research-article

Network artificial intelligence, fast and slow

Authors:

Liang ZhangAuthors Info & Claims

NativeNi '22: Proceedings of the 1st International Workshop on Native Network Intelligence

Pages 14 - 20

https://doi.org/10.1145/3565009.3569521

Published: 06 December 2022 Publication History

Abstract

As networks have historically been built around connectivity, architectural features concerning quality of service, mobility, security and privacy have been added as afterthoughts - with consequent well known architectural headaches for their later integration. Despite Artificial Intelligence (AI) is more a means to an end, that an architectural feature itself, this is not completely different from what concerns its integration: in particular, while Cloud and Edge computing paradigms made it possible to use AI techniques to relieve part of network operation, however AI is currently little more than an additional tool. This paper describes a vision of future networks, where AI becomes a first class commodity: its founding principle lays around the concept of "fast and slow" type of AI reasoning, each of which offers different types of AI capabilities to process network data. We next outline how these building blocks naturally maps to different network segments, and discuss emerging AI-to-AI communication patterns as we move to more intelligent networks.

References

[1]

K. S. Narendra et al. "Application of learning automata to telephone traffic routing and control". In: IEEE Trans. SMC 7.11 (1977).

[2]

R. Boutaba et al. "A comprehensive survey on machine learning for networking: evolution, applications and research opportunities". In: JISA 9.1 (2018).

[3]

H. Lutfiyya et al., eds. IEEE TSNM SI on Embracing AI for Network and Service Management. Vol. 18. 2021.

[4]

D. Rossi and L. Zhang. "Landing AI on Networks: An equipment vendor viewpoint on Autonomous Driving Networks". In: IEEE TNSM 19.3 (2022).

[5]

https://ec.europa.eu/info/funding-tenders/opportunities/portal/screen/opportunities/topic-details/horizon-ju-sns-2022-stream-b-01-01.

[6]

P. Chemouil et al., eds. IEEE JSAC SI on Advances in AI and ML for Networking. Vol. 38. 2020.

[7]

L. Frost et al., eds. Report of TWG AI: Landscape of AI Standards. 2021.

[8]

https://www.etsi.org/technologies/experiential-networked-intelligence.

[9]

https://datatracker.ietf.org/rg/coinrg/about/.

[10]

https://medium.com/@larsbuttler/power-to-the-people-a-i-native-ad634a65871c#.eb23bp3cg.2016.

[11]

https://www.ericsson.com/en/reports-and-papers/ericsson-technology-review/articles/bss-and-artificial-intelligence-time-to-go-native. 2019.

[12]

https://www.deepsig.ai/ai-native-communications. 2022.

[13]

G. Wu. "6G Technologies for Mobile Connected Intelligence". In: ITU Kaleidoscope (ITU-K). 2021.

[14]

J. Hoydis et al. "Toward a 6G AI-native air interface". In: IEEE Communications Magazine 59.5 (2021), pp. 76--81.

[15]

P. Carbone et al. "NeuroRAN: rethinking virtualization for AI-native radio access networks in 6G". In: CoRR abs/2104.08111 (2021).

[16]

W. Wu et al. "AI-native network slicing for 6G networks". In: IEEE Wireless Communications 29.1 (2022), pp. 96--103.

[17]

Y. Xiao et al. "Toward self-learning edge intelligence in 6G". In: IEEE Communications Magazine 58.12 (2020), pp. 34--40.

[18]

X. Li et al. "Advancing Software-Defined Service-Centric Networking Toward In-Network Intelligence". In: IEEE Network 35.5 (2021).

Digital Library

[19]

https://h2020daemon.eu/. 2022.

[20]

G. Li et al. "XuanYuan: An AI-Native Database." In: IEEE Data Eng. Bull. 42.2 (2019), pp. 70--81.

[21]

E. Gelenbe et al. "Self-aware networks and QoS". In: Proceedings of the IEEE 92.9 (2004).

[22]

E. Liang et al. "Neural packet classification". In: ACM SIGCOMM. 2019.

Digital Library

[23]

K. Vaidya et al. "Partitioned Learned Bloom Filters". In: ICLR. 2021.

[24]

D. Harel et al. "Autonomics: In search of a foundation for next-generation autonomous systems". In: PNAS 117.30 (2020).

[25]

K. Winstein and H. Balakrishnan. "Tcp ex machina: Computer-generated congestion control". In: ACM SIGCOMM. 2013.

Digital Library

[26]

X. Nie et al. "Dynamic TCP initial windows and congestion control schemes through reinforcement learning". In: IEEE JSAC 37.6 (2019).

[27]

S. Emara et al. "Eagle: Refining congestion control by learning from the experts". In: IEEE INFOCOM. 2020.

[28]

J. Widmer et al. "A survey on TCP-friendly congestion control". In: IEEE network 15.3 (2001).

Digital Library

[29]

R. Al-Saadi et al. "A survey of delay-based and hybrid TCP congestion control algorithms". In: IEEE Comm. S&T 21.4 (2019).

[30]

A. Lazaridou et al. "Multi-Agent Cooperation and the Emergence of (Natural) Language". In: CoRR abs/1612.07182 (2016).

[31]

I. Mordatch and P. Abbeel. "Emergence of Grounded Compositional Language in Multi-Agent Populations". In: AAAI (2018).

[32]

D. Sculley et al. "Hidden Technical Debt in Machine Learning Systems". In: NeurIPS. 2015.

[33]

M. Ferriol-Galmés et al. "Routenet-erlang: A graph neural network for network performance evaluation". In: IEEE INFOCOM. 2022.

[34]

S. Lapuschkin et al. "Unmasking Clever Hans predictors and assessing what machines really learn". In: Nature 10.1 (2019).

[35]

https://www.europarl.europa.eu/thinktank/en/document/EPRS_BRI(2021)698792.

[36]

P. J. Phillips et al. "Four principles of explainable artificial intelligence". In: NIST Draft (2020).

[37]

Z. Meng et al. "Interpreting Deep Learning-Based Networking Systems". In: ACM SIGCOMM. 2020.

Digital Library

[38]

R. R. Hoffman et al. "Trust in automation". In: IEEE Intelligent Systems 28.1 (2013).

Digital Library

[39]

Z. Ben Houidi and D. Rossi. "Neural language models for network configuration: Opportunities and reality check". In: Computer Communications 193 (2022).

[40]

P. Molino and C. Ré. "Declarative machine learning systems". In: Commun. of the ACM 65.1 (2021), pp. 42--49.

Digital Library

[41]

Z.-H. Zhou. "Learnware: on the future of machine learning." In: Frontiers Comput. Sci. 10.4 (2016), pp. 589--590.

Digital Library

[42]

https://www.acumos.org/.

[43]

https://onnx.ai/.

[44]

E. Jonas et al. "Cloud Programming Simplified: A Berkeley View on Serverless Computing". In: CoRR abs/1902.03383 (2019).

[45]

S. Kotni et al. "Faastlane: Accelerating Function-as-a-Service Workflows". In: USENIX ATC. 2021.

[46]

N. Yaseen et al. "Towards a Cost vs. Quality Sweet Spot for Monitoring Networks". In: ACM HotNets. 2021.

Digital Library

[47]

D. D. Clark et al. "A knowledge plane for the internet". In: ACM SIGCOMM. 2003.

Digital Library

[48]

H. V. Madhyastha et al. "iPlane: An information plane for distributed services". In: USENIX OSDI. 2006.

[49]

A. Shieh et al. "NetQuery: A knowledge plane for reasoning about network properties". In: ACM SIGCOMM. 2011.

Digital Library

[50]

A. Mestres et al. "Knowledge-defined networking". In: ACM SIGCOMM Computer Communication Review 47.3 (2017), pp. 2--10.

Digital Library

[51]

A. Tversky and D. Kahneman. "Judgment under Uncertainty: Heuristics and Biases". In: Science 185.4157 (1974).

[52]

D. Kahneman. Thinking, fast and slow. 2011.

[53]

B. McMahan et al. "Communication-efficient learning of deep networks from decentralized data". In: PMLR AI and statistics. 2017.

