Page images

single institution but useful to an audience geographically dispersed.

"2. The inadequacy of general data banks or general collections of information to meet local needs where remote resources can be used in a complementary fashion to fulfill the need.

"3. The centralization of programming services, processing capabilities or scientific resources with a geographically dispersed need. "4. The need for interpersonal (including intergroup) direct communication. This includes teleconferencing and educational activities. "5. A justification on economic, security or social grounds for distribution of responsibility for load sharing among organizations or geographical regions." (Davis, 1968, pp. 1–2). "In certain areas, such as law enforcement, medicine, social security, and education, there is a need for joint Federal-State computer communications networks which can apply new technology to improving the management of major national programs in these areas." (Johnson, 1967, p. 5).

"It has been suggested that a principal advantage to be gained from computer networks is the ability to distribute work evenly over the available installations or to perform certain computations at installations particularly suited to the nature of the job.' (Dennis, 1968, p. 374).

[ocr errors]

"The time-sharing computer system can unite a group of investigators in a cooperative search for the solution to a common problem, or it can serve as a community pool of knowledge and skill on which anyone can draw according to his needs." (Fano and Corbató, 1966, p. 129).


"Within a computer network, a user of any cooperating installation would have access programs running at other cooperating installations, even though the programs were written in different languages for different computers. This forms the principal motivation for considering the implementation of a network." (Marill and Roberts, 1966, p. 426).

3.10 "The establishment of a network may lead to a certain amount of specialization among the cooperating installations. If a given installation, X, by reason of special software or hardware, is particularly adept at matrix inversion, for example, one may expect that users at other installations in the network will exploit this capability by inverting their matrices at X in preference to doing so on their own computers." (Marill and Roberts, 1966, p. 426).

"An interconnected network would make it possible for the top specialists in any field to instruct anyone within the reach of a TV receiver." (Brown et al., 1967, p. 74).

[blocks in formation]

c. all operations may be publicized." (Brown et al., 1967, p. 209).

3.12 "The operator's charges to clients must be in fair proportion to the usage made of installation resources (processing, time, storage occupancy, etc.). Therefore adequate records must be kept of resource use." (Dennis, 1968, p. 375).

"A principal [individual or group of individuals] is charged for resources consumed by computations running on his behalf. A principal is also charged for retention in the system of a set of computing entities called retained objects, which may be program and data segments ." (Dennis and Van Horn, 1965, p. 8).

[ocr errors]

"The equitable allocation of space and time by administrative fiat. This is probably an overwhelming problem in a network since the predicting of communication paths and computing facilities required by any user would be quite unwieldy. . .

"Thus a more elaborate scheme seems to be necessary- one whose rates are proportional to the value of the service. This would be modified in a network because the rate for the same kind of service may vary among the installations." (Brown et al., 1967, p. 212).

"Built-in accounting and analysis of system logs are used to provide a history of system performance as well as establish a basis for charging users.' (Estrin et al., 1967, p. 645).

3.13 "Questions of technical feasibility and economic value are not the sole determinants of the computer utility. The development of the computer utility may be influenced by norms, or lack of norms, about the confidentiality of data. At the moment there do not seem to be any clear standards of good practice; perhaps there was less need before technology greatly increased capabilities for handling data." (Jones, 1967, p. 555).

"It should be easy and convenient for a user to allow controlled access to any of his segments, with different access privileges for different users." (Graham, 1968, p. 367).

3.14 "The designer must decide whether he will provide the high-speed service to all users, to provide the service that the majority request, and leave the minority to fend for themselves, or to provide the degree of speed needed in each case, but no more. Ideally, he should know the entire distribution of response time requirements. It is even desirable to know how the arrival of these queries will be distributed in time throughout the day. In attempting to meet requirements, he must consider what is actually being retrieved in any stated response interval. Does the user want hard copy or will he be satisfied with citations or index records? The engineering problems associated with high-speed retrieval of hard copy from files can be formidable. If a conversational, or browsing, mode of search is used in which the searcher uses a succession of queries, do we aim to minimize his total search time, or only to give him immediate

[blocks in formation]

1) the ability of the network to accept additional traffic;

2) the 'importance' of each user and the 'utility' of his traffic;

3) the data rate of each input transmission medium or the transducer used;

4) the tolerable delay time for delivery of the traffic." (Baran, 1964, p. v).

