An expert system-based approach to capacity allocation in a multiservice application environment

The problem of bandwidth allocation for multiservice packet networks is discussed, and an expert system solution approach for solving it is described. The approach requires a minimal amount of processing, is very efficient, and has a fast response time. The implementation is based on modular capacity expansions and a priori limits on the number of connections for each service type. This approach can perform near-optimal capacity allocation in real time by using heuristic knowledge to virtually eliminate the required computations in this process. This implementation strategy ensures that each service demand meets its objectives. Concurrency control of this distributed expert system is considered. The advantages of the implementation in providing the ability to make rational decisions in an environment of uncertainty and imprecision, such as in the presence of nonsystematic overloads and network failures, are discussed.<>