DocumentCode :
184970
Title :
Multiple-clustering ARMAX-based predictor and its application to freeway traffic flow prediction
Author :
Cheng-Ju Wu ; Schreiter, Thomas ; Horowitz, Roberto
Author_Institution :
Dept. of Mech. Eng., Univ. of California at Berkeley, Berkeley, CA, USA
fYear :
2014
fDate :
4-6 June 2014
Firstpage :
4397
Lastpage :
4403
Abstract :
An adaptive predictor for a linear discrete time-varying stochastic system is proposed in this paper in order to forecast freeway traffic flow at a specific location over a one-hour horizon. Historical sensor data is first clustered by the K-means method to obtain the representative data pattern of the sensor. For each K-means cluster and using the clusters centroid as the exogenous input, the time-varying output of the sensor is subsequently modeled as an ARMAX stochastic process, and identified in real time using a recursive least squares (RLS) with forgetting factor algorithm. Based on the identified ARMAX model, a D-step ahead optimal predictor is generated for each cluster and its associated estimated error prediction variance calculated. The cluster and its associated ARMAX estimate that produces the smallest estimated D-step ahead error prediction variance is selected at each sampling time instant to generate the optimal D-step ahead predictor of the sensor output. The proposed technique is applied to empirical vehicle detector station (VDS) data to forecast both freeway mainline and on-ramp traffic flow at specific locations over a horizon of one hour. Results indicate that the proposed traffic flow predictor often offers superior flexibility and overall forecast performance compared to using either only historical data or only real-time sensor data on both normal commute days and days when unusual incidents occur.
Keywords :
autoregressive processes; discrete time systems; forecasting theory; least squares approximations; linear systems; pattern clustering; recursive estimation; road traffic; sampling methods; sensor fusion; stochastic systems; traffic information systems; ARMAX stochastic process; D-step ahead error prediction variance; VDS data; adaptive predictor; autoregressive moving average with exogenous input model; cluster centroid; empirical vehicle detector station data; error prediction variance; forgetting factor algorithm; freeway mainline traffic flow forecasting; freeway traffic flow prediction; historical sensor data clustering; identified ARMAX model; k-means cluster method; linear discrete time-varying stochastic system; multiple clustering ARMAX-based predictor; on-ramp traffic flow forecasting; optimal D-step ahead predictor; overall forecast performance; real-time sensor data; recursive least squares; representative data pattern; sampling time instant; sensor output; time-varying output; Autoregressive processes; Clustering algorithms; Detectors; Polynomials; Prediction algorithms; Predictive models; Traffic control; Filtering; Identification; Modeling and simulation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
American Control Conference (ACC), 2014
Conference_Location :
Portland, OR
ISSN :
0743-1619
Print_ISBN :
978-1-4799-3272-6
Type :
conf
DOI :
10.1109/ACC.2014.6859388
Filename :
6859388
Link To Document :
بازگشت