Traffic Prediction on Communication Network based on Spatial-Temporal Information

Power communication network traffic prediction is important basis of safely assigning and economically running. The forecasting precision will directly affect the reliability, economy running and supplying power quality of power system. Paper first expounds the electric power communication network traffic prediction research present situation, summarized the characteristics of the forecast and the influencing factors, summarizes the commonly used method, is put forward to the return of the electric power communication network traffic based on libsvm prediction method, and the PSO (particle swarm optimization) algorithm is adopted to model parameters optimization, with the test set error as the decision, based on the optimization of model parameters, choice, makes the prediction precision is improved.

Download Full-text

Power communication network traffic prediction based on two dimensional prediction algorithms

Proceedings of the 2016 4th International Conference on Electrical & Electronics Engineering and Computer Science (ICEEECS 2016) ◽

10.2991/iceeecs-16.2016.187 ◽

2016 ◽

Author(s):

Lei Xiao ◽

Xue Yang ◽

Min Zhu ◽

Lipeng Zhu

Keyword(s):

Communication Network ◽

Network Traffic ◽

Traffic Prediction ◽

Two Dimensional ◽

Prediction Algorithms

Download Full-text

Information visualization and traffic prediction analysis platform development in electric power communication network

2015 17th International Conference on Advanced Communication Technology (ICACT) ◽

10.1109/icact.2015.7224876 ◽

2015 ◽

Author(s):

WeiDong Feng ◽

Yong Sun ◽

Ran Zhan ◽

ZhenChao Sun ◽

Geng Zhang ◽

...

Keyword(s):

Communication Network ◽

Electric Power ◽

Information Visualization ◽

Traffic Prediction ◽

Prediction Analysis ◽

Platform Development ◽

Analysis Platform

Download Full-text

Traffic Prediction Based on Grey Model Optimized by Buffer Operator and PSO in Communication Network for Electric Power

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.397-400.1994 ◽

2013 ◽

Vol 397-400 ◽

pp. 1994-1998

Author(s):

Run Ze Wu ◽

Ying He ◽

Liang Rui Tang

Keyword(s):

Communication Network ◽

Prediction Model ◽

Electric Power ◽

Fitness Function ◽

Prediction Method ◽

Grey Model ◽

Traffic Prediction ◽

Prediction Result ◽

Correlation Degree ◽

Improved Model

To meet the requirements of planning and to improve accuracy and stability of traffic prediction model in the communication network for electric power, a traffic prediction method based on grey model optimized by buffer operator and particle swarm optimization (PSO) is proposed in this paper. Variable weights buffer operators are implemented for preprocessing traffic data to enhance the adaptability of gray prediction model. Taking the maximum grey correlation degree between prediction series and true series as objective function, based on the search ability of PSO, the fitness function is founded, which can determine the optimal parameters of gray model. Applying the improved model to traffic prediction in communication network for electric power, a new prediction result is drawn. The prediction result shows that the improved model has higher prediction accuracy compared with the traditional GM (1, N) model.

Download Full-text