Holidays Busy Traffic Forecasting Based on MPSO-SVR Algorithm
Holiday traffic prediction is the foundation of the whole communication network planning. In order to predict the busy traffic accurately and ensure the stability of the network, a support vector regression machine (SVR) combined with the improved particle swarm optimization algorithm (MPSO) is proposed, an inertia weight and shrinkage factor is introduced in the algorithm. The proposed algorithm is used to predict the busy traffic in Mid-autumn day. Simulation result shows that, compared with SVR algorithm and the basic particle swarm optimization optimize SVR (PSO-SVR) method, MPSO-SVR algorithm has a higher prediction precision.
Keywordsbusy traffic forecasting support vector regression machine improved particle swarm optimization algorithm
Unable to display preview. Download preview PDF.
- 1.Elattar, E.E., Goulermas, J.(Y.), Wu, Q.H.: Electric Load Forecasting Based on Locally Weighted Support Vector Regression. IEEE Transaction on Systems 40, 438–447 (2010)Google Scholar
- 5.Zhong, L., Pan, H.: Pattern recognition. Wuhan University Press, Wuhan (2006)Google Scholar
- 6.Ali, F.A., Selvan, K.T.: A Study of PSO and its Variants in respect of Microstrip Antenna Feed Point optimization, vol. 8, pp. 1817–1820 (2009)Google Scholar