대한토목학회논문집 (KSCE Journal of Civil and Environmental Engineering Research)

  • 제38권1호
  • /
  • Pages.73-80
  • /
  • 2018
  • /
  • 1015-6348(pISSN)
  • /
  • 2799-9629(eISSN)
대한토목학회 (Korean Society of Civil Engeneers)
권호 표지
DOI QR코드

DOI QR Code

대용량 이력자료를 활용한 다중시간대 고속도로 교통량 예측

Multiple Period Forecasting of Motorway Traffic Volumes by Using Big Historical Data

  • 장현호 (서울대학교) ;
  • 윤병조 (인천대학교 도시과학대학 도시공학과)
  • 투고 : 2017.09.11
  • 심사 : 2017.11.17
  • 발행 : 2018.02.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

고속도로 교통류 제어는 기존의 Reactive 방식(실시간 대응)에서 Proactive 방식(사전 대응)으로 발전하고 있다. 첨단 고속도로 교통류 제어의 핵심 입력자료 중 하나는 여러 시간대에 걸치는 장래 교통량 상태이다. 다중 시간대 교통량 예측을 위해서는 장래 상태의 불확실성을 극복해야 한다. 이는 예측 시간대의 확장에 따라 장래 상태의 불확실성은 증가하기 때문이다. 따라서 다중 시간대 교통량 예측을 위해서는 장래 상태의 불확실성을 효과적으로 극복할 수 있는 실행 가능한 방안이 필요하다. 본 연구에서는 대용량 이력자료에 내재된 교통류 상태의 시간적 진화 행태를 이용하여 장래 상태의 불확실성을 효과적으로 극복함으로써 다중 시간대 장래 교통량 상태를 예측하는 모형을 제시하도록 한다. 개발 모형은 현행 교통량의 상태 진화를 기반으로 대용량 자료에 내재된 과거 상태를 추출하고, 이를 이용하여 장래 상태를 예측한다. 추가로, 개발된 모형은 실제 적용을 고려하여 자료관리시스템에 적합하도록 설계되었다. 적용결과, 개발모형은 다중 시간대에 걸치는 불확실성을 효과적으로 극복함으로써 우수한 예측력을 보였으며, 첨단자료관리시스템에 실제 적용이 가능하다고 판단된다.

In motorway traffic flow control, the conventional way based on real-time response has been changed into advanced way based on proactive response. Future traffic conditions over multiple time intervals are crucial input data for advanced motorway traffic flow control. It is necessary to overcome the uncertainty of the future state in order for forecasting multiple-period traffic volumes, as the number of uncertainty concurrently increase when the forecasting horizon expands. In this vein, multi-interval forecasting of traffic volumes requires a viable approach to conquer future uncertainties successfully. In this paper, a forecasting model is proposed which effectively addresses the uncertainties of future state based on the behaviors of temporal evolution of traffic volume states that intrinsically exits in the big past data. The model selects the past states from the big past data based on the state evolution of current traffic volumes, and then the selected past states are employed for estimating future states. The model was also designed to be suitable for data management systems in practice. Test results demonstrated that the model can effectively overcome the uncertainties over multiple time periods and can generate very reliable predictions in term of prediction accuracy. Hence, it is indicated that the model can be mounted and utilized on advanced data management systems.

키워드

참고문헌

  1. Altman, N. S. (1992). "An introduction to kernel and nearestneighbor nonparametric regression." The American Statistician, Vol. 46, pp. 175-185.
  2. Chang, H. and Lee, S. (2003). "A study on link travel time prediction by short term simulation based on CA." Journal of Korean Society of Transportation, Vol. 21, No. 1, pp. 91-102 (in Korean).
  3. Chang, H., Park, D., Lee, S., Lee, H. and Baek, S. "Dynamic multi-interval bus travel time prediction using bus transit data." Transportmetrica, Vol. 6, No. 1, pp. 19-38. https://doi.org/10.1080/18128600902929591
  4. Davis, G. and Nihan, N. (1991). "Nonparametric regression and short-term freeway traffic forecasting." Journal of Transportation Engineering, Vol. 117, No. 2, pp. 178-188. https://doi.org/10.1061/(ASCE)0733-947X(1991)117:2(178)
  5. Karlsson, M. and Yakowitz, S. (1987). "Rainfall-runoff forecasting methods, old and new." Stochastic Hydrology and Hydraulics, Vol. 1, No. 4, pp. 303-318. https://doi.org/10.1007/BF01543102
  6. Mulhern, F. J. and Caprara, R. J. (1994). "A nearest neighbor model for forecasting market response." International Journal of Forecasting, Vol. 10, No. 2, pp. 191-207. https://doi.org/10.1016/0169-2070(94)90002-7
  7. Oswald, R. K., Scherer, W. T. and Smith, B. (2000). "Traffic flow forecasting using approximate nearest neighbor nonparametric regression." A research project report for U.S. DOT University transportation center.
  8. Qi, Y. and Smith, B. L. (2004). "Identifying nearest-neighbors in a large-scale incident data archive." Transportation Research Report, 1879, pp. 89-98.
  9. Robinson, P. (1983). "Nonparametric estimators for time series." Journal of Time Series Analysis, Vol. 4, No. 3, pp. 185-207. https://doi.org/10.1111/j.1467-9892.1983.tb00368.x
  10. Smith, B. L., Williams, B. M. and Oswald, R. K. (2002). "Comparison of parametric and nonparametric models for traffic flow forecasting." Transportation Research Part C, Vol. 10, No. 4, pp. 303-321. https://doi.org/10.1016/S0968-090X(02)00009-8
  11. Stathopoulos and Karlaftis (2003). "A multivariate state-space approach for urban traffic flow modeling and prediction." Transportation Research Part C, Vol. 11, No. 2, pp. 121-135. https://doi.org/10.1016/S0968-090X(03)00004-4
  12. Vlahogianni, E. I., Karlaftis, M. G. and Golias, J. C. (2005). "Optimized and meta-optimized neural networks for short-term traffic flow prediction: A genetic approach." Transportation Research Part C, Vol. 13, No. 3, pp. 211-234. https://doi.org/10.1016/j.trc.2005.04.007
  13. Vlahogianni, E. I., Karlaftis, M. G. and Golias, J. C. (2014). "Short-term traffic forecasting: Where we are and where we're going." Transportation Research Part C, Vol. 43, No. 1, pp. 3-19. https://doi.org/10.1016/j.trc.2014.01.005
  14. Yoon, B. and Chang, H. (2014). "Potentialities of data-driven nonparametric regression in urban signalized traffic flow forecasting." Journal of Transportation Engineering, Online.