awards will be presented to the best paper at the workshop.
- Nur Zincir-Heywood, Dalhousie University, Canada
- Idilio Drago, Politecnico di Torino, Italy
- Robert Harper, Moogsoft, UK
For more information, contact the chairs at: firstname.lastname@example.org
The current interest in both Artificial Intelligence (AI) and Machine Learning (ML) techniques in the context of network management has come about due to the requirement to address the complex management of software defined infrastructures, including slices, SDN, NFV, and SFC features, which are beyond the reasonable input, scope and ability for direct human interaction. Progress in both computing hardware (such as GPUs, TPUs, and bespoke chip architectures), as well and the performance and accuracy of machine learning methods such as neural networks, has made Artificial Intelligence and Machine Learning realistic approaches for use in network management.
The AIMLEM workshop addresses both the advances and challenges related to Artificial Intelligence and Machine Learning techniques for enhanced network management of network elements and services in current and future highly dynamic and highly scalable 5G environments.
The advances and challenges are expected to be multiple, and there are clearly many open questions that need to be addressed, including:
- How can Artificial Intelligence and Machine Learning Techniques really be used for effective and/or enhanced network management;
- What are the abstractions and knowledge representation / data models needed to ensure that AI is deployable for network management and orchestration;
- How do the existing technologies of networking, NFV, SDN, services become features and aspects of AI and ML, and how are they managed in this context;
- Is it better to adapt existing components to support AL and ML, or is it better to design new ones, considering the price / performance trade-offs for introducing AI/ML in management and orchestration;
- How can the use of induction and explanation systems of AI highlight what decisions have been made and how these situations have occurred.
AIMLEM aims at providing an international forum for researchers and practitioners from academia, industry, network operators, and service providers to discuss and address the challenges deriving from such emerging scenarios where AI and ML systems, processes, and workflows used in both service and network domains. The workshop welcomes contributions from both computing and network-oriented research communities, with the aim of facilitating discussion, cross-fertilization and exchange of ideas and practices, and successfully promote innovative solutions toward a real use of AI and ML. Contributions that discuss lessons learnt and best practices, describe practical AI and ML deployment and implementation experiences, and demonstrate innovative AI and ML use-cases are especially encouraged for presentation and publication.
We are interested in papers that use Artificial Intelligence and/or Machine Learning the following topics:
- Distributed versus centralised management architectures and algorithmic approaches of AI and ML for 5G
- Dynamic management and orchestration for virtualized features of NFV, SDN, and SFC (including function placement, network slicing)
- AI assisted network and cloud slicing
- Data, information, and semantic models, and abstractions and knowledge representation for AI systems in network management
- Network data / metadata collection, analysis, distribution, and visualisation for operations and testing of AI/ML methods and algorithms
- Evaluation (performance and feasibility) of integrating AI and ML into the networks (e.g., operation, management and orchestration)
- Success scenarios of AI/ML demonstrated in network management
- And other AI / ML management and orchestration related topics
- Workshop Paper Submission: November 23, 2018
- Notification of Acceptance: December 18, 2019
- Camera-ready Submission: January 10, 2019
Submitted papers must be original work, not under review at other journals/conferences, and may comprise a maximum of 6 A4 (210 mm x 297 mm) pages in 2-column IEEE conference style with a minimum font size of 10 pt. Papers should be submitted electronically using the EDAS online submission system. All accepted papers must be presented by one of the authors.
Submission at: http://edas.info/N25418
Papers accepted for AIMLEM 2019 will be included in the conference proceedings and IEEE Xplore. The IEEE reserves the right to remove any paper from IEEE Xplore if the paper is not presented at the workshop.