"Many separate low-data-rate devices time-shared or concentrated into a single high-data-rate link permit better averaging, as compared to a few correspondingly-higher-data-rate users. But, as many of the high-data-rate users 'get in' and 'get out' fast, they have a short holding time. This helps the averaging process. To be precise in this computation, a better understanding of the number of users, their use statistics, and the network characteristics appears mandatory.

The mixed requirement that, while we wish to give priority treatment to the higherprecedence traffic of equal network loading, we must also satisfy the goal that we preserve a minimum transmission capability for the lower-precedence traffic. Thus, instead of a blanket rule that all traffic of a given precedence grade will be transmitted before handling the next lower precedence grade, we choose to use the time ratios of these precedence categories to act as a preference weighting factor." (Baran, 1964, pp. 30, 33).

"An added complication may be introduced in the form of a hierarchy of precedence classifications. This can be a very useful feature of the communications system, allowing important messages to avoid delay by by-passing a string of messages of relatively low urgency. But it adds an extra dimension to the message queue, requiring separate listings for each precedence. This system can go beyond governing of the order of transmission, and can allow high-priority messages to interrupt others during their transmission. In such a system, message switching has an advantage over circuit switching, in that an interrupted message can be automatically retransmitted as soon as possible, with no further action by the sender. But the possibility of interruption necessitates that the entire contents of a message be retained in storage until its last transmission is completed." (Shafritz, 1964, p. N2.3-3).

"The difference between control strength and priority is that control strength is used for defining interrupt classes (an interrupt class is the set of all requests with the same control strength), while priority is used for ordering requests within the same interrupt class." (Dahm et al., 1967, p. 774).

3.15 "In real time data


oriented problems, four major system equipment performance factors must be evaluated:

1. Real time processing capability of central processor(s)

2. Core memory size provided in central processor(s)

3. Bulk storage size provided

4. Limitations on real time access to bulk storage." (Birmingham, 1964, p. 38.)

3.16 "It seems imperative that EDUCOM . . . establish certain technical standards and operation procedures which each state or regional group must meet before they can be interconnected. These standards should apply to digital transmission, telephonic communications, and television..." (Brown et al., 1967, p. 54).

"One final thought about integration. Integration is facilitated by the standardization of equipment, processes, and languages. However, standardization in command-and-control systems must be considered in the light of the evolutionary nature of these systems. First, standardization should be based upon those elements which are missionindependent; that is, the elements standardized should be general-purpose in nature. Secondly, the standardization of system elements should be modular; that is, it should be possible to add other elements to them in order to modify or increase the capabilities of the system. If system elements are standardized at too low a level of aggregation, the system's speed of response is increased, but its flexibility is reduced. If, on the other hand, elements are standardized at the higher levels of aggregation, provided these are not higher than the level of the designer's problem, flexibility is increased, but there is an accompanying reduction in the system's speed of response. It is this trade-off between flexibility and speed of response that makes the standardization problem such a difficult one." (Jacobs, 1964, pp. 41-42).

"In general the standards of distributed-control systems are standards built around each class of job for each level of job for each unique function of the system. Procedures and languages need not be standardized across job levels or across functions. Minimum standardization does not, however, imply the complete freedom of each functional unit to select idiosyncratic communication codes or bizarre formats. Such matters as codes, formats, file structures, vocabularies, and message syntax are all aspects of performance programs, and the library of these program building blocks, from which any information-processing job can be built, is bounded from above. Executive control over the limits of the library establishes the boundaries of the range of alternatives available at any organizational level. This is standardization of a sort, but it allows considerably more flexibility than the standardization generated by a rigid set of specifications to be applied across functions and up and down the

hierarchy of information-processing jobs." (Bennett, 1964, p. 107).

