Ali Haghani

Zhongxiang Wang, Ali Shafahi, Ali Haghani

Safely serving the school transportation demand with the minimum number of buses is one of the highest financial goals of school transportation directors. To achieve that objective, a good and efficient way to solve the routing and scheduling problem is required. Due to the growth of the computing power, the spotlight has been shed on solving the combined problem of the school bus routing and scheduling problem. We show that an integrated multi-school bus routing and scheduling can be formulated with the help of trip compatibility. A novel decomposition algorithm is proposed to solve the integrated model. The merit of this integrated model and the decomposition method is that with the consideration of the trip compatibility, the interrelationship between the routing and scheduling sub-problems will not be lost in the process of decomposition. Results show the proposed decomposed problem could provide the solutions using the same number of buses as the integrated model in much shorter time (as little as 0.6%) and that the proposed method can save up to 26% number of buses from existing research.

Kiana Roshan Zamir, Ali Shafahi, Ali Haghani

Bike sharing systems' popularity has consistently been rising during the past years. Managing and maintaining these emerging systems are indispensable parts of these systems. Visualizing the current operations can assist in getting a better grasp on the performance of the system. In this paper, a data mining approach is used to identify and visualize some important factors related to bike-share operations and management. To consolidate the data, we cluster stations that have a similar pickup and drop-off profiles during weekdays and weekends. We provide the temporal profile of the center of each cluster which can be used as a simple and practical approach for approximating the number of pickups and drop-offs of the stations. We also define two indices based on stations' shortages and surpluses that reflect the degree of balancing aid a station needs. These indices can help stakeholders improve the quality of the bike-share user experience in at-least two ways. It can act as a complement to balancing optimization efforts, and it can identify stations that need expansion. We mine the District of Columbia's regional bike-share data and discuss the findings of this data set. We examine the bike-share system during different quarters of the year and during both peak and non-peak hours. Findings reflect that on weekdays most of the pickups and drop-offs happen during the morning and evening peaks whereas on weekends pickups and drop-offs are spread out throughout the day. We also show that throughout the day, more than 40% of the stations are relatively self-balanced. Not worrying about these stations during ordinary days can allow the balancing efforts to focus on a fewer stations and therefore potentially improve the efficiency of the balancing optimization models.

Hyoshin Park, Ali Shafahi, Ali Haghani

Location of depots and routing of emergency response units are assumed to be interdependent in the incident management system. System costs will be excessive if delay regarding routing decisions is ignored when locating response units. This paper presents an integrated method to solve location and routing problem of emergency response units on freeways. The principle is to begin with a location phase for managing initial incidents and to progress through a routing phase for managing the stochastic occurrence of next incidents. Previous models used the frequency of independent incidents and ignored scenarios in which two incidents occurred within proximal regions and intervals. The proposed analytical model relaxes the structural assumptions of Poisson process (independent increments) and incorporates evolution of primary and secondary incident probabilities over time. The proposed mathematical model overcomes several limiting assumptions of the previous models, such as no waiting-time and returning rule to original depot. Our stochastic programming method hedges well against a wide range of scenarios in which probabilities of a sequence of incidents are assigned. The initial non-linear stochastic model is linearized. As a long-term strategy, the model incorporates flexibility in choosing the locations. The temporal locations flexible to a future policy-change are compared with current practice that locates all units in one permanent depot.