Recursive estimation based on the equality-constrained optimization for intersection origin-destination matrices

A fast constrained recursive identification (CRI) algorithm is proposed to estimate intersection origin-destination (O-D) matrices dynamically. The ba sic idea of the CRI algorithm is to estimate intersection O-D matrices base d on equality-constrained optimization and then to adjust them by Bell's co rrection (Bell, M.G.H., 1991a. The estimation of origin-destination matrice s by constrained generalized least squares. Transporation Research 25B, 13- 22; Bell, M.G.H., 1991b. The real-time estimation of origin-destination flo ws in the presence of platoon dispersion. Transportation Research 25B, 115- 125.) for inequality constraints. Numerical results show that the accuracy of estimates by the CRI algorithm is fairly good-the solutions obtained by the CRI are optimal in majority of the cases, while the computational effor ts are very limited-increment mainly lies on the evaluation of an inverse f or an mxm matrix (m = 4 for a typical intersection) compared with the ordin ary recursive least squares method. These results mean that a properly desi gned recursive algorithm can indeed avoid iterative procedure in each time step to obtain highly accurate on-line estimates for intersection O-D matri ces. Therefore, the CRI algorithm with its reasonable balance between accur acy and computational simplicity is very suitable for practical use. (C) 19 99 Elsevier Science Ltd. All rights reserved.