The Journal of The Korea Institute of Intelligent Transport Systems (한국ITS학회 논문지)

The Korea Institute of Intelligent Transport Systems (한국ITS학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Traffic Prediction Using Hybrid Approach of Machine Learning and Simulation Techniques

기계학습과 시뮬레이션 기법을 융합한 교통 상태 예측 방법 개발 연구

  • 김예은 (한국과학기술원 건설 및 환경공학과) ;
  • 김성훈 (한국교통연구원 스마트시티교통연구센터) ;
  • 여화수 (한국과학기술원 건설 및 환경공학과)
  • Received : 2021.05.25
  • Accepted : 2021.08.03
  • Published : 2021.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

With the advent of big data, traffic prediction has been developed based on historical data analysis methods, but this method deteriorates prediction performance when a traffic incident that has not been observed occurs. This study proposes a method that can compensate for the reduction in traffic prediction accuracy in traffic incidents situations by hybrid approach of machine learning and traffic simulation. The blind spots of the data-driven method are revealed when data patterns that have not been observed in the past are recognized. In this study, we tried to solve the problem by reinforcing historical data using traffic simulation. The proposed method performs machine learning-based traffic prediction and periodically compares the prediction result with real time traffic data to determine whether an incident occurs. When an incident is recognized, prediction is performed using the synthetic traffic data generated through simulation. The method proposed in this study was tested on an actual road section, and as a result of the experiment, it was confirmed that the error in predicting traffic state in incident situations was significantly reduced. The proposed traffic prediction method is expected to become a cornerstone for the advancement of traffic prediction.

빅데이터의 등장과 더불어 교통 상태 예측은 과거 이력 데이터 분석 방식에 힘을 싣고 발전되어 왔으나, 이 방법은 관측된 적 없는 돌발 상황에 충분히 대응하지 못한다는 약점이 있다. 본 연구에서는 기계학습과 시뮬레이션 기법의 융합을 통해 돌발 상황 발생 시 교통 상태 예측 정확도 감소를 보완할 수 있는 예측 기법을 제시한다. 데이터 기반 방식의 맹점은 과거에 관측된 적 없는 데이터 패턴이 인지되었을 때 드러난다. 본 연구에서는 시뮬레이션을 이용하여 과거 이력 데이터를 보강하는 방법으로 문제를 해결하고자 하였다. 제시한 방법은 기계학습 기반의 교통 예측을 수행하고, 예측 결과와 실시간으로 수집되는 교통 데이터를 지속적으로 비교하여 돌발 상황 발생 여부를 판단한다. 돌발 상황이 인지되었을 시, 시뮬레이션을 통해 생성한 데이터베이스를 활용하여 예측을 수행한다. 본 연구에서 제시한 방법은 실제 도로 구간을 대상으로 검증되었으며, 검증 결과 돌발 상황에서의 교통 상태 예측 정확도 향상을 확인할 수 있었다. 본 연구에서 제시한 융합 교통 예측 방법은 향후 교통 예측 고도화에 이바지할 수 있을 것으로 전망된다.

Keywords

Acknowledgement

본 연구는 국토교통부 교통물류연구사업의 연구비지원(21TLRP-B146733-04)에 의해 수행되었습니다.

References

  1. Daganzo C. F.(1994), "The cell transmission model: A dynamic representation of highway traffic consistent with the hydrodynamic theory," Transportation Research Part B: Methodological, vol. 28, no. 4, pp.269-287. https://doi.org/10.1016/0191-2615(94)90002-7
  2. Kotsialos A. et al.(2002), "Traffic flow modeling of large-scale motorway networks using the macroscopic modeling tool METANET," IEEE Transactions on Intelligent Transportation Systems, vol. 3, no. 4, pp.282-292. https://doi.org/10.1109/TITS.2002.806804
  3. Kuchipudi C. M. and Chien S. I.(2003), "Development of a hybrid model for dynamic travel-time prediction," Transportation Research Record, vol. 1855, no. 1, pp.22-31. https://doi.org/10.3141/1855-03
  4. Oh S. et al.(2015), "Short-term travel-time prediction on highway: A review of the data-driven approach," Transport Reviews, vol. 35, no. 1, pp.4-32. https://doi.org/10.1080/01441647.2014.992496
  5. Pan B., Demiryurek U. and Shahabi C.(2021), "Utilizing real-world transportation data for accurate traffic prediction," 2012 IEEE 12th International Conference on Data Mining.
  6. Smith B., Billy L., Williams M. and Keith Oswald R.(2002), "Comparison of parametric and nonparametric models for traffic flow forecasting," Transportation Research Part C: Emerging Technologies, vol. 10, no. 4, pp.303-321. https://doi.org/10.1016/S0968-090X(02)00009-8
  7. Tak S. and Yeo H.(2016), "Development of Traffic Prediction and Optimal Traffic Control System for Highway based on Cell Transmission Model in Cloud Environment," Journal of Korea Institute of Intelligent Transport Systems, vol. 15, no. 4, pp.68-80.
  8. Tak S. et al.(2014), "Real-time travel time prediction using multi-level k-nearest neighbor algorithm and data fusion method," Computing in Civil and Building Engineering, pp.1861-1868.
  9. Tak S. et al.(2016), "Development of a Data Driven Framework for Real Time Travel Time Prediction," Computer Aided Civil and Infrastructure Engineering, vol. 31, no. 10, pp.777-793. https://doi.org/10.1111/mice.12205
  10. The Caltrans Performance Measurement System(PeMS), http://pems.dot.ca.gov, 2021.03.04.