Skip to content

Invention of Packet Switching

1961 to 1964.Networking.Invention.Date precision, year.Evidence grade, primary.4 primary sources

Drivers:

Performance improvementScalability demandSecurity incident

Military concerns about nuclear survivability drove Baran's work. Academic interest in resource sharing drove Kleinrock's research. Both recognised that circuit switching was fundamentally unsuited to computer communication patterns.

Before packet switching, making a phone call required a dedicated wire connecting you to the other person. Packet switching is like sending a letter: your message is put in an envelope with an address, and it finds its own way through the postal system. This means many messages can share the same wires, and if one route is blocked, messages can take another path.

Invention of Packet Switching event plate

Structured atlas record showing date, domain, evidence grade, source count, and predecessor and successor links.

Event plate: Invention of Packet Switching Convergence-divergence layout. The central hero card carries the event year, type, title, evidence grade, domain and era band. 0 predecessor cards on the left feed in with red arrows labelled "absorbs". 0 successor cards on the right derive with red arrows labelled "spawns". Key terms below the hero pin the vocabulary the event introduced. EVENT PLATE Source: https://www.lk.cs.ucla.edu/data/files/Kleinrock/Information%20Flow%20in%20Large%20Communication%20Nets.pdf 1961 - INVENTION Invention of PacketSwitching primary evidence Domain: AI and machine learning Era band: E6 AI-scale systems KEY TERMS - VOCABULARY THE EVENT INTRODUCED packet switching circuit switching distributed network store-and-forward Convergence-divergence: predecessors absorbed, successors spawned Hero card carries year, evidence and domain. 0 predecessors flow in from the left; 0 successors flow out to the right. Key termsbelow pin the vocabulary the event introduced.

Forecasts and counterfactuals stay labelled as opinion in the event data. Source: Computer History Museum.

Before

Existing telecommunications relied on circuit switching, where a dedicated physical path was established for each call. This approach was inefficient for computer data, which arrives in bursts, and vulnerable to single points of failure. A nuclear attack could disable entire communication networks by destroying key switching centres.

What changed

Packet switching divided data into small, independently-routed packets that could take different paths through a network and be reassembled at the destination. This made networks more efficient for bursty computer traffic and more resilient to failures.

How it happened

Leonard Kleinrock at MIT developed the mathematical theory of packet switching in his 1961 PhD work. Independently, Paul Baran at RAND Corporation designed distributed packet-switched networks for military survivability in 1964. In the UK, Donald Davies at NPL coined the term "packet" and designed similar systems in 1965-66. These parallel developments converged to form the foundation of modern networking.

Outcomes

  • Established theoretical and practical foundation for computer networks
  • Demonstrated that distributed networks could survive partial failures
  • Enabled efficient sharing of network resources among multiple users
  • Coined terminology still used today (packet, packet switching)

Limitations

  • Early packet networks had limited bandwidth
  • No standardised protocols existed initially
  • Security was not a primary consideration
  • Required significant computing power at each node

Lessons learnt

  • Distributed architectures provide resilience
  • Independent parallel research can converge on similar solutions
  • Mathematical foundations are essential for engineering scalable systems

Stakeholders and artefacts

Organisations

  • MITacademiaKleinrock's PhD research
  • RAND CorporationacademiaBaran's distributed communications research
  • National Physical LaboratoryacademiaDavies' packet switching development

Individuals

  • Leonard KleinrockResearcher, MITMathematical theory of packet switching
  • Paul BaranResearcher, RAND CorporationDistributed network architecture for survivability
  • Donald DaviesResearcher, NPLCoined 'packet', designed NPL network

Artefacts

  • PacketspecificationSelf-contained unit of data with addressing information
  • Store-and-forwardmethodologyTechnique where nodes receive complete packets before forwarding

Key terms

packet switchingcircuit switchingdistributed networkstore-and-forward

Causality

Made possible: First ARPANET Message Transmitted.

On this course

Read in the path How the Internet Works.

Sources

1Leonard Kleinrock. "Information Flow in Large Communication Nets". MIT, 1961-05-31.peer reviewedwww.lk.cs.ucla.edu/data/files/Kleinrock/Information%20Flow%20in%20Large%20Communication%20Nets.pdf
2Paul Baran. "On Distributed Communications: I. Introduction to Distributed Communications Networks". RAND Corporation, 1964-08.authoritativewww.rand.org/pubs/research_memoranda/RM3420.html
3Donald Davies. "A Digital Communication Network for Computers Giving Rapid Response at Remote Terminals". National Physical Laboratory, 1966.authoritative
4Barry M. Leiner, Vinton G. Cerf, David D. Clark, Robert E. Kahn, Leonard Kleinrock, Daniel C. Lynch, Jon Postel, Larry G. Roberts, Stephen Wolff. "A Brief History of the Internet". Internet Society, 1997.authoritativewww.internetsociety.org/internet/history-internet/brief-history-internet/