Large-scale systems of all types, such as data centers, cloud computing environments, edge clouds, IoT and embedded environments, are becoming more and more complex. Managing such systems only with human resources puts an enormous burden on the operators and scales poorly from an economic perspective. To mitigate this issue IT operators increasingly rely on tools from artificial intelligence for assistance.

Artificial Intelligence for IT Operations (AIOps) is an emerging field arising in the intersection between the research areas of machine learning, big data and streaming analytics, and the management of IT operations. The main aim is to analyze system information of different kinds (metrics, logs, customer input, etc) to support administrators by optimizing various objectives like prevention of SLA violation, early anomaly detection and auto-remediation, energy-efficient system operation, providing optimal QoE for customers, predictive maintenance and many more. In this field, a constantly growing interest can be observed, and thus, practical tools are developed from both the academy and industry sectors.

As a result, AIOps progress towards a future standard for IT operation management. However, the combination of previously separate research fields brings many challenges. Novel modeling techniques are needed that help to understand the dynamics of different systems, laying out the basis for assessing time horizons and uncertainty for imminent SLA violations, the early detection of emerging problems, autonomous remediation, decision making, and support, and various optimization objectives. Furthermore, a good understanding and interpretability of these aiding models are especially important for building trust between the employed tools and the domain experts. This will result in faster adoption of AIOps and further increase the interest in this research field.

The main aim of this workshop is to bring together researchers from both academia and industry to present their experiences, results, and work in progress in this field. We want to strengthen the community and unite it towards the goal of joining the efforts for solving the main challenges the field is currently facing. A consensus and adoption of the principles of openness and reproducibility will boost the research in this emerging area significantly.

More information on the workshop website: https://aiopsworkshop.github.io/

Submission Guidelines

Authors are invited to submit full papers (with a maximum length of 12 pages, including references and appendices.) using (Springer LNCS format). Papers must be written in English and are to be submitted in PDF format online via the Easychair submission interface:

https://easychair.org/my/conference?conf=aiops2020#.

If any problem arises when submitting your paper, please contact aiops2020@cit.tu-berlin.de.

Each paper will be reviewed by at least three members of the international program committee for ensuring high quality. Paper acceptance will be based on originality, significance, technical soundness, and clarity of presentation. All accepted papers will be included in the workshop proceedings published as part of the Lecture Notes in Computer Science (LNCS) series of Springer. At least one author of an accepted paper must register and participate in the workshop. Registration is subject to the terms, conditions, and procedures of the main ICSOC conference to be found on the conference website: http://www.icsoc.org/.

List of Topics

•  Early anomaly, fault and failure (AFF) detection and analysis

• Self-healing, self-correction and auto-remediation

• Self-adaptive time-series based models for prognostics and forecasting

• AFF identification, localization, and isolation

• Root cause analysis

• Adaptive fault tolerance policies

• Forecasting of hardware and process quality

• Decision support

• Planning under uncertainty

• Predictive and prescriptive maintenance

• Maintenance scheduling and on-demand maintenance planning

• Fault-tolerant system control

• Reliability and quality assurance

• Autonomic process optimization

• Energy-efficient cloud operation

• Autonomous service provisioning

• Explainable AI in general

• Visual analytics and interactive machine learning

• Active and life-long learning

• Information and communication models for AIOps systems 

• Platforms: Time-series DBs, Streaming, Data Lakes

• AI platforms for AIOps

• Design of experiment (DoE) for different use-cases, testbeds, evaluation scenarios 

Publication

Opportunity to publish improved versions of accepted papers as part of its dedicated post-workshop proceedings in Springer’s LNCS series.

Venue

The workshop will be collocated with ICSOC 2020 conference in Dubai 14-17 of December 2020.

More information: http://www.icsoc.org/

Contact

All questions about submissions should be emailed to aiops2020@cit.tu-berlin.de

Sponsors

Huawei Technologies Co., Ltd.