RsRS: Ridesharing Recommendation System Based
on Social Networks to Improve the User’s QoE
Abstract : Ridesharing is a mobility concept in which a trip is shared by a vehicle’s driver and one or more passengers called riders. Ridesharing is considered as a more environmentally friendly alternative to single driver commutes in pollution-creating vehicles on overcrowded streets. In this paper, we present the core of a new strategy of the ridesharing system, making it more flexible and competitive than the recurring system. More precisely, we allow the driver and the rider to meet each other at an intermediate starting location and to separate at another intermediate ending location not necessarily their origins and destinations, respectively. This allows to reduce both the driver’s detour and the total travel cost. The term “A priori approach” means that the driver sets the sharing cost rate on the common path with rider in advance. Exact and heuristic approaches to identify meeting locations, while minimizing the total travel cost of both driver and rider are proposed. Finally, we analyze their empirical performance on a set of real road networks consisting of up to 3,5 million nodes and 8,7 million edges. Our experimental results show that our heuristics provide efficient performances within short CPU times and improves the recurring ridesharing approach in terms of cost-savings.
Dynamic ride sharing systems, such as Uber, 1Lyft2andDidi Chuxing, 3have become popular transport alternatives in cities across the world. These systems offer real time plat-forms to both private car owners and the passengers for sharing rides in similar directions. They usually dispatch a taxi (ora private car) that is not fully occupied to a ride request, and schedule specified pick-up and drop-off locations and time sequences for the sharing ride, with the objective of finding the best match between the drivers and passengers. These sharing services, however, only provide sub-optimal sharing schedule due to the unpredictable en-route sharing requests. The on-board passengers may encounter unexpected route sharing requests and thus could suffer unpleasant sharing experience with extended travel time during their trips. By contrast, another type of taxi-sharing systems, such asBandwagon, 4also spring up. These systems are designed to shrink taxi lines by instantly matching the passengers waiting in line with similar directions and letting them share rides.
? You won’t have much freedom or flexibility with your schedule and activities.
? You won’t have much privacy.
? The designated driver is responsible for his passengers.
Before providing a framework for ridesharing services, we need to define how users plan their shared rides in advance by looking at currently available examples. We outline the needs that the service has to satisfy, the main features of the service itself, and the perceived value of it, both from the passenger and the driver’s point of view. A scenario is depicted in where there are three different locations that are connected and easily reachable by car. Passengers and drivers must know in advance all the details of the trip, and both parties agree on factors such as the time and the location of departure and arrival.
? Reduce traffic congestion.
? Reduce the number of trips a vehicle makes.
? Reduce the emissions that come from vehicles.
? ou don’t have to make cash payment.
? You are able to track where the driver is at any given moment.
? You are notified as the driver gets close to where you are.
|