- Stuart Clayman (University College London, UK)
- Slawomir Kuklinski (Orange Labs, Warsaw, Poland)
- Qiong Zhang (Fujitsu Laboratories, Dallas USA)
- Min Xie (Telenor Research, Norway)
- Rashid Mijumbi (Nokia Bell Labs, Dublin, Ireland)
Workshop website: https://www.icin-conference.org/AIMLEM.php
Intelligent network is the use of cognitive computing technologies to meet the various requirements of seamless wide-area coverage, high-capacity hot-spot, low-power massive-connections, low latency, high-reliability, and other scenarios. An intelligent network can be viewed as the existing network integrated with cognitive and cooperative mechanisms to promote performance and achieve intelligence. Under the new service paradigm, there are various technical challenges and problems that need to be addressed in order to extensively improve the user’s quality of experience (QoE), such as complicated decision making for routing, dynamic and context-aware network management, resource optimization, and in-depth knowledge discovery in complex environments.
Assisted by artificial intelligence (AI) and machine learning, an intelligent network is expected to greatly enhance user experience and have a huge impact to all aspects of people’s lifestyles in terms of work, social interactions, and economy. In particular, network ecosystems could be upgraded with new capabilities, such as the provisioning of personalized and smart network services assisted by AI, optimized communication physical layer design based on machine learning, and adaptive resource management based on cognitive power that can mimic or augment human intelligence.
This Special Issue (SI) will bring together academic and industrial researchers to discuss technical challenges and recent results related to intelligent networks. To meet the demanding requirements needed for user experience, efficiency, and performance in a complex network environment, novel design, configuration, and optimization for communications and networking are in great need.
Submitted papers in this SI are expected to focus on state-of-the-art research in various aspects of intelligent network, especially the use of AI and machine learning for communication and networking. Topics of interest include, but are not limited to, the following areas:
- Innovative architecture, infrastructure, techniques and testbeds for intelligent network
- Machine learning, AI and other innovative approaches for intelligent network
- Context-aware, emotion-aware, and other novel networking services
- Multi-modal information fusion, contextual data management and in-depth knowledge discovery for complex networking environment
- Data-driven behavior prediction for cognitive network
- Network tools, testbed and performance evaluation based on AI and machine learning
- AI-based performance evaluation for Intelligent Network
Manuscripts should conform to the standard format as indicated in the Information for Authors section of the Paper Submission Guidelines. All manuscripts to be considered for publication must be submitted by the deadline through Manuscript Central. Select the “Special Issue: Intelligent Network Assisted by Cognitive Computing and Machine Learning” topic from the drop-down menu of Topic/Series titles.
- Manuscript Submission Deadline: October 10, 2018
- Initial Decision: November 30, 2018
- Revised Manuscript Due: Dececember 31, 2018
- Decision Notification: January 31, 2018
- Final Manuscript Due: February 15, 2019
- Publication Date: May 2019
- Min Chen (Huazhong University of Science and Technology, China)
- Honggang Wang (UMass Dartmouth, Dartmouth, MA, USA)
- Sanjeev Mehrotra (Microsoft Research, USA)
- Victor C. M. Leung (The University of British Columbia, Canada)
- Iztok Humar (University of Ljubljana, Slovenia)
Paper submissions deadline: *September 12th, 2018*, 11:59:59 EDT (midnight)
AI and Machine Learning are currently being exploited in almost every scientific fields. However, networking has still a limited development and deployment of these techniques.
AI can be effectively used in many networking areas, such as fault isolation, intrusion detection, event correlation, log analysis, capacity planning, and design optimization, just to name a few. Moreover, the complexity of today networks makes it challenging to design scalable network measurement and analysis techniques and tools. Machine learning and big data analytics techniques promise to shed light on this enormous amount of data, but smart and scalable approaches must be conceived to make them applicable to the networking practice.
WAIN workshop aims at showing to the community new contributions in this field. It looks for smart approaches and uses cases useful for understanding when and how applying AI in networking. The workshop will allow researchers and practitioners to share their experiences and ideas and discuss the open issues related to the application of machine learning to computer networks data.
This workshop will include both contributed and invited papers.
