A Novel Approach to Estimate Freeway Traffic State: Parallel Computing and Improved Kalman Filter

This paper presents a novel approach for freeway traffic state estimation. Although there is currently a wide variety of estimation methods, new designs and technologies can still be created and implemented to improve the accuracy and time efficiency. In this study, a parallel computing framework is developed. The parallel computing framework uses a genetic algorithm process to calibrate the parameters of the traffic model based on the freeway traffic data once an hour. Meanwhile, the framework uses a Kalman filter algorithm process to optimize the traffic model results with the real-time freeway traffic data. Under the framework, the operations of the two processes will not interfere with each other, thus reducing the time it takes to estimate, increasing the efficiency. Furthermore, an improved Kalman filter algorithm is proposed. The algorithm optimizes the traffic model results by balancing the ratio of detector measurements to model results based on their variances, instead of using the Taylor series expansion. Therefore, time efficiency and accuracy of the Kalman filter algorithm are improved. The effectiveness of the approach is evaluated using real field data. Experiments have shown that this approach has high real-time tracking accuracy, and is faster and more accurate than the extended Kalman filter. Results also indicated that the estimation accuracy can be enhanced by accessing additional data sources.