B-ISDN is expected to support a variety of services, each with its own traffic characteristics and quality-of-service requirements. Such diversity, however, has created new congestion control problems, some of which could be alleviated by a traffic prediction scheme. The paper investigates the applicability of artificial neural networks for traffic prediction in broadband networks. Recent work has indicated that such prediction is possible, as the neural networks are able to learn a complex mapping between past and future arrivals. Such work, however, has been based on the use of artificially generated traffic, and by definition the past and future arrivals are related. Real traffic is considered and it is shown that prediction is possible for certain traffic types but not for others. It is demonstrated that simple linear regression prediction techniques perform equally as well as do neural networks.
展开▼