Papers will be published at ACM SIGMETRICS Performance Evaluation Review (https://www.sigmetrics.org/per.shtml,*2 to 4 page long*). Furthermore, authors will have the option to submit a longer version of their paper to one of the special issues.
Topics of Interest
The following is a non-exhaustive list of topics of interest for WAIN workshop:
- Applications of ML in communication networks
- Data analytics and mining in networking
- Traffic monitoring through AI
- Application of deep learning and reinforced-learning in networking
- Benchmarks design for big data or ML
- Protocol design using ML
- Methodologies for network anomaly detection and cybersecurity
- Visualization for network characteristics and trafficmonitoring
- Requirements and expectations when using AI
- AI applied to IoT, 5G or cloud
- Performance Optimization through ML and Big Data
- Experiences and best-practices using machine learning in operational networks
- Reproducibility of ML in networking
- Paper submissions deadline: *September 12th, 2018*, 11:59:59 EDT (midnight)
- Notification of Acceptance: *October 12th, 2018*
Submissions must be original, unpublished work, and not under consideration at another conference or journal. The format for the submissions is that of PER (two-column 10pt ACM format), *between 2 and 4 pages long,* including all figures, tables, references, and appendices. Papers must include authors names and affiliations for single-blind peer reviewing by the PC. Authors of accepted papers are expected to present their papers at the workshop.
EasyChair submission website will be online within few days.
- Luca Vassio <https://www.tlc-networks.polito.it/public/phd-and-post-docs/luca-vassio>, Politecnico di Torino, Italy
- Zhi-Li Zhang <http://www-users.cs.umn.edu/~zhang089/>, University of Minnesota, US
- Sung-Ju Lee <https://sites.google.com/site/wewantsj/home>, KAIST, Korea
- Marco Canini, KAUST (Saudi Arabia)
- Song Chong, KAIST, (South Korea)
- Edmundo de Souza e Silva, Federal University of Rio de Janeiro (Brazil)
- Lixin Gao, UMASS (USA)
- Danilo Giordano, Politecnico di Torino (Italy)
- Leana Golubchik, University of Southern California (USA)
- Dan Li, Tsinghua University (China)
- Marco Mellia, Politecnico di Torino (Italy)
- Giovanni Neglia, Inria (France)
- Rayadurgam Srikant, UIUC (USA)
- Patrick Thiran, EPFL (Switzerland)
- Martino Trevisan, Politecnico di Torino (Italy)
- Hui Zang, Huawei Santa Clara (USA)
- Nur Zincir-Heywood, Dalhousie University (Canada)
2nd International Workshop on Network Intelligence (NI 2019)
“Machine Learning for Networking”
in conjunction with IEEE INFOCOM 2019
29 April – 2 May 2019 – Paris, France
Technically Sponsored by IEEE Communications Society,
Technical Committee on Cognitive Networking,
Technical Committee on Big Data, and
IEEE Network Intelligence Emerging Technologies initiative (IEEE NI ETI)
Network Intelligence considers the embedding of Artificial Intelligence (AI) in future networks to fasten service delivery and operations, leverage Quality of Experience (QoE) and guarantee service availability, also allowing better agility, resiliency, faster customization and security. This concept inherits the solid background of autonomic networking, cognitive management, and artificial intelligence. It is envisioned as mandatory to manage, pilot and operate the forthcoming network built upon SDN, NFV and cloud.
The main goal of the Network Intelligence Workshop is to present state-of-the-art research results and experience reports in the area of network intelligence, addressing topics such as artificial intelligence techniques and models for network and service management; smart service orchestration and delivery, dynamic Service Function Chaining, Intent and policy based management, centralized vs. distributed control of SDN/NFV based networks, analytics and big data approaches, knowledge creation and decision making. This workshop offers a timely venue for researchers and industry partners to present and discuss their latest results in Network Intelligence.
