SPO-VCS: An End-to-End Smart Predict-then-Optimize Framework with Alternating Differentiation Method for Relocation Problems in Large-Scale Vehicle Crowd Sensing

TL;DR

This paper introduces SPO-VCS, an end-to-end deep learning framework that optimizes vehicle relocation in large-scale urban sensing by integrating prediction and optimization, reducing errors and improving coverage.

Contribution

It develops a novel end-to-end SPO framework with an alternating differentiation method for vehicle relocation, directly minimizing task-specific divergence instead of prediction errors.

Findings

Effective in real-world taxi datasets in Hong Kong

Significantly improves sensing coverage and decision accuracy

Demonstrates the potential for intelligent transportation applications

Abstract

Ubiquitous mobile devices have catalyzed the development of vehicle crowd sensing (VCS). In particular, vehicle sensing systems show great potential in the flexible acquisition of spatio-temporal urban data through built-in sensors under diverse sensing scenarios. However, vehicle systems often exhibit biased coverage due to the heterogeneous nature of trip requests and routes. To achieve a high sensing coverage, a critical challenge lies in optimally relocating vehicles to minimize the divergence between vehicle distributions and target sensing distributions. Conventional approaches typically employ a two-stage predict-then-optimize (PTO) process: first predicting real-time vehicle distributions and subsequently generating an optimal relocation strategy based on the predictions. However, this approach can lead to suboptimal decision-making due to the propagation of errors from upstream prediction. To this end, we develop an end-to-end Smart Predict-then-Optimize (SPO) framework by integrating optimization into prediction within the deep learning architecture, and the entire framework is trained by minimizing the task-specific matching divergence rather than the upstream prediction error. Methodologically, we formulate the vehicle relocation problem by quadratic programming (QP) and incorporate a novel unrolling approach based on the Alternating Direction Method of Multipliers (ADMM) within the SPO framework to compute gradients of the QP layer, facilitating backpropagation and gradient-based optimization for end-to-end learning. The effectiveness of the proposed framework is validated by real-world taxi datasets in Hong Kong. Utilizing the alternating differentiation method, the general SPO framework presents a novel concept of addressing decision-making problems with uncertainty, demonstrating significant potential for advancing applications in intelligent transportation systems.