Empowering IT Operations through Artificial Intelligence – A New Business Perspective
DOI:
https://doi.org/10.18502/kss.v4i1.6003Abstract
This paper aims to describe the concept of applying Artificial Intelligence to IT Operations (AIOps) and its main components, Big Data, Machine Learning and Trend Analysis. The concept was implemented by developing a multi-layered fusion of the technologies that powers the components in AIOps platforms present on the IT market. The core of an AIOps platform is represented by the Big Data organization structure and by a massive parallel data processing platform like Apache Hadoop. The ML component of the platform is able to infer the future behaviour and the regular operations that are performed from the large volume of collected data, in order to develop the ability to automate the activities. AIOps platforms find their place especially in very complex IT infrastructures, ones that require constant monitoring and quick decisions in case of failures. The case study is based on the Moogsoft AIOps platform, and its features are presented in detail, using the Cloud trial version, clearly showing the potential of such an advanced tool for infrastructure monitoring and reporting. The experiment was focused on the way Moogsoft is monitoring computing resources, is handling events and records alerts for the defined timespan, alerts grouped by category (like web services, social media, networking). The platform is also able to display at any given moment the unresolved situations and their type of origin, and includes automated remediation tools. The study presents the features of this software category, consisting in benefits for the business environment and their integration into the Internet-of-Things model.
Keywords: Big Data, Machine Learning, AIOps, business performance.
References
Gartner official website (2017). Market Guide for AIOps Platforms. Published: 03 August 2017 ID: G00322184, https://www.gartner.com/en/documents/3772124/market-guide-for-aiops-platforms
Lawrence, C. (2018). How the Convergence of AI and IoT is Transforming Customer Support. https:// www.momenta.partners/edge/how-the-convergence-of-ai-and-iot-is-transforming-customer-support
Paskin, S. (2018). What is AIOps? Artificial Intelligence for IT Operations Explained, https://www.bmc. com/blogs/what-is-aiops/.
Banica, L. and Radulescu, M. (2015). Using Big Data in the Academic Environment. In Procedia Economics and Finance, Volume 33/2015, pp. 277-286
Banica, L. and Hagiu, A. (2015). Big Data in Business Environment. Scientific Bulletin – Economic Sciences, Volume 14/ Issue 1, pp.79-86
Rosenbush, S. and Totty, M. (2013). How Big Data Is Changing the Whole Equation for Business, http://www.wsj.com/articles/SB10001424127887324178904578340071261396666
Martinez, I. (2017). Finding Hidden Customer Behavior Patterns Using Big Data Analytics, https://dzone. com/articles/find-hidden-customer-behavior-patterns-using-big-d
Tiwari, K. (2017). When Machine Learning meets Big Data, https://towardsdatascience.com/when- machine-learning-meets-big-data-4923091ba140
Zhang, Q., Yang, L. T., Chen, Z., et al. (2018). A survey on deep learning for big data. Information Fusion, Volume 42, 2018, pp. 146-157
Null, C. (2018). Essential guide to AIOps: Top tools and implementation tips, https://techbeacon.com/essential-guide-aiops-top-tools-implementation-tips
Lo, F. (2014). Big Data Technology, available at https://datajobs.com/what-is-hadoop-and-nosql
Banica, L., Paun, V., Stefan, C. (2014). Big Data leverages Cloud Computing opportunities. International Journal of Computers & Technology, Volume 13, No.12, http://cirworld.org/journals/index.php/ijct/ article/view/3036
Klass, L. (2018). Machine Learning - Definition and application examples, https://www.spotlightmetal. com/machine-learning--definition-and-application-examples-a-746226/?cmp=go-aw-art-trf- SLM_DSA-20180820&gclid=EAIaIQobChMIhrWU7_iU3wIVy4eyCh2PfQVHEAAYAyAAEgLvAPD_BwE
Ayodele, T., O. (2010). Types of Machine Learning Algorithms, DOI: 10.5772/9385, https://www. researchgate.net/publication/221907660_Types_of_Machine_Learning_Algorithms
Sahu, Y. (2018). Machine Learning Applications for Businesses, https://www.mangoblogger.com/blog/ machine-learning-applications-for-businesses/
Rouse, M. (2018). AIOps (artificial intelligence for IT operations), https://searchitoperations.techtarget. com/definition/AIOps
Harper_a, R. (2017). Understanding the Machine Learning in AIOps, Part 1, https://www.moogsoft.com/ blog/aiops/understanding-machine-learning-aiops/
Harper_b, R. (2017). Understanding the Machine Learning in AIOps – Part 3: Fishing for Information in a Sea of Data, https://www.moogsoft.com/blog/aiops/understanding-machine-learning-aiops-part-3
Casper, D. (2017). Moogsoft AIOps On-Prem Trial, https://www.moogsoft.com/blog/moogsoft-aiops-on- prem-trial/
Ismail, B.I., Mostajeran, E., Ab Karim, M., B., et al. (2015). Evaluation of Docker as Edge Computing Platform, DOI: 10.1109/ICOS.2015.7377291, https://www.researchgate.net/publication/281445982
Docker official wesite (2018). https://www.docker.com/what-docker
Moogsoft official website (2018). Moogsoft AIOps Version 7.0.1, https://www.moogsoft.com/blog/ moogsoft-aiops-on-prem-trial/
Riley, C. (2018). Tips for Putting AIOps Into Practice: What You Can Do Right Now, https://dzone.com/ articles/tips-for-putting-aiops-into-practice-what-you-can