The main topic of this NI 2019 edition is “Machine Learning for Networking” which puts the attention on the particular application of machine learning tools to the optimization of next generation networks. Machine and deep learning techniques become increasingly popular and achieve remarkable success nowadays in many application domains, e.g., speech recognition, bioinformatics and computer vision. Machine learning is capable to exploit the hidden relationship from voluminous input data to complicated system outputs, especially for some advanced techniques, like the deep learning. Moreover, some other techniques, e.g., reinforcement learning, could further adapt the learning results in the new environments to evolve automatically. These features perfectly match the complex, dynamic and time-varying nature of today’s networking systems.
This workshop is supported by IEEE ComSoc Emerging Technical Initiative on Network Intelligence, technically sponsored by IEEE Communications Society, Technical Committee on Cognitive Networking, and Technical Committee on Big Data.
Topics of Interest
This workshop presents state-of-the-art research in machine learning for networking. Both theoretical and system papers will be considered, to present novel contributions in the field of machine learning, deep learning and, in general, network intelligent tools, including scalable analytic techniques and frameworks capable of collecting and analyzing both online and offline massive datasets, open issues related to the application of machine learning into communications and networking problems and to share new ideas and techniques for machine learning in communication systems and networks. The topics of interest include (but not limited to):
Papers must be submitted electronically as PDF files, formatted for 8.5×11-inch paper. The length of the paper must be no more than 6 pages in the IEEE double-column format (10-pt font). Papers should neither have been published elsewhere nor being currently under review by another conference or journal. The reviews will be single blind. At least one of the authors of every accepted paper must register and present the paper at the workshop. Accepted papers will be published in the combined INFOCOM 2019 Workshop proceedings and will be submitted to IEEE Xplore.
EDAS link for paper submission: http://edas.info/N25585
General Chairs (ordered by last name)
Technical Program Committee Chairs (ordered by last name)
NI Steering Committee Members (ordered by last name)
Series on Data Science and Artificial Intelligence for Communications
The objective of the Data Science and Artificial Intelligence for Communications Series of the IEEE Communications Magazine is to provide a forum across industry and academia to advance the development of network and system solutions using data science and artificial intelligence.
Innovations in artificial intelligence, machine learning, reinforcement learning and network data analytics introduce new opportunities in various areas, such as channel modeling and estimation, cognitive communications, interference alignment, mobility management, resource allocation, network control and management, network tomography, multi-agent systems, prioritization of network ultra-broadband deployments. These new analytic platforms will help revolutionize our networks and user experience. Through gathering, processing, learning and controlling the vast amounts of information in an intelligent manner future networks will enable unprecedented automation and optimization.
This Series solicits articles addressing numerous topics within its scope including, but not limited to, the following:
- All aspects of artificial intelligence, machine learning, reinforcement learning and data analytics aiming at enabling and enhancing next generation networks. The scope of issues that can be addressed includes both conventional measures such as traffic management, QoE, service quality, as well as future network behavior through intelligent services and applications.
- Methods, systems and infrastructure for the analysis of network, service traffic and user behavior for efficient and reliable design of networks, including deep learning and statistical methods for network tomography.
- Predictive analytics and artificial intelligence for network optimization, network security, network assurance, and data privacy and integrity. Diagnosis of network failures using analytics and AI.
- Automated communication infrastructure among smart machines and agents (including humans, e.g. speech and vision), and information fusion for automation and enablement of multi-agent systems.
- Communication and networking to facilitate smart data-centric applications
Manuscripts must be submitted through the magazine’s submissions Website at http://mc.manuscriptcentral.com/commag-ieee. You will need to register and then proceed to the author center. On the manuscript details page, please select Data Science and Artificial Intelligence for Communications Series from the drop-down menu. Manuscripts should be tutorial in nature and should not be under review for any other conference or journal. They should be written in a style comprehensible and accessible to readers outside the specialty of the article. Mathematical equations should not be used. For detailed submission guidelines please refer to the magazine website for the list of guidelines that must be followed by all submissions to the IEEE Communications Magazine: https://www.comsoc.org/commag/paper-submission-guidelines
Authors are encouraged to contact the Series Editor before submitting an article in order to ensure that the article will be appropriate for the Series. Papers can be submitted anytime during the year. They will receive a review process, and, if accepted, they will be published in the first slot available for this Series.