[54]

V. Cerf and R. Kahn. "A protocol for packet network intercommunication". In: IEEE Trans. Comm. 22.5 (1974).

[55]

D. L. Tennenhouse and D. J. Wetherall. "Towards an active network architecture". In: ACM SIGCOMM (1996).

Digital Library

[56]

https://github.com/apple/coremltools.

[57]

O. Marfoq et al. "Throughput-optimal topology design for cross-silo federated learning". In: NIPS. 2020.

[58]

Z. B. Houidi et al. "Towards a systematic multi-modal representation learning for network data". In: ACM HotNets. 2022.

Digital Library

[59]

V. Sreekanti et al. "Cloudburst: Stateful Functions-as-a-Service". In: VLDB (2020).

Digital Library

[60]

R. David et al. "TensorFlow Lite Micro: Embedded Machine Learning for TinyML Systems". In: MLSys (2021).

[61]

C. Filsfils et al. "SRv6 network programming". In: IETF RFC 8986 (2021).

[62]

J. Xing et al. "A Vision for Runtime Programmable Networks". In: ACM HotNets. 2021.

Digital Library

Cited By

Soto PCamelo MGarcia-Aviles GMunicio EGramaglia MKosmatos ESlamnik-Kriještorac NDe Vleeschauwer DBazco-Nogueras AFuentes LBallesteros JLutu ACominardi LPaez IAlcalá-Marín SChatzieleftheriou LGarcia-Saavedra AFiore M(2024)Designing the Network Intelligence Stratum for 6G networksComputer Networks10.1016/j.comnet.2024.110780(110780)Online publication date: Sep-2024
https://doi.org/10.1016/j.comnet.2024.110780

Index Terms

Network artificial intelligence, fast and slow
1. Computing methodologies
  1. Machine learning
2. Networks
  1. Network performance evaluation
    1. Network measurement

Recommendations

Hybrid Bionic Cognitive Architecture for Artificial General Intelligence Agents
Abstract
The article describes the author’s proposal on cognitive architecture for the development of a general-level artificial intelligent agent («strong» artificial intelligence). New principles for the development of such an architecture are proposed — ...
Artificial intelligence
Abstract
Artificial intelligence (AI) is the Science and Engineering domain concerned with the theory and practice of developing systems that exhibit the characteristics we associate with intelligence in human behavior. Starting with a brief history of ...
DARPA's explainable artificial intelligence (XAI) program
IUI '19: Proceedings of the 24th International Conference on Intelligent User Interfaces

The DARPA's Explainable Artificial Intelligence (XAI) program endeavors to create AI systems whose learned models and decisions can be understood and appropriately trusted by end users. This talk will summarize the XAI program and present highlights ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

NativeNi '22: Proceedings of the 1st International Workshop on Native Network Intelligence

December 2022

38 pages

ISBN:9781450398879

DOI:10.1145/3565009

Conference Chairs:
Alessandro Finamore
Huawei Technologies
,
Marco Fiore
IMDEA Networks Institute
,
Carlee Joe-Wong
Carnegie Mellon University

Copyright © 2022 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGCOMM: ACM Special Interest Group on Data Communication

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 06 December 2022

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

CoNEXT '22

Sponsor:

SIGCOMM

CoNEXT '22: The 18th International Conference on emerging Networking EXperiments and Technologies

December 9, 2022

Rome, Italy

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
198
Total Downloads

Downloads (Last 12 months)36
Downloads (Last 6 weeks)4

Reflects downloads up to 05 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Soto PCamelo MGarcia-Aviles GMunicio EGramaglia MKosmatos ESlamnik-Kriještorac NDe Vleeschauwer DBazco-Nogueras AFuentes LBallesteros JLutu ACominardi LPaez IAlcalá-Marín SChatzieleftheriou LGarcia-Saavedra AFiore M(2024)Designing the Network Intelligence Stratum for 6G networksComputer Networks10.1016/j.comnet.2024.110780(110780)Online publication date: Sep-2024
https://doi.org/10.1016/j.comnet.2024.110780

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents