Evolutionary Autonomous Networks





autonomous network, intent, principles, architecture, evolution, online experimentation


The communication networks of today can greatly benefit from autonomous operation and adaptation, not only due to the implicit cost savings, but also because autonomy will enable functionalities that are infeasible today. Across industry, academia and standardisation bodies there has been an increased interest in achieving the autonomous goal, but a path on how to attain this goal is still unclear.

In this paper we present our vision for the future of autonomous networking. We introduce the concepts and technological means to achieve autonomy and propose an architecture which emerges directly through the application of these concepts, highlighting opportunities and challenges for standardisation. We argue that only a holistic architecture based on hierarchies of hybrid learning, functional composition, and online experimental evaluation is expressive and capable enough to realise true autonomy within communication networks.


Download data is not yet available.

Author Biographies

Paul Harvey, Rakuten Mobile Innovation Studio, Japan

Paul Harvey received his doctorate in Computing Science from the University of Glasgow focusing on heterogeneous adaptive systems. He possesses extensive experience in academia, including multiple international collaborations and positions, and is currently bridging academic and industrial research. He is one of the original founders of the Autonomous Networks Research & Innovation Lab in Rakuten Mobile Japan and is passionate about pursing collaborative and open research.

Alexandru Tatar, Rakuten Mobile Innovation Studio, Japan

Alexandru Tatar is a researcher at Rakuten. He received an Engineering Degree from Polytechnic University of Bucharest and a Ph.D. from UPMC Sorbonne University, France. His work focuses on autonomous networks and on studying user behaviour in e-commerce.

Pierre Imai, Rakuten Mobile Innovation Studio, Japan

Pierre Imai is Head of the Research & Innovation Department at Rakuten Mobile and has been working for the Rakuten Institute of Technology as Principal Scientist since 2016. His research and work experience includes the fields of networking & telecommunications, self-optimizing & autonomous systems, internet-scale distributed systems, artificial intelligence & machine learning, and robotics. Before joining Rakuten, he was improving the content distribution and active network monitoring systems down to network protocol level at Google, working on future internet and telecommunications research at NEC Labs Europe, and participated in multiple EU and national research projects such as ANA and Onelab. He is especially interested in building systems that can learn and improve themselves, for example, a network stack that autonomously re-composes and re-configures itself to reach close-to-optimal performance based on the current state of the network and traffic – as he did for his PhD, on a research grant from the Swiss National Fund.

Leon Wong, Rakuten Mobile Innovation Studio, Japan

Leon Wong is the Industry Research Collaboration Lead for Rakuten Mobile Autonomous Networking Research & Innovation Lab. He has over 15 years experience in Telecommunications and IT, as a Subject Matter Expert in OSS, Solution Architect and Lead Engineer for international projects. Prior to joining Rakuten Mobile, he was responsible for building GPU High Performance Computing clusters for Rakuten Technology Division.

Laurent Bringuier, Rakuten Mobile Innovation Studio, Japan

Laurent Bringuier graduated from Paris-Sud University with a maîtrise degree in electrical and computer engineering. Laurent has over 20 years experience in the telecommunication industry working in a range of companies from small start-up operators to large international vendors. In that time, he gained experience as a network engineer, OSS IT architect, and OSS project manager on network and infrastructure resource management. He transitioned to R&D, working in Rakuten Institute of Technology as a research project manager on various applied machine learning projects from inception to conclusion. Now, Laurent is one of the original members of the Autonomous Networks Research & Innovation Dept in Rakuten Mobile Japan. Here he is leveraging his pragmatic telco knowledge and experience in applied research management to contribute to the creation of an autonomous network.


M. Harris, The End Of Absence: Reclaiming What We’ve Lost in a World of Constant Connection. Harper Perennial, 2014.

R. Stahlmann, A. Festag, A. Tomatis, I. Radusch, and F. Fischer, “Starting European field tests for Car-2-X communication: the DRIVE C2X framework,” in 18th ITS World Congr. and Exhibition, 2011, p. 12.

J. V Jacobs et al., “Employee acceptance of wearable technology in the workplace,” Appl. Ergon., vol. 78, pp. 148–156, 2019.

M. Jalasri and L. Lakshmanan, “A Survey: Integration of IoT and Fog Computing,” in 2018 2nd Int. Conf. Green Comput. and Internet of Things (ICGCIoT), 2018, pp. 235–239.

G. Davis, “2020: Life with 50 billion connected devices,” in 2018 IEEE Int. Conf. Consum. Electron. (ICCE), 2018, p. 1.

3GPP, “Public Warning System (PWS) requirements,” 2015.

M. Simsek, A. Aijaz, M. Dohler, J. Sachs, and G. Fettweis, “5G-enabled tactile internet,” IEEE J. Sel. Areas Commu., vol. 34, no. 3, pp. 460–473, 2016.

O. Babaoglu et al., “The Self-Star Vision,” Springer, Berlin, Heidelberg, 2005, pp. 1–20.

M. Smirnov, “Autonomic Communication—Research Agenda for a new Communication Paradigm. Company whitepaper,” Fraunhofer Inst. Open Commu. Syst., Berlin, Ger., 2004.

A. G. Ganek and T. A. Corbi, “The dawning of the autonomic computing era,” IBM Syst. J., vol. 42, no. 1, pp. 5–18, 2003.

P. Demestichas, V. Stavroulaki, D. Boscovic, A. Lee, and J. Strassner, “m@ANGEL: autonomic management platform for seamless cognitive connectivity to the mobile internet,” Commu. Mag. IEEE, vol. 44, no. 6, pp. 118–127, Jun. 2006.

N. Wiener, Cybernetics. Technology Press, 1949.

D. D. Clark, C. Partridge, J. C. Ramming, and J. T. Wroclawski, “A knowledge plane for the internet,” in Proceedings of the 2003 conference on Applications, technologies, architectures, and protocols for computer communications – SIGCOMM ’03, 2003, p. 3.

P. Imai and C. Tschudin, “Practical online network stack evolution,” in Proceedings – 2010 4th IEEE International Conference on Self-Adaptive and Self-Organizing Systems Workshop, SASOW 2010, 2010, pp. 34–41.

P. Imai, “Exploring Online Evolution of Network Stacks,” University of Basel, Switzerland, 2015.

P. Smolensky, “Connectionist AI, symbolic AI, and the brain,” Artif. Intell. Rev., vol. 1, no. 2, pp. 95–109, 1987.

V. Paxson and S. Floyd, “Why we don’t know how to simulate the Internet,” in Proc. the 29th Conf. Winter Simul., 1997, pp. 1037–1044.

3GPP, “Telecommunications Maangement: Study on Scenarios for Intent Driven Management Services for Mobile Networks,” 2020.

A. Clemm, L. Ciavaglia, L. Granville, and J. Tantsura, “Intent-Based Networking - Concepts and Overview,” 2019.

T. Szigeti, D. Zacks, M. Falkner, and S. Arena, Cisco Digital Network Architecture: Intent-based Networking for the Enterprise. Cisco Press, 2018.

A. Rafiq, M. Afaq, and W.-C. Song, “Intent-based networking with proactive load distribution in data center using IBN manager and Smart Path manager,” J. Ambient Intell. Humaniz. Comput., pp. 1–18, 2020.

M. Behringer et al., “RFC 7575: Autonomic Networking: Definitions and Design Goals,” 2015.

J. Mitola, “Cognitive Radio Architecture Evolution,” Proc. IEEE, vol. 97, no. 4, pp. 626–641, Apr. 2009.

S. Dobson, E. Bailey, S. Knox, R. Shannon, and A. Quigley, “A first approach to the closed-form specification and analysis of an autonomic control system,” in ICECCS ’07: Proc. 12th IEEE Int. Conf. Engineering Complex Computer Systems, 2007, pp. 229–237.

J. O. Kephart and D. M. Chess, “The vision of autonomic computing,” Computer (Long. Beach. Calif)., vol. 36, no. 1, pp. 41–50, 2003.

J. Boyd, G. T. Hammond, and A. U. (U.S.). Press, A Discourse on Winning and Losing. Air University Press, Curtis E. LeMay Center for Doctrine Development and Education, 2018.

E. Gat, R. P. Bonnasso, R. Murphy, and A. Press, “On Three-Layer Architectures,” in Artif. Intell. and Mobile Robots, 1997, pp. 195–210.

D. M. Ritchie, “A Stream Input-Output System,” in AT&T Bell Laboratories Technical J., 1984, pp. 311—324.

R. G. Guy et al., “Implementation of the Ficus replicated file system,” in USENIX Conf. Proc., 1990, vol. 74, pp. 63–71.

P. Harvey, A linguistic approach to concurrent, distributed, and adaptive programming across heterogeneous platforms. 2015.

N. C. Hutchinson and L. L. Peterson, “The X-Kernel: An Architecture for Implementing Network Protocols,” IEEE Trans. Softw. Eng., vol. 17, no. 1, pp. 64–76, 1991.

S. Patarin, S. Patarin, M. Makpangou, M. Makpangou, and S. Pat, “Pandora: A Flexible Network Monitoring Platform,” in Proc. USENIX 2000 Annu. Tech. Conf., 2000, p. 200.

F. Ogel, S. Patarin, I. Piumarta, and B. Folliot, “C/SPAN: a self-adapting web proxy cache,” in Autom. Comput. Workshop. 2003. Proc., 2003, pp. 178–185.

“Autonomic Network Architecture Project.”

“The FP7 4WARD Project.”

M. Harris et al., “Digital Transformation Initative Telecommunications Industry,” communicate, Jan-2019. [Online]. Available: https://ieeexplore.ieee.org/document/8399482/. [Accessed: 05-Apr-2019].

A. Brogi, J. Soldani, and P. Wang, “TOSCA in a Nutshell: Promises and Perspectives,” in Service-Oriented and Cloud Computing, 2014, pp. 171–186.

K. Chaudhuri, D. Doligez, L. Lamport, and S. Merz, “Verifying Safety Properties with the TLA+

Proof System,” in Proceedings of the 5th International Conference on Automated Reasoning, 2010, pp. 142–148.

D. Jackson, Software Abstractions: Logic, Language, and Analysis. The MIT Press, 2012.

IETF, “YANG - A Data Modeling Language for the Network Configuration Protocol (NETCONF),” 2010.

S. Russell and P. Norvig, “Artificial Intelligence: A Modern Approach, 2nd edition,” Prentice-Hall, 2003, pp. 1–5.

J. E. Laird, The Soar Cognitive Architecture. The MIT Press, 2012.

F. E. Ritter, F. Tehranchi, and J. D. Oury, “ACT-R: A cognitive architecture for modeling cognition,” WIREs Cogn. Sci., vol. 10, no. 3, p. e1488, 2019.

M. Minsky, “Logical versus Analogical or Symbolic versus Connectionist or Neat versus Scruffy,” AI Mag., vol. 12, no. 2, pp. 34–51, Apr. 1991.

M. Minsky and S. Papert, “Perceptrons: An essay in computational geometry,” MIT Press, 1969.

K. Fukushima, “Cognitron: A self-organizing multilayered neural network,” Biol. Cybern., vol. 20, no. 3–4, pp. 121–136, 1975.

J. Schmidhuber, “Deep Learning in Neural Networks: An Overview,” Neural Netw., vol. 61, pp. 85–117, 2015.

K. Shao, Z. Tang, Y. Zhu, N. Li, and D. Zhao, “A Survey of Deep Reinforcement Learning in Video Games,” arXiv Prepr. arXiv1912.10944, 2019.

C. Lemke, M. Budka, and B. Gabrys, “Metalearning: a survey of trends and technologies,” Artif. intell. Rev., vol. 44, no. 1, pp. 117–130, 2015.

J. Schmidhuber, “Ultimate cognition à la Gödel,” Cogn. Comput., vol. 1, no. 2, pp. 177–193, 2009.

T. Bäck, Evolutionary Algorithms in Theory and Practice - Evolution Strategies, Evolutionary Programming, Genetic Algorithms. Oxford University Press, 1996.

M. Dorigo and G. Di Caro, “Ant colony optimization: a new meta-heuristic,” in Proc. 1999 Congr. Evolutionary Comput. – CEC99 (Cat. No. 99TH8406), 1999, vol. 2, pp. 1470–1477.

S. M. Lavalle, “Rapidly-Exploring Random Trees: A New Tool for Path Planning,” 1998.

H. A. Simon, “The Sciences of the Artificial,” 3rd ed., Cambridge, MA: MIT Press, 1996, pp. 51–52.

D. Wood, J. S. Bruner, and G. Ross, “The Role of Tutoring in Problem Solving,” J. Child Psychol. Psychiatry, vol. 17, no. 2, pp. 89–100, 1976.

J. J. Ramos-Munoz, L. Yamamoto, and C. Tschudin, “Serial Experiments Online,” in ACM SIGCOMM Comput. Commu. Review, 2008, vol. 38, no. 2, pp. 31–42.

G. D. Troxel et al., “Adaptive Dynamic Radio Open-source Intelligent Team (ADROIT): Cognitively-controlled Collaboration among SDR Nodes,” in Netw. Techn. for Software Defined Radio Networks, 2006. SDR ’06.1st IEEE Workshop, 2006, pp. 8–17.

J. C. Bicket, “Bit-rate selection in wireless networks,” Massachusetts Institute of Technology, 2005.

E. Real, C. Liang, D. R. So, and Q. V Le, “Automl-zero: Evolving machine learning algorithms from scratch,” arXiv Prepr. arXiv2003.03384, 2020.

R. S. Sutton and A. G. Barto, “Reinforcement Learning: An Introduction, 2nd ed,” MIT Pressl, 2017, pp. 19–35.

3GPP, “36.902: Evolved Universal Terrestrial Radio Access Network (E-UTRAN); Self-configuring and self-optimizing network (SON) use cases and solutions,” 2008.

O. Faldik, R. Payne, J. Fitzgerald, and B. Buhnova, “Modelling system of systems interface contract behaviour,” arXiv Prepr. arXiv1703.07037, 2017.

B. Porter, M. Grieves, R. R. Filho, and D. Leslie, “REx: A Development Platform and Online Learning Approach for Runtime Emergent Software Systems,” 12th USENIX Symp. Oper. Syst. Des. Implement. (OSDI ’16), pp. 333–348, 2016.

M. Harris et al., “Digital Transformation Initative Telecommunications Industry,” communicate, Jan-2019.

R. Jurdak, C. V. Lopes, and P. Baldi, “A framework for modeling sensor networks,” in Proc. Building Softw. for Pervasive Comput. Workshop at OOPSLA, 2004, vol. 4, pp. 1–5.

V. Rozsa et al., “An Application Domain-Based Taxonomy for IoT Sensors.,” in ISPE te, 2016, pp. 249–258.

M. Eid, R. Liscano, and A. El Saddik, “A novel ontology for sensor networks data,” in Proceedings of 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006, 2006, pp. 75–79.

G. F. Riley and T. R. Henderson, “The ns-3 Network Simulator,” in Modeling and Tools for Netw. Sim., Berlin, Heidelberg: Springer Berlin Heidelberg, 2010, pp. 15–34.

Forsk, “Naos Overview.” 2020.






Special Issue on Zero-touch Network and Service Automation (ZSM)