TITLE

Short-term Traffic Flow and Hourly Electric Load Forecasting Algorithm based on Echo State Neural Networks

AUTHOR(S)
Qingsong Song; Xibin Liu; Xiangmo Zhao
PUB. DATE
March 2012
SOURCE
International Journal of Digital Content Technology & its Applic;Mar2012, Vol. 6 Issue 4, p166
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
An algorithm for short-term traffic flow and hourly electric load forecasting based on echo state neural networks (ESN) is proposed in this paper. ESN is a new paradigm for using recurrent neural networks (RNNs) with a simpler training method. While the prediction, traffic flows and load patterns are treated as time series signals; no further information is used than the past data records, such as weather, seasonal variations. The relation between key parameter of the ESN and the predicting performance is discussed; ESN and feedforward neural network (FNN) are compared with the same tasks also. Simulation experiment results demonstrate that the proposed ESN algorithm is valid and can obtain more accurate predicting results than the FNNs for these short-term traffic flow and hourly electric load prediction problems.
ACCESSION #
76361762

 

Related Articles

  • Design and Application of Reduced Error Pruning Tree for Traffic Incident Detection. Qingchao Liu; Jian Lu; Shuyan Chen; Yaping Li; Xingchen Yan // Applied Mechanics & Materials;2014, Vol. 744-746, p1931 

    For aim applied to develop Intelligent Transportation System (ITS), a traffic incident detection method based on Reduced Error Pruning Tree (REPTree) algorithm of decision tree is presented. Different from unpruned decision tree, REPTree model is a fast decision tree learner which builds a...

  • A Novel Active Safety Algorithm using Improved Neural Network. Jiguang Chen; Huanyan Qian; Jiming Yu; Shuo Chen; Xiaoyong Yan // Information Technology Journal;2014, Vol. 13 Issue 1, p110 

    In recent years, with the beginning of the close integration of the Intelligent Transportation System (ITS) and vehicle ad hoc networks, the active safety of vehicle ad hoc network, just as collision warning, has become an important direction. This study puts forward a novel active safety...

  • Parallel Implementation of BP Neural Network for Traffic Prediction on Sunway Blue Light Supercomputer. Jinqiao Feng; Weidong Gu; Jingshan Pan; Hongjun Zhong; Jidong Huo // Applied Mechanics & Materials;2014, Issue 614, p521 

    Parallelized training algorithm of MLP-BP neural network is implemented on the Sunway Blue Light Supercomputer. Efforts are mainly focused on the dada parallel method based on the characteristics of the training process. The implementation mainly depends on MPI techniques, which ensures the...

  • Gaussian Mixture Models and Probabilistic Decision-Based Neural Networks for Pattern Classification: A Comparative Study. Yiu, K. K.; Mak, M. W.; Li, C. K. // Neural Computing & Applications;1999, Vol. 8 Issue 3, p235 

    Probabilistic Decision-Based Neural Networks (PDBNNs) can be considered as a special form of Gaussian Mixture Models (GMMs) with trainable decision thresholds. This paper provides detailed illustrations to compare the recognition accuracy and decision boundaries of PDBNNs with that of GMMs...

  • Feature Selection Using Probabilistic Neural Networks. Hunter, A. // Neural Computing & Applications;2000, Vol. 9 Issue 2 

    Selection of input variables (features) is a key stage in building predictive models. As exhaustive evaluation of potential feature sets using full non-linear models is impractical, it is common practice to use simple fast-evaluating models and heuristic selection strategies. This paper...

  • Editorial. Li, Kang // Transactions of the Institute of Measurement & Control;2006, Vol. 28 Issue 1, p1 

    The article discusses various reports published within the issue, including one by Dongbin Zhao and Jianqiang Yi on neural network optimization and another on immune genetic algorithm by Quanyuan Jiang, Zhenyu Zou, Zhiyong Wang and Yijia Cao.

  • Intelligent preprocessing for neural networks in the H1 experiment. Pre┬┤votet, J. C.; Denby, B.; Garda, P.; Granado, B.; Fro┬Ęchtenicht, W.; Grindhammer, G.; Janauschek, L.; Kiesling, C.; Kobler, T.; Koblitz, B.; Schmidt, S.; Tzamariudaki, B.; Udluft, S. // AIP Conference Proceedings;2001, Vol. 583 Issue 1, p73 

    After the upgrade of the HERA machine at DESY in 2001, an increase in the luminosity of a factor 5 is expected. Since the data output rate of the L2 trigger should be kept at the pre-upgrade level, a smarter way of preprocessing data has been developed, extracting the most physically relevant...

  • A Robust Evolutionary Algorithm for Training Neural Networks. Yang, Jinn-Moon; Kao, Cheng-Yan // Neural Computing & Applications;2001, Vol. 10 Issue 3, p214 

    A new evolutionary algorithm is introduced for training both feedforward and recurrent neural networks. The proposed approach, called the Family Competition Evolutionary Algorithm (FCEA), automatically achieves the balance of the solution quality and convergence speed by integrating multiple...

  • Vehicular Traffic Re-Routing For Avoiding Traffic Congestion in VANET. Kirthiga, N.; Dhivyashree, M.; Karthik, S.; Srihari, K. // Advances in Natural & Applied Sciences;Jul2014, Vol. 8 Issue 8, p116 

    The number of vehicles allow to use a particular lane is not fixed in the existing system. When there is a active mobile network and suddenly an accident occur, the upcoming vehicles gets slow down due to the congestion. In the existing system, only the detection of congestion is analyzed but...

Share

Read the Article

Courtesy of THE LIBRARY OF VIRGINIA

Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics