The article discusses the rationale for the choice of methods and algorithms for mutual information coordination (consensus achievement) in a distributed multi-agent system used to solve the problem of information monitoring in complex technological objects. The architecture of this multi-agent system is decentralized and based on the set of intelligent monitoring agents that receive and process data from the object under control which is a part of the system within which information monitoring is performed. The purpose of the monitoring is to predict the instances of non-stationary load occurrence at the objects being monitored. A feature of the system is the presence of non-stationary load propagation time lag over the subsets of monitoring objects. The problem of predicting the instances of non-stationary load occurrence and propagation as part of an intelligent monitoring agent is solved by means of a neural network model trained using the precedents occurring at the object. To account for the propagation of non-stationary load time lag, it is proposed to perform additional training of the neural network model not only on its own data set, but also on the data sets of the nearest neighbors connected by the propagation of non-stationary load time lag which requires solving the problem of their mutual information coordination. The article discusses approaches to the selection and modification of the algorithms for the multi-agent system architecture – multicast messaging concerning the instances of non-stationary load occurrence and routing of these messages in a decentralized structure of an information monitoring system. The data structures necessary for these algorithms and protocols for the interaction of intelligent monitoring agents, which provide an increase in the speed of message delivery, are considered.
1. Sharif Ullah Al-Mamun G.M., Kabir F., Nazeen F., Sobah J. A review on data center monitoring system using smart sensor network. International Research Journal of Science, Technology, Education, and Management. 2022;2(1). Available from: https://zenodo.org/record/6496816#.ZGI0zyPP3iA (accessed on 11.03.2023). DOI: 10.5281/zenodo.6496816.
2. Wilson E. Network monitoring and analysis. M.: LORI; 2002. 350 p. (In Russ.).
3. Copos B., Levitt K., Bishop M., Rowe J. Is anybody home? inferring activity from smart home network traffic. IEEE Security and Privacy Workshops (SPW). 2016;3. Available from: https://ieeexplore.ieee.org/abstract/document/7527776 (accessed on 11.03.2023). DOI: 10.1109/SPW.2016.48.
4. Yuleisi G.P., Kholod I.I. Interaction in multi-agent systems of data mining. Izvestiya SPbSETU "LETI". 2020;3:18–23. (In Russ.).
5. Hochreiter S., Schmidhuber J. Long short-term memory. Neural computation. 1997;9(8): 1735–1780. Available from: https://pubmed.ncbi.nlm.nih.gov/9377276 (accessed on 11.03.2023). DOI: 10.1162/neco.1997.9.8.1735.
6. Zhuang S.Q., Zhao B.Y., Joseph A.D., Katz R.H., Bayeux J.K. An architecture for scalable and fault-tolerant wide-area data dissemination. In Proc. of the Eleventh International Workshop on Network and Operating System Support for Digital Audio and Video (NOSSDAV 2001); 2001. Available from: https://www.sci-hub.ru/10.1145/378344.378347 (accessed on 17.03.2023). DOI: 10.1145/378344.378347.
7. Rowstron A., Druschel P. Pastry: Scalable, distributed object location and routing for large-scale peer-to-peer systems. In Proc. IFIP/ACM Middleware 2001, Heidelberg, Germany. 2001. Available from: https://link.springer.com/chapter/10.1007/3-540-45518-3_18 (accessed on 17.03.2023). DOI: 10.1007/3-540-45518-3_18.
8. Stoica I., Morris R., Karger D., Kaashoek M.F., Balakrishnan H. Chord: A scalable peer-to-peer lookup service for Internet applications. In Proc. ACM SIGCOMM’01, San Diego, CA. 2001. Available from: https://ieeexplore.ieee.org/document/1180543 (accessed on 20.03.2023). DOI: 10.1109/TNET.2002.808407.
9. Janotti J., Gifford D.K., Johnson K.L., Kaashoek M.F., O’Toole J.W. Overcast: Reliable Multicasting with an Overlay Network. In Proc. of the Fourth Symposium on Operating System Design and Implementation (OSDI). 2000;197–212. Available from: https://rd.springer.com/chapter/10.1007/11582267_5 (accessed on 20.03.2023). DOI: 10.1007/11582267_5.
10. Leach P., Mealling M., Salz R. A Universally Unique IDentifier (UUID) URN Namespace. The Internet Society (RFC). 2005. Available from: http://www.ietf.org/rfc/rfc4122.txt (accessed on 20.03.2023). DOI: 10.17487/RFC4122.
Rykshin Maxim Sergeevich
Moscow, Russian Federation