3.17 "A built-in system for user feedback would be essential in determining near-future needs and current inadequacies of the network." (Brown et al., 1967, p. 216).

"It was considered that it might be useful to have all users of materials feed back their evaluations, which could be analyzed statistically for consideration of the next user." (Brown et al., 1967, p. 63).

"Provisionally we characterize a network by: A. Remote and rapid services regarding selection, acquisition, organization, storage, retrieval, and processing of information and procedures in current files . .

B. Feedback to the

1. Originator or organizer of the information (hence there would be a Community of users improving a common store of materials and procedures).

2. Supervisor of the network services (hence the system would be adaptive to the needs of the users)." (Brown et al., 1967, pp. 49-50).

"In designing a priority handling system, we should never permit ourselves to believe that we have more (or less) usable communications capability than we really have. This implies network status control feedback loops." (Baran, 1964, pp. 17-18).

3.18 "To facilitate system scaling, reliability, and modularity, many multi-processor operating systems are designed to treat the processors as homogeneous system resources. Hence, there is no 'supervisor' processor, each schedules and controls itself. To prevent critical races and inconsistent results, only one processor at a time is permitted to alter or examine certain shared system data bases; all other processors attempting simultaneous access are locked-out. This phenomenon is not strictly limited to homogeneous processor systems, similar requirements apply to any multi-processor scheme utilizing shared data bases." (Madnick, 1968, p. 19).

3.19 "Some general observations may be of interest. There are indications that the cost of operating an information system network, organized along subject lines, varies little with change of process allocation within the system. Whether all acquisition and input processes are carried on in a center clearing house or distributed in some logical manner among the service centers does not appear to make a significant difference in cost. On the other hand, centralization in the regionally organized system becomes imperative if excess operating costs are to be avoided. In a system organized to serve users on a project basis, there is an indication of some economy of operation being achieved by complete decentralization." (Sayer, 1965, pp. 141-142.)

"The least expensive method of organizing a science information system network appears to be on a regional basis with the centralization of acquisition input processes being undertaken in a central clearing house." (Sayer, 1965, p. 142.)

3.20 "In the network concept, then, the technical information centers would be linked by the traffic routing centers. Each would become dependent upon the other with both responding to the law of supply and demand, service and customer satisfaction, and continued viability based upon justification of existence through performance." (Vlannes, 1965, p. 5).

"Other choices in the spectrum may include that of a network of information centers in which each community performs and contributes to the advancement of knowledge in accordance with its capabilities. Of course, a network must impose a series of constraints in order to operate, but it also allows for the flexibility that a rigidly structured system cannot accommodate. A network also fosters a sense of competition in which each community must ever strive to re-orient itself in order to survive and progress in its changing environment. In addition, each must become sensitive to the changes in the other communities in order that it may react, re-evaluate and adapt to the net set of goals that are inevitable." (Vlannes, 1965, p. 4.)

"In order to gain control over the accountability data, a telephone switchboard was added to the system... With the formalization of the terminal network, the concept of operation changed from a central computer with satellite terminals to the concept of a central terminal network with satellite computers." (O'Sullivan, 1967, p. 169).

3.21 "Many of the larger systems must also take into account the requirements for providing machine-readable output for use in a decentralized network of search centers. The designer must remember that other users will place constraints on the parent system. It must be remembered that a change to the central system has multiple effects on the various members of the decentralized network. Good system documentation will be essential in providing programs to the local search centers. A constant training requirement will also be imposed upon the central system, and technical liaison must be maintained with all users in the network. Effective file maintenance procedures must be developed well in advance of implementation of the decentralized system. Changes and updatings to the central nie will occur frequently, and an adequate mechanism must be available for insuring that these same changes are made to all files in the field." (Austin, 1966, p. 245).

"Locating the point of minimum sufficient centralization for a system may call for a some what atypical philosophy of system design, a philosophy not commonly held by theoreticians on the subject but often implicit in the daily design practices of the engineers and logicians involved in the actual specification of system details. That

is, a system should have standardized procedures for only the smallest job units that can be formally specified. These fixed subroutines can then be combined to form larger routines suitable for performing larger segments of the overall activity. At any point where two jobs are dissimilar, this dissimilarity can be reflected not only in different flow diagrams but also in different formats, codes, sequencing procedures, indexing methods, displays, and so forth. To this extent, the system is neither tailor-made nor ready-made. It is not uneconomically designed so that every job is unique, nor is it standard but ill-fitting because dissimilar jobs are forced into standardization. Rather, like a made-to-measure suit, the system is built around small standardized parts, each designed to fit a small part of the overall job. The larger portions of the system are not standardized as total units, but are unique configurations of standardized smaller parts." (Bennett, 1964, p. 108).

3.22 Baran (1964) considers, for example, "four separate techniques that can be used singly or in combination to achieve, through automation, 'best' use of a seriously, degraded and overloaded communications plant, within the framework of a rapidly changing organizational structure." (p. v).

3.23 "Calulation of the average daily volume and the peak volume of information to be handled in the system consists of four steps:

1. Calculate the average daily volume of messages presently flowing in the system.

2. Calculate the average number of characters in each message.

3. Calculate the average daily total transmission time.

4. Calculate the peak volumes.

The communications designer must plan the system to handle the peak traffic loads with acceptable delay as well as the total traffic load.” (Gentle, 1965, p. 58.)

"Calculate Call Volume. The first step in calculating the volume of information that must be handled by the data communications system is to determine the number of messages (called 'traffic') handled in an average day. This is done for traffic to and from every point in the system. The volume is calculated by taking a sample of several days' traffic and actually counting the number of messages handled each day at each location. The number of days to be included in the study is based upon the estimated number of messages that are handled in a month. An estimate of the monthly volume should be made, and the following table may be used as a guide in determining the number of days to be studied.

[blocks in formation]

Ideally the working days to be studied should be chosen at random, but if for any reason a series of consecutive days must be selected, care should be taken to avoid days immediately preceding or following holidays. In addition, the count must be made at each location from which information is sent and at which information is received." (Gentle, 1965, pp. 58-59.)

"Calculate the Total Transmission Time. The third step, after calculating the average number of characters per message, is to determine the average daily total transmission time. At this point a transmission speed must be assumed. This transmission time can be calculated by dividing the average number of characters per message by the assumed speed of the system. If the average message has 2,500 characters, for example, and the assumed transmission speed is 10 characters per second, the average transmission time per message will be 250 seconds. To this figure, however, must be added some operating time for dialing the call, waiting for the connection to be established and, in some cases, coordinating the forthcoming transaction with the personnel at the receiving end. Operating time should be calculated from a study of a sample of calls, but if this is impracticable, the system designer may use 100 seconds as an overall average for the operating time on each dialed-up data communications call.

"The amount of delay to be expected during the busy hour depends upon the holding time of the circuit at the receiving location and the total number of minutes in the busy hour during which information will be received. Data communication planners refer to a series of charts which indicate the expected delay in transmissions when holding time, circuit use, and number of circuits in the group are known factors. The number of incoming circuits affects the probability that a calling part will receive a busy signal." (Gentle, 1965, pp. 63, 65).

"The intervals at which messages are transmitted. Are these intervals fixed or random? What are the peak rates, and at what times of day will they occur?" (Reagan, 1966, p. 23).

"To determine the proper size of a dial system required, it is necessary to study the company's busy hour, calculate the average message length, determine the total number of call seconds involved, and then consult the hundred-call-second (CCS) tables developed for telephone trunk loading. On the CCS tables is a listing for the number of trunk lines required for a given loading and grade of service desired. If you want only one lost (busy)

call in every hundred, the tables will show how many trunk lines are required. If you can tolerate 10 lost calls per hundred, the tables show that you can get by with fewer lines. In this manner, you choose the grade of service you require to handle your particular data communications problem." (Birmingham, 1964, p. 37).

"Whenever it is necessary to have a large number of stations communicate among a large number of potential addresses, it is a practical necessity to use some form of switching. There is always a very wide variety of potential groupings and possible network configurations. The shape and complexity of the resulting network is very much dependent upon the economies one wishes. to make in circuit groupings. The choice of these groupings in turn depends upon the statistics of the expected traffic. If the traffic statistics are known very accurately, large savings in cost of selection of routes and assignment of channels can be realized." (Baran, 1964, p. 15).

"Complex data communications systems that terminate many lines in a central facility usually use either a multi-line communications controller in conjunction with general-purpose computer or a specialized, stored-program communications processor. These units are capable of buffering and controlling simultaneous input/output transmissions on many different lines. Again, a wide variety of equipment is now available to perform these functions. The available devices differ in the number and speed of lines they can terminate and in their potential for performing auxiliary or independent data processing. Examples include the three multi-line communications controllers available for use with the general-purpose IBM System/360 computers and the Collins Data Central system, a computer system designed especially for message switching applications." (Reagan, 1966, p. 26).

[ocr errors]

"Data rate alone, however, does not provide a complete measure of network loading; some devices have a short duty cycle, such as one computer sending the contents of its core to a remote computer. While such devices place a heavy peak demand for service, they are highly intermittent. On the other hand, a pulse-coded telephone call places a lower peak demand load, but ties up network capacity for a longer period and results in heavier average loading. Therefore, we should include an expected message-duration or holding-time factor in the network-load weighting table." (Baran, 1964, p. 30).

"It is necessary to have some idea of the types of messages that the system will be handling so that estimates of transmission rate requirements can be made. This calculation is intimately tied in with the distribution of terminals from the central computer system. It may be economically justifiable, even at necessity, to multiplex several of the terminals

together onto one high-speed line." (Stephenson, 1968, p. 55).

"It is vital to have some knowledge of the average mix of message types and message lengths in the system." (Stephenson, 1968, p. 55).

"The results obtained from the numerical solution of a model give a precise and comprehensive description of the statistical effects of high traffic. The value of such precise and extensive data for computer systems may not be obvious, especially since 'worst case' examples and physical reasoning can establish much of the qualitative behavior of the system. The two prominent facts which warrant such analysis are the large scale of most multiconsole systems, and the critical nature of machine response in their conception. Because multi-console systems are of such large scale, it can be worthwhile economically to thoroughly evaluate proposed designs, seeking to achieve maximum capacity. Such design evaluation requires a rather accurate knowledge of the traffic in the various parts of the system. Because much of the effectiveness of a multi-console system can be rapidly dissipated by poor response characteristics, an accurate statistical description of response is also needed. The existence of a capability for rapidly solving general queueing models makes this approach a much needed alternative to Monte Carlo simulations or experiments in traffic studies." (Fife and Rosenberg, 1964, pp. H1-6).

3.24 "The unequal and intermittent loading of net-type channels in present communications results in inefficient utilization of radio frequencies. If channels were made available to other users during periods of idleness, more communications could be handled within a given frequency band. A solution to the problem of frequency congestion can be found in giving each user access to a group of channels through a system which selects an idle channel for each call and releases the channel as soon as the call is terminated. Such a system may be called a random access system, since an idle channel is selected at random from the group each time a user wishes to place a call. After a channel is selected, a means is needed to direct the call to the intended group or individual without disturbing users to whom the call is not directed. This process is called discrete addressing and is applied in the form of tone signalling to many systems in use today. The combination of the terms Random Access Discrete Address describes a class of communication systems employing these principles and is frequently referred to by the acronym, ‘RADA”.” (Horne et al., 1967, pp. 115-116).

"Adaptive channel communication systems provide efficient bandwidth utilization by allowing time sharing of a small number of channels by a large group of users with low duty rates. Unlike fixed frequency netted systems, where a call to a nonbusy subscriber cannot be made if his assigned frequency is in use by another of the net members,

« PreviousContinue »