PCruise: Reducing cruising miles for taxicab networks

In taxicab industry, a long standing challenge is how to reduce taxicab's mileage spent without a fare, i.e., cruising mile. The current solution for this challenge usually requires the participation of the passengers. To solve the issue without the passengers involved, in this paper, we propose a cruising system, pCruise, for taxicab drivers to maximize theirs profits by finding the optimal route to pick up a passenger, thus reducing the cruising mile. In pCruise, base on collected GPS records about other near taxicabs, a taxicab characterizes its cruising process with a cruising graph. When a taxicab becomes vacant and tries to find a passenger, cruising graph will provide the shortest cruising route with at least one expected available passengers for this taxicab. With the shortest cruising routes, taxicabs will significantly reduce theirs cruising miles. We evaluate pCruise based on a 7 days 10 GB real world GPS dataset from a city with more than 15,000 taxicabs. The evaluation results show that pCruise can assist taxicab drivers to reduce cruising miles by 41% on average.