Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

RI-PIENO -- Revised and Improved Petrol-Filling Itinerary Estimation aNd Optimization

Marco Savarese, Antonio De Blasi, Carmine Zaccagnino, Giacomo Salici, Silvia Cascianelli, Roberto Vezzani, Carlo Augusto Grazia

TL;DR

RI-PIENO addresses refueling itinerary optimization by integrating intra-vehicle data with external price and routing information in a dynamic framework. It extends PIENO with a Daily Trip Graph to capture habitual mobility, a Random Forest-based weekly mileage predictor, and a time-evolving DAG optimization that uses GraphHopper routing and fuel-cost trade-offs. The approach yields cost and time savings over previous methods and can reduce emissions by better aligning refueling with driver patterns. The framework supports deployment over V2X-enabled roadside infrastructure and scalable cloud/edge ecosystems, with tunable preferences via $K_1$ and $K_2$ that balance cost, time, and detours.

Abstract

Efficient energy provisioning is a fundamental requirement for modern transportation systems, making refueling path optimization a critical challenge. Existing solutions often focus either on inter-vehicle communication or intra-vehicle monitoring, leveraging Intelligent Transportation Systems, Digital Twins, and Software-Defined Internet of Vehicles with Cloud/Fog/Edge infrastructures. However, integrated frameworks that adapt dynamically to driver mobility patterns are still underdeveloped. Building on our previous PIENO framework, we present RI-PIENO (Revised and Improved Petrol-filling Itinerary Estimation aNd Optimization), a system that combines intra-vehicle sensor data with external geospatial and fuel price information, processed via IoT-enabled Cloud/Fog services. RI-PIENO models refueling as a dynamic, time-evolving directed acyclic graph that reflects both habitual daily trips and real-time vehicular inputs, transforming the system from a static recommendation tool into a continuously adaptive decision engine. We validate RI-PIENO in a daily-commute use case through realistic multi-driver, multi-week simulations, showing that it achieves significant cost savings and more efficient routing compared to previous approaches. The framework is designed to leverage emerging roadside infrastructure and V2X communication, supporting scalable deployment within next-generation IoT and vehicular networking ecosystems.

RI-PIENO -- Revised and Improved Petrol-Filling Itinerary Estimation aNd Optimization

TL;DR

RI-PIENO addresses refueling itinerary optimization by integrating intra-vehicle data with external price and routing information in a dynamic framework. It extends PIENO with a Daily Trip Graph to capture habitual mobility, a Random Forest-based weekly mileage predictor, and a time-evolving DAG optimization that uses GraphHopper routing and fuel-cost trade-offs. The approach yields cost and time savings over previous methods and can reduce emissions by better aligning refueling with driver patterns. The framework supports deployment over V2X-enabled roadside infrastructure and scalable cloud/edge ecosystems, with tunable preferences via and that balance cost, time, and detours.

Abstract

Efficient energy provisioning is a fundamental requirement for modern transportation systems, making refueling path optimization a critical challenge. Existing solutions often focus either on inter-vehicle communication or intra-vehicle monitoring, leveraging Intelligent Transportation Systems, Digital Twins, and Software-Defined Internet of Vehicles with Cloud/Fog/Edge infrastructures. However, integrated frameworks that adapt dynamically to driver mobility patterns are still underdeveloped. Building on our previous PIENO framework, we present RI-PIENO (Revised and Improved Petrol-filling Itinerary Estimation aNd Optimization), a system that combines intra-vehicle sensor data with external geospatial and fuel price information, processed via IoT-enabled Cloud/Fog services. RI-PIENO models refueling as a dynamic, time-evolving directed acyclic graph that reflects both habitual daily trips and real-time vehicular inputs, transforming the system from a static recommendation tool into a continuously adaptive decision engine. We validate RI-PIENO in a daily-commute use case through realistic multi-driver, multi-week simulations, showing that it achieves significant cost savings and more efficient routing compared to previous approaches. The framework is designed to leverage emerging roadside infrastructure and V2X communication, supporting scalable deployment within next-generation IoT and vehicular networking ecosystems.

Paper Structure

This paper contains 12 sections, 7 equations, 4 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Method
  3. Daily Trip Graph.
  4. POI Creator
  5. Flow Generator
  6. Weekly Mileage Prediction.
  7. Fuel Stop Optimization.
  8. Experiments and Results
  9. Weekly Mileage Prediction.
  10. Comparison with PIENO.
  11. Operation Modes.
  12. Conclusions

Figures (4)

  • Figure 1: Communication between RI-PIENO components.
  • Figure 2: Geographical map of all the clustered stops that a user has performed during the observation period, colored based on their frequency of visit that week. Note that only stops visited with at least Medium frequency are considered as POIs.
  • Figure 3: Daily Trip Graph obtained after the user's observation period, which reflects their typical weekly trips (i.e., between ordered POIs) day by day.
  • Figure 4: User path from a POI (home) to another POI (workplace) and Fuel Station stop (dark pink) proposed by the Baseline (left), PIENO (center), and RI-PIENO (right), with relative cost and time. The fuel stations in the area are in light pink.