- Irena Atov, Microsoft, USA (email@example.com)
- Kwang-Cheng Chen, University of South Florida, USA (firstname.lastname@example.org)
- Shui Yu, University of Technology Sydney, Australia (email@example.com)
Scope and Motivation:
The Cyber-Physical Systems (CPSs) have become very complex, more sophisticated, intelligent and autonomous. We cite as example of CPS smart grid in energy sector, smart factory and industry 4.0, intelligent transportation systems, healthcare and medical systems, and robotic systems. The CPSs offer very complex interaction between heterogeneous cyber and physical components; additionally to this complexity they are exposed to important disturbances due to unintentional and intentional events which lead the prediction of their behaviors (categorized as “Normal” or “Faulty”) a very difficult task. Meanwhile, cyber security for CPS is attracting the attention of research scientists in both industry and academia since the number of cyber-attacks have increased and their behaviors have become more sophisticated commonly known as zero-day threats.
Conventional cyber security mechanisms, such Intrusion Detection and Prevention Systems (IDS/IPS), and access control have not the capability to detect, prevent and block this category of cyber-attacks since the zero-day threats exhibit an unknown misbehavior that are not defined in signatures’ database of the security systems. Recently, a new era of cyber security mechanisms based on Artificial Intelligent (AI) are under development to protect the CPSs from these zero-day attacks. In the context of cyber security, the machine learning technologies are used to manage a huge amount of heterogeneous data that come from different sources of information with a goal of generating automatically different attacks patents and hence predict accurately the future attackers’ misbehavior. Meanwhile, game-theoretic approaches have been used in the context of cyber defense to solve the decision-making issues (i.e., the suspect device is an attacker or not) and attacks prediction. In decision-making issue, the cyber security game is used to study the interaction between the security agents (e.g., IDS and IPS) and their opponents (e.g. attackers) with a goal to determine the optimal decision making of security agent to classify the suspected opponent as attacker or not.
Preventing the occurrence of zero-day attacks requires the collaboration between different AI systems including machine learning and game theory, as well as security expert intervention. In fact, the involving of human intervention in the decision-making leads an improvement of attacks detection since the purpose of human-machine interaction is to reduce the number of false positives.
Another example to illustrate the migration of security solutions to use more intelligent principles and technologies, the Identity Management & Access control (IAM) which switch from a simple login/password checking to voice and facial recognition.
This Special Issue (SI) aims to bring together researchers from academic and industrial to share their visions of the AI application in cyber security context, present challenges and recent works and advances related to AI-based cyber security applied to CPSs. Potential topics include, but not limited to the following:
- Design and verification of AI-based security solutions,
- Impact of AI-based security solutions on CPS performances,
- Safety of AI-based security solutions.
- IDS/IPS based on machine learning,
- IDS/IPS based on deep and reinforcement learning,
- Cyber security game to protect the CPS,
- Authentication and Access Control,
- AI modeling for attack behavior,
- Attacks prediction based on machine learning and game theory,
- Human-machine interaction in the context of cyber security,
- Application of AI-based security in internet of things and transportation segments
- AI-based Solution for Physical layer security
- Manuscript Submission Deadline: May 1st 2019
- Initial Decision: August 1st, 2019
- Revised Manuscript Due: September 1st, 2019
- Decision Notification: November 1st, 2019
- Final Manuscript Due: December 1st, 2019
- Publication Date: May 2020
Manuscripts should conform to the standard format as indicated in the Information for Authors section of the Paper Submission Guidelines.
All manuscripts to be considered for publication must be submitted by the deadline through Manuscript Central. Select the “May 2020: Cyber Security based on Artificial Intelligence for Cyber-Physical Systems” topic from the drop-down menu of Topic/Series titles.
Guest Editors of the Special Issue: