서울 수도권 지하철 승객이 인터넷으로 구매한 채소 등의 신선 식품을 퇴근하는 도중에 이동 경로상의 지하철역 구내의 서비스 시설물에서 배달받는다고 가정하면, 제기되는 문제는 어떤 지하철역에 서비스 시설물을 설치하면 얼마나 많은승객들이 이용하는 가를 파악하는 것이다. 이러한 문제는 픽업 문제로 알려져 있고, 픽업 문제를 풀려면 교통 흐름을 설명하는 교통 네트워크가 있어야 되고 각 교통 흐름의 이동 경로도 알 수 있어야 된다. 서울 수도권 교통카드 시스템의 교통카드 트랜잭션 데이터베이스로부터 지하철 승객의 출발역에서 도착역 까지 움직이는 이동 경로인 승객 흐름을 구할 수 있으므로, 서울 수도권 지하철 교통 시스템에서 픽업 문제는 승객 흐름을 최대한 많이 포착하는 서비스 시설물들을 설치할지하철역들을 선정하는 것이다.
본 논문에서 서울 수도권 지하철 시스템과 지하철 승객들의 흐름을 픽업 문제의 모델에 맞추어 수식화하였고, 이를 기반으로 하여 지하철 승객들의 흐름을 기종점 통행 행렬을 만들어 단계별로 가장 많은 통과 승객수를 갖는 픽업 역을 계산해내는 빠른 휴리스틱 알고리즘을 제안하였다. 대용량 교통 네트워크와 교통 흐름에 해당되는 약 400여 개의 지하철역을 가진 서울 수도권 지하철 네트워크와 약 500만 명의 지하철 교통카드 트랜잭션들을 입력으로 하여 제안된 알고리즘으로 선정된 픽업 역들을 빠른 시간 내에 얻었고, 그 중에서 상위 10개 픽업 역들을 지하철 안내 지도에 표시하여 설명하였다. 그리고, 그 결과가 거의 최적해와 같음을 추가 실험을 통하여 검증하였다.
Some subway passengers may want to have their fresh vegetables purchased through internet at a service facility within the subway station of the Metropolitan Seoul subway system on the way to home, which raises further questions about which stations are chosen to locate service facilities and how many passengers can use the facilities. This problem is well known as the pickup problem, and it can be solved on a traffic network with traffic flows which should be identified from origin stations to destination stations. Since flows of the subway passengers can be found from the smart card transaction database of the Metropolitan Seoul smart card system, the pickup problem in the Metropolitan Seoul subway system is to select subway stations for the service facilities such that captured passenger flows are maximized. In this paper, we have formulated a model of the pickup problem on the Metropolitan Seoul subway system with subway passenger flows, and have proposed a fast heuristic algorithm to select pickup stations which can capture the most passenger flows in each step from an origin-destination matrix which represents the passenger flows. We have applied the heuristic algorithm to select the pickup stations from a large volume of traffic network, the Metropolitan Seoul subway system, with about 400 subway stations and five millions passenger transactions daily. We have obtained not only the experimental results in fast response time, but also displayed the top 10 pickup stations in a subway guide map. In addition, we have shown that the resulting solution is nearly optimal by a few more supplementary experiments.
Some subway passengers may want to have their fresh vegetables purchased through internet at a service facility within the subway station of the Metropolitan Seoul subway system on the way to home, which raises further questions about which stations are chosen to locate service facilities and how many passengers can use the facilities. This problem is well known as the pickup problem, and it can be solved on a traffic network with traffic flows which should be identified from origin stations to destination stations. Since flows of the subway passengers can be found from the smart card transaction database of the Metropolitan Seoul smart card system, the pickup problem in the Metropolitan Seoul subway system is to select subway stations for the service facilities such that captured passenger flows are maximized. In this paper, we have formulated a model of the pickup problem on the Metropolitan Seoul subway system with subway passenger flows, and have proposed a fast heuristic algorithm to select pickup stations which can capture the most passenger flows in each step from an origin-destination matrix which represents the passenger flows. We have applied the heuristic algorithm to select the pickup stations from a large volume of traffic network, the Metropolitan Seoul subway system, with about 400 subway stations and five millions passenger transactions daily. We have obtained not only the experimental results in fast response time, but also displayed the top 10 pickup stations in a subway guide map. In addition, we have shown that the resulting solution is nearly optimal by a few more supplementary experiments.
