Free Parking Space Prediction and Reliability Analysis Based on Big Data Analysis

The number of free parking spaces (FPSs) is highly dynamic and stochastic, calling for a parking guidance model that enables the driver to find the right parking lot. This paper explores the distribution of FPSs number in parking lots, predicts the number of FPSs, and proposes a parking guidance model with a solving algorithm. Firstly, the number of FPSs from several parking lots was subjected to big data analysis, revealing that the hourly number of FPSs obey similar trends on different weekdays. On this basis, the data on the FPSs number of the parking lots were classified by hourly, weekly and holiday features. Whereas the FPSs number obeys the normal distribution, a parking guidance model was established with the most reliable path to forecast the number of FPSs. Then, the solving algorithm was proposed based on the reliability boundary. Finally, the effectiveness of the model and algorithm was verified through simulation. Compared with the actual data, the prediction accuracy of the model is more than 95%. The research results shed new light on the development of parking guidance systems.

[1]  Mohammed Abdul Wajeed,et al.  Image Based Tumor Cells Identification Using Convolutional Neural Network and Auto Encoders , 2019, Traitement du Signal.

[2]  Younghan Kim,et al.  A Novel Location-Centric IoT-Cloud Based On-Street Car Parking Violation Management System in Smart Cities , 2016, Sensors.

[3]  Martin Mauve,et al.  Predicting Parking Lot Occupancy in Vehicular Ad Hoc Networks , 2007, 2007 IEEE 65th Vehicular Technology Conference - VTC2007-Spring.

[4]  K Takada,et al.  Optimisation of parking guidance and information systems display configurations , 2001 .

[5]  José López Vicario,et al.  Autonomous Car Parking System through a Cooperative Vehicular Positioning Network , 2017, Sensors.

[6]  Miaomiao Wang,et al.  Hybrid particle swarm optimization and differential evolution algorithm for bi-level programming problem and its application to pricing and lot-sizing decisions , 2015, J. Intell. Manuf..

[7]  Jian Wang,et al.  Path planning and tracking for vehicle parallel parking based on preview BP neural network PID controller , 2015 .

[8]  Marc A. Rosen,et al.  Intelligent optimization to integrate a plug-in hybrid electric vehicle smart parking lot with renewable energy resources and enhance grid characteristics , 2014 .

[9]  Ram Rajagopal,et al.  Optimal dynamic parking pricing for morning commute considering expected cruising time , 2014 .

[10]  Klaus Moessner,et al.  An Arrival and Departure Time Predictor for Scheduling Communication in Opportunistic IoT , 2016, Sensors.

[11]  R. Y. Udaykumar,et al.  Stochastic Model of Electric Vehicle Parking Lot Occupancy in Vehicle-to-grid (V2G)☆ , 2016 .

[12]  Ho Gi Jung,et al.  Automatic free parking space detection by using motion stereo-based 3D reconstruction , 2010, Machine Vision and Applications.

[13]  David A. Cartes,et al.  An Intelligent Auction Scheme for Smart Grid Market Using a Hybrid Immune Algorithm , 2011, IEEE Transactions on Industrial Electronics.

[14]  Koji Zettsu,et al.  Space–time multiple regression model for grid-based population estimation in urban areas , 2016, Int. J. Geogr. Inf. Sci..

[15]  Ling Huang,et al.  Simultaneous Optimization of Vehicle Arrival Time and Signal Timings within a Connected Vehicle Environment , 2020, Sensors.

[16]  Soumya Banerjee,et al.  An intelligent hybrid scheme for optimizing parking space: A Tabu metaphor and rough set based approach , 2011 .

[17]  Jih-Fu Tu.  Parking lot guiding with IoT way , 2019 .

[18]  Günther Schmidt,et al.  Neural and fuzzy approaches to vision-based parking control , 1996 .

[19]  Yanfeng Ouyang,et al.  Parking Space Management via Dynamic Performance-Based Pricing , 2015, ArXiv.