Parking Availability Prediction Using Arrival and Service Rates

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current navigation systems in vehicles do not effectively predict parking availability, leading to inefficient vehicle operation and increased time and fuel consumption while searching for parking.

Innovation Solution

A computer-implemented method using timestamps from vehicle processing systems to calculate arrival and service rates, determining the probability of parking availability, and controlling the vehicle to navigate to areas with high availability, employing Markov chain models and trace mining algorithms for real-time assessment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of time

If navigation systems provide basic route guidance without parking prediction, then the system complexity remains low, but vehicles experience increased time and fuel consumption while searching for parking

Engineering Contradiction:

Improvetime consumption while searching for parkingVSAvoidsystem complexity

Core Design Contradiction:

Loss of timeVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by calculating arrival rates and service rates in advance, predicting parking availability probabilities before the vehicle reaches the destination. This allows the navigation system to proactively identify and guide vehicles to parking areas with high availability, rather than reacting after the vehicle arrives and searches for parking.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms by continuously monitoring parking area data and vehicle data, updating arrival and service rates dynamically. The predicted parking availability probabilities are fed back to the navigation system, which adjusts route guidance accordingly, creating a closed-loop control system that improves parking search efficiency.

Inventive Principle:

Principle #23Feedback

2Measurement precision

If the system calculates detailed arrival and service rates using Markov chain models, then parking availability prediction accuracy improves, but computational requirements and processing time increase

Engineering Contradiction:

Improveparking availability prediction accuracyVSAvoidcomputational power requirement

Core Design Contradiction:

Measurement precisionVSPower

Solution Approach 1:

The system changes parameters by transforming complex parking dynamics into simplified arrival rates and service rates. These parameter transformations reduce the computational complexity of predicting parking availability while maintaining sufficient accuracy for navigation decision-making.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system introduces intermediary elements (arrival rate and service rate calculations) that mediate between raw parking area data and final parking availability predictions. This intermediary layer simplifies the computational model, making it more efficient while preserving predictive accuracy.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Loss of energy

If the navigation system guides vehicles to parking areas with high availability probability, then fuel consumption and wear and tear reduce, but the system requires real-time data processing and prediction capabilities

Engineering Contradiction:

Improvefuel consumptionVSAvoidreal-time data processing capability

Core Design Contradiction:

Loss of energyVSDifficulty of detecting and measuring

Solution Approach 1:

The system replaces mechanical trial-and-error parking search with an information-based prediction system. By substituting physical exploration (driving around looking for parking) with computational prediction (calculating availability probabilities), the system reduces fuel consumption and vehicle wear while providing guidance to high-availability parking areas.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11328596B2Parking prediction

Publication Date: 2022.05.10 GM GLOBAL TECHNOLOGY OPERATIONS LLC

AI summary

In one example implementation, a computer-implemented method includes receiving, by a host processing device, timestamps from a vehicle processing system of a target vehicle, the timestamps being determined based at least in part on parking area data for a target parking area and vehicle data for the target vehicle. The method further includes calculating, by the host processing device, an arrival rate and a service rate based on the timestamps. The method further includes calculating, by the host processing device, a probability of parking availability for the target parking area based at least in part on the arrival rate and the service rate. The method further includes controlling, by the host processing device, the vehicle based at least in part on the probability of parking availability for the target parking area.