In the near future, the packet switching system will need a large switching capacity. But, large processor can not be obtained in cheap way. So, it seems better to use smaller processors in a distributed fashion to obtain a large switching capacity. If several small switching devices are interconnected, it will be possible to increase the traffic handling capacity. Depending on the topology of the network, overall processing characteristics are different. Switching networks like torus etc. have the problem, because their nodes have the transit traffic. According to the increase of the switching network size, the transit traffic becomes large and the overall traffic efficiency of the network decreases significantly. The mesh network, in which all nodes are interconnected, does not have that problem, because there is no transit traffic in any node. This paper describes the composition of mesh type distributed packet switching systems. Flexible architectures are proposed, which are based on the building block structure. A node of these architectures is composed of several switching elements, and one or two intranode switches. Using these architectures, the addition of a new node to the system can be done without any modification of the fundamental units. The experimental system has been designed and built.

A store and fordward speech interpolation telephonic concentrator system is introduced. This paper presents first the system, describes its main parts and components and using typical parameters the probable system operation is outlined. Following, a study on capacity and delay of transmission of each voice packet is done by supposing that a M/D/1 model can be applied to the system. As voice has special characteristics and packets don't arrive randomly as supposed in the M/D/1 model, an analysis using a computer simulation is done. The source generating speech is closely matched with human voice by using a model with good resolution specially for small pauses of talkers during the active generation of speech. Using this source, simulations representing 120 or 180 sec. of actual time are done. As its results are different of those predicted by the M/D/1 model, the capacity of the system is forecasted again through examples. To increase even more the capacity without impairing the frozen out fraction of the speech or increasing the delay of each packed, a different method to decrease congestion in those short moments of high arrival rate of packets is intended. This method consist in to transmit from each voice sample only 7 bits during the high congestion moments, creating new capacity by shortening packets. Results of parameters obtained by simulation and probable capacity of the system are again shown.

This paper describes the voice-data hybrid transmission facilities, which can be obtained by using 64 kbit/sec digital line. Instead of using separate transmission facilities for voice and data services, or instead of increasing the digital transmission rate, the silent portion of telephonic speech can be used to transmit the data. The line is available for the data transmission when a pause of the voice is detected, and the line is blocked for the data transmission during a talkspurt of the voice. Two models of the hybrid transmission system are shown. The first model, in which the data arrive randomly in bursts, is useful to describe a kind of interactive process. The second model, in which the data arrive continuously, describes file transfers, facsimile transmissions, etc. The necessary buffers, the blocking probabilities, the data delay, and other factors of both models are calculated.