Journal of the Society of Disaster Information (한국재난정보학회 논문집)

The Korean Society of Disaster Information (한국재난정보학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Prediction of Traffic Volume on Highway by the Reference Day of Archived Data

이력자료 참조일수에 따른 고속도로 교통량 예측에 관한 연구

  • Received : 2018.06.14
  • Accepted : 2018.06.25
  • Published : 2018.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose: In Korea, traffic information is collected in real time as part of Intelligent Transportation System to enhance efficiency of road operation. However, traffic information based on real-time data is different from the traffic situation the driver will experience. Method: In this study, forecasts were made for future highway traffic by day and time period by adjusting the Archived data reference days to 3, 5 and 10 days based on existing traffic Archived data. Results: Fewer days of reference in the past showed smaller errors. The prediction of Monday based on five past histories showed greater errors than the 10 past histories, as the traffic flow on the sixth Monday of 2016 was somewhat different from the usual holiday. Conclution: This study shows that less of the reference days of the past history when estimating traffic volume, the more accurate the data of the traffic history of the event can be used on special days.

연구목적: 현재 국내에서는 지능형 교통체계(Intelligent transport system)의 일환으로 실시간 교통정보를 수집하여 도로운영의 효율성을 높이고 있다. 하지만 실시간 자료를 기반으로 한 교통정보는 운전자가 경험하게 될 교통상황과는 차이가 존재한다. 연구방법: 본 연구에서는 기존 교통량 이력자료 바탕으로 이력자료의 과거참조일수를 3일, 5일, 10일로 조정하여 요일별, 시간대별로 장래의 고속도로 교통량 예측을 수행하였다. 연구결과: 과거 참조일수가 적을수록 예측오차가 작게 나타나는 것을 알 수 있었다. 5번의 과거이력을 참조하여 월요일을 예측한 결과는 10번의 과거이력을 참조했을 때보다 오차가 크게 나타났는데 이는 분석대상 기간인 2016년의 6번째 월요일이 명절이기 때문에 평소의 월요일 교통흐름과는 다소 차이가 있었기 때문으로 판단된다. 결론: 본 연구를 통해 교통량예측 시 과거이력의 참조일수가 적을수록 비교적 오차가 적은 것을 알 수 있었으며 특수한 날에는 해당 이벤트의 교통량이력의 자료를 사용하면 보다 정확도 높은 결과를 나타낼 수 있을 것으로 판단된다.

Keywords

References

  1. Park, Y.H. (2001). A Study on Forecasting of road Traffic Volume by ARIMA Model. Journal of Korean Society of Transportation, 40, 303-308.
  2. Kim, H.J. Park, S.H. Jang, K.T.(2016). Short-term Traffic States Prediction Using k-Nearest Neighbor Algorithm: Focused on Urban Expressway in S eoul. Journal of Korean Society of Transportation, 34(2), 158-167. https://doi.org/10.7470/jkst.2016.34.2.158
  3. Lee, S.J. Kim, B.I. Kwon, H. (2004). The study of Estimation model for the short-term travel time prediction. Journal of Korea Institute of Intelligent Transport Systems, 3(1), 31-44.
  4. Lim, S.H. Lee, H.M. Park S.L. Heo, T.Y. (2013). A Study of Travel Time Prediction using K-Nearest Neighborhood Method, The Korean Journal of Applied Statistics, 26(5), 835-845. https://doi.org/10.5351/KJAS.2013.26.5.835
  5. Byeon, S.C. (2006). A study on forcasting short-term travel time considering the traffic characteristics. University of Seoul.
  6. Jang, S.C. et al.(2005). Traffic-Flow Forecasting using ARlMA, Neural Network and Judgment Adjustment. The Korean Operations Research and Management Science Society, 773-777.
  7. Chang, H.H. et al.. (2009). Development and Application of multi-Interval Volume Prediction Technique using Historical Data. Journal of Korean Society of Transportation, 61, 749-754.
  8. Yoo, S.L. Kim, J.S. Jeong, J.S. Jeong, J.Y. (2014). A Prediction of Marine Traffic Volume using Artificial Neural Network and Time Series Analysis. Jouranl of the Korean Society of Marine Environment & Safety, 133-134.
  9. Jang J.H. et al.(2004), Dynamic Travel Time Prediction Using AVI Data, Journal of Korean Society of Transportation. 22(7). pp.169-175
  10. Beak, S.K. Park, J.B. Chang, H.H. (2003). Multiple-interval freeway traffic flow forecasting with non-parametric regression considering seasonal traffic patterns. Journal of Korean Society of Transportation, 44, 1-6.