This paper proposes a connection admission control (CAC) method for asynchronous transfer mode (ATM) networks based on the possibility distribution of cell loss ratio (CLR). The possibility distribution is estimated in a fuzzy inference scheme by using observed data of the CLR. This method makes possible secure CAC, thereby guaranteeing the allowed CLR. First, a fuzzy inference method is proposed, based on a weighted average of fuzzy sets, in order to estimate the possibility distribution of the CLR. In contrast to conventional methods, the proposed inference method can avoid estimating excessively large values of the CLR. Second, the learning algorithm is considered for tuning fuzzy rules for inference. In this, energy functions are derived so as to efficiently achieve higher multiplexing gain by applying them to CAC. Because the upper bound of the CLR can easily be obtained from the possibility distribution by using this algorithm, CAC can be performed guaranteeing the allowed CLR. The simulation studies show that the proposed method can well extract the upper bound of the CLR from the observed data. The proposed method also makes possible self-compensation in real time for the case where the estimated CLR is smaller than the observed CLR. It preserves the guarantee of the CLR as much as possible in operation of ATM switches. Third, a CAC method which uses the fuzzy inference mentioned above is proposed. In the area with no observed CLR data, fuzzy rules are automatically generated from the fuzzy rules already tuned by the learning algorithm with the existing observed CLR data. Such areas exist because of the absence of experience in connections. This method can guarantee the allowed CLR in the CAC and attains a high multiplex gain as is possible. The simulation studies show its feasibility. Finally, this paper concludes with some brief discussions.

A fuzzy-inference method in which fuzzy sets are defined by the families of their alpha -level sets, based on the resolution identity theorem, is proposed. It has the following advantages over conventional methods: (1) it studies the characteristics of fuzzy inference, in particular the input-output relations of fuzzy inference; (2) it provides fast inference operations and requires less memory capacity; (3) it easily interfaces with two-valued logic; and (4) it effectively matches with systems that include fuzzy-set operations based on the extension principle. Fuzzy sets defined by the families of their alpha -level sets are compared with those defined by membership functions in terms of processing time and required memory capacity in fuzzy logic operations. The fuzzy inference method is then derived, and important propositions of fuzzy-inference operations are proved. Some examples of inference by the proposed method are presented, and fuzzy-inference characteristics and computational efficiency for alpha -level-set-based fuzzy inference are considered.>

Multistage fuzzy inference, where in the consequence in an inference stage is passed to the next stage as a fact, is studied and formulated as a type of linguistic-truth-value propagation, based on a concept of linguistic similarities between conditional propositions in successive stages. The formulation is useful in studying the characteristics of multistage fuzzy inference and reveals its structural relationship to multilayer perceptrons. The learning algorithm for multistage fuzzy inference is then derived, using backpropagating error information. The algorithm provides a means of automatically training the multistage fuzzy inference network, using input-output exemplar patterns. Intermediate membership functions based on simulation results, which are generated automatically in the intermediate stage, are proposed. The intermediate stage fuzzy-classifies the input space using intermediate membership functions. In this way, intermediate membership functions provide information regarding regional characteristics in exemplar patterns.>