This paper proposes an access network requirements analysis method based on similar service feature values clustering. The network service feature values data are collected from the real access network, including devices and users’ information. The K-means ++ algorithm is adopted to cluster the PON ports, based on the similar service feature values of users connected to them. 3 classifiers are selected for classification training and prediction. They are K-nearest neighbors, SVMs and perceptron. In the case of no clustering, K-nearest neighbor algorithm performs better, and the classification correct rate is about 91.1%. And if the data is divided into 5 groups by K-means++ algorithm, it can be calculated that the average accuracy is 94.3%. Compared with the result without clustering of service feature values, it achieves more accurate prediction and the correct rate is increased by 3.3%. With this method, the operator can determine whether the PON port needs to be expanded, making the expansion planning more forward-looking. At the same time, combining the prediction results with the PON port geographic information, it can distinguish areas with sufficient or insufficient broadband resources, and helps operators adjust service allocation plans to match user needs.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.