NPL network
Jump to navigationJump to search
NPL network schematic
The NPL Network or NPL Data Communications Network was a local area computer network operated by a team from the National Physical Laboratory in London that pioneered the concept of packet switching.
Based on designs first proposed by Donald Davies in 1965, elements of the first version of the network, the Mark I, became operational during 1969 then fully operational in 1970, and the Mark II version operated from 1973 until 1986. The NPL network and the ARPANET in the United States were the first two computer networks that implemented packet switching and the NPL network was the first to use high-speed links.[1][2]
Origins[edit]
In 1965, Donald Davies, who was later appointed to head of the NPL Division of Computer Science, proposed a national data network based on packet switching in Proposal for the Development of a National Communications Service for On-line Data Processing. After the proposal was not taken up nationally, during 1966 he headed a team which produced a design for a local network to serve the needs of NPL and prove the feasibility of packet switching.[3] The design was the first to describe the concept of an “Interface computer”, today known as a router.[4]
The next year, a written version of the proposal entitled NPL Data Network was presented by Roger Scantlebury at the Symposium on Operating Systems Principles. It described how computers (nodes) used to transmit signals (packets) would be connected by electrical links to re-transmit the signals between and to the nodes, and interface computers would be used to link node networks to so-called time-sharing computers and other users. The interface computers would transmit multiplex signals between networks, and nodes would switch transmissions while connected to electrical circuitry functioning at a rate of processing amounting to mega-bits.[2][5][6][7][8][9] In Scantlebury’s report following the conference, he noted “It would appear that the ideas in the NPL paper at the moment are more advanced than any proposed in the USA”.[10][11][12][13][14]
Larry Roberts incorporated these concepts into the design for the ARPANET.[15] The NPL network proposed a line speed of 768 kbit/s.[16] Influenced by this, the planned line speed for ARPANET was upgraded from 2.4 kbit/s to 50 kbit/s and a similar packet format adopted.[17][18]
Packet switching[edit]
NPL network packet
The first theoretical foundation of packet switching was the work of Paul Baran, in which data was transmitted in small chunks and routed independently by a method similar to store-and-forward techniques between intermediate networking nodes.[19] Davies independently arrived at the same model in 1965 and named it packet switching.[20] He chose the term “packet” after consulting with an NPL linguist because it was capable of being translated into languages other than English without compromise.[21] Davies gave the first public presentation of packet switching on 5 August 1968.[22] Concurrently with the ARPANET, NPL under Davies was one of the first two organisations that implemented a packet switching network.[2][10][23][24]
Network development[edit]
The NPL team used their packet switching concept to produce an experimental network using a Honeywell 516 node. Coincidentally, this was the same computer chosen by the ARPANET to serve as Interface Message Processors.
Construction began in 1968.[25] Elements of the first version of the network, Mark I NPL Network, became operational during 1969 then fully operational in January 1970, later using high-speed T1 links (1.544 Mbit/s line rate), the first computer network to do so.[26][27][28] The Mark II version operated from 1973.[2][5][29] The NPL team also carried out simulation work on the performance of packet networks, including datagram networks.[30][31] The local area NPL network and the wide area ARPANET in the United States were the first two computer networks that implemented packet switching.[1][32][33]
The NPL network was later interconnected with other networks, including the ARPANET via Peter Kirstein’s research group at University College London in 1973, and CYCLADES via the European Informatics Network (EIN) in 1976.[2]
In 1976, 12 computers and 75 terminal devices were attached,[34] and more were added. The network remained in operation until 1986, influencing other research in the UK and Europe.[35][36]
Alongside Donald Davies, the NPL team included Derek Barber, Roger Scantlebury, Peter Wilkinson, Keith Bartlett, and Brian Aldous.[37]
Protocol development[edit]
NPL network model
One of the first uses of the term ‘protocol‘ in a data-commutation context occurs in a memorandum entitled A Protocol for Use in the NPL Data Communications Network written by Roger Scantlebury and Keith Bartlett in April 1967.[38][26] The Mark II version which operated from 1973 used a layered protocol architecture.[26]
The NPL network was a tesbed for internetworking research throughout the 1970s. Davies, Scantlebury and Barber were members of the International Networking Working Group (INWG) which proposed a protocol for internetworking.[39][40][41] Derek Barber was appointed director of the European COST 11 project which became the European Informatics Network (EIN) while Scantlebury led the UK technical contribution.[42][43][44] The EIN protocol helped to launch the proposed INWG standard.[45][46] Bob Kahn and Vint Cerf acknowledged Davies and Scantlebury in their 1974 paper “A Protocol for Packet Network Intercommunication“.[47]
NPL research investigated the “basic dilemma” involved in internetworking; that is, a common host protocol would require restructuring existing networks if they were not designed to use the same protocol. NPL connected with the European Informatics Network by translating between two different host protocols while the NPL connection to the Post Office Experimental Packet Switched Service used a common host protocol in both networks. This work confirmed establishing a common host protocol would be more reliable and efficient.[48]
Davies and Barber published books on “communication networks for computers” in 1973 and “computer networks and their protocols” in 1979.[49][50] They spoke at the Data Communications Symposium in 1975 about the “battle for access standards” between datagrams and virtual circuits, with Barber saying the “lack of standard access interfaces for emerging public packet-switched communication networks is creating ‘some kind of monster’ for users”.[51] For a long period of time, the network engineering community was polarized over the implementation of competing protocol suites, commonly known as the Protocol Wars. It was unclear which type of protocol would result in the best and most robust computer networks.[52]
Davies’ research at NPL later focused on data security for computer networks.[53]
Modern recognition[edit]
NPL sponsors a gallery, opened in 2009, about the development of packet switching and “Technology of the Internet” at The National Museum of Computing.[54]