유전자 알고리즘에 기반한 개인용 이동기기 재배치 기법의 설계 = Design of a Personal Mobility Relocation Scheme based on Genetic Algorithms

다국어 초록 (Multilingual Abstract)

This paper presents a design and evaluates the performance of a resource relocation scheme for personal mobility sharing services, mainly targeting at kickboards and scooters. To employ suboptimal genetic algorithms, a relocation schedule is first encoded into a chromosome consisting of consecutive pairs of (overstock, understock) stations. Next, a fitness function is defined by the relocation distance and the number of relocation operations, while those are dependent on how many relocation pairs can be merged. The evolution step keeps enhancing this fitness from the randomly chosen population. Third, we tailor the legacy genetic operations such as selection, reproduction, evaluation, and invalid chromosome fix to adjust the unmatching number of locations. The experiment result, obtained via a prototype implementation with the Java language, shows that the proposed scheme can reduce the relocation distance by up to 33.3%p for the given parameter setting on given geographical distribution of kickboards and demand behaviors.

국문 초록 (Abstract)

본 논문은 킥보드와 같은 개인용 이동기기 공유 서비스에서 기기들의 효율적인 재배치 기법을 설계하고 그 성능을 평가한다. 부분 최적 기법인 유전자 알고리즘을 적용하기 위해 하나의 재배치 스케줄을 (과보유지역, 부족지역) 쌍의 연속인 염색체로 설정하고 주어진 병합 이동 차수를 고려하여 이동거리 혹은 최대 재배치 수에 따른 적합도 함수를 정의한다. 임의로 선택된 인구 집합에 대해 적합도가 향상되도록 진화를 반복하는데, 선택, 교배, 평가 등의 유전자 연산을 이 염색체에 적합하도록 변경한다. 또 교배 연산의 결과 발생할 수 있는 유효하지 않은 염색체를 보정하는 기능을 추가한다. Java 언어로 구현된 프로토타입을 이용한 실험 결과, 제안된 기법은 실험에서 주어진 이동기기들의 지역적 분포와 수요에 있어서 재배치 거리를 최대 33.3 %p까지 감소시킨다.

참고문헌 (Reference)

1 이정훈 ; 박경린, "유전자 알고리즘에 기반한 이동식 주차단속 차량의 운행 스케줄 결정" 대한공간정보학회 29 (29): 45-52, 2021

2 Atac, S., "Vehicle sharing systems: A review and a holistic management framework" 10 : 10-, 2021

3 Sun, S., "Subgraph matching with effective matching order and indexing" 34 (34): 491-505, 2022

4 Shimizu, T., "Sensor-independent pedestrian detection for personal mobility vehicles in walking space using dataset generated by simulation" 1788-1795, 2020

5 Castanho, M., "SMART-C: Developing a ‘Smart City’ assessment system using cognitive mapping and the choquet integral" 68 (68): 562-573, 2021

6 Li, X., "Reducing car-sharing relocation cost through non-parametric density estimation and stochastic programming" 1-6, 2020

7 Tamura, K., "Performance comparison of typical binary-integer encodings in an Ising machine" 9 : 81032-81039, 2021

8 Di Febbraro, A., "One-way car-sharing profit maximization by means of user-based vehicle relocation" 20 (20): 628-641, 2019

9 Rabl, V., "Making smart transportation work in smart cities" 1-6, 2020

10 Magaia, N., "Industrial Internet-of-Things security enhanced with deep learning approaches for smart cities" 8 (8): 6393-6405, 2021

11 Greco, M., "Heuristic function to solve the generalized covering TSP with artificial intelligence search" 1-8, 2020

12 Ekárt, A., "Genetic programming with transfer learning for urban traffic modeling and prediction" 1-8, 2020

13 Fernandez, C., "Fleet management optimization in car rental industry: Decision aid models for logistics improvement" 168-172, 2020

14 Jorge, D., "Comparing optimal relocation operations with simulated relocation policies in one-way carsharing systems" 15 (15): 1667-1675, 2014

15 Paiva, S., "Analysis of mobility changes caused by COVID-19 in a context of moderate restrictions using data collected by mobile devices" 10 : 8906-8915, 2022

16 Li, L., "An agent-based simulation for shared automated electric vehicles with vehicle relocation" 3308-3313, 2019

17 Kypriadis, D., "An Efficient scheme for dynamic car relocation in free-floating car-sharing systems" 527-530, 2019

18 Zhang, R., "Ambulance deployment with relocation through robust optimization" 16 (16): 138-147, 2019

19 Toledo, A., "A hyper-heuristic for the orienteering problem with hotel selection" 8 : 1303-1313, 2020

20 Chai, H., "A hierarchical blockchain-enabled federated learning algorithm for knowledge sharing in internet of vehicles" 22 (22): 3975-3986, 2021