Dynamic Space Allocation Based on Internal Demand for Optimizing Release of Shared Parking

Abstract

The size of cities has been continuously increasing because of urbanization. The number of public and private transportation vehicles is rapidly increasing, thus resulting in traffic congestion, traffic accidents, and environmental pollution. Although major cities have undergone considerable development in terms of transportation infrastructure, problems caused by a high number of moving vehicles cannot be completely resolved through the expansion of streets and facilities. This paper proposes a solution for the parking problem in cities that entails a shared parking system. The primary concept of the proposed shared parking system is to release parking lots that are open to specific groups for public usage without overriding personal usage. Open-to-specific-groups parking lots consist of parking spaces provided for particular people, such as parking buildings at universities for teachers, staff, and students. The proposed shared parking system comprises four primary steps: collecting and preprocessing data by using an Internet of Things system, predicting internal demand by using a recurrent neural network algorithm, releasing several unoccupied parking lots based on prediction results, and continuously updating the real-time data to improve future internal usage prediction. Data collection and data forecasting are performed to ensure that the system does not override personal usage. This study applied several forecasting algorithms, including seasonal ARIMA, support vector regression, multilayer perceptron, convolutional neural network, long short-term memory recurrent neural network with a many-to-one structure, and long short-term memory recurrent neural network with a many-to-many structure. The proposed system was evaluated using artificial and real datasets. Results show that the recurrent neural network with the many-to-many structure generates the most accurate prediction. Furthermore, the proposed shared parking system was evaluated for some scenarios in which different numbers of parking spaces were released. Simulation results show that the proposed shared parking system can provide parking spaces for public usage without overriding personal usage. Moreover, this system can generate new income for parking management and/or parking lot owners.

Modelling and comparing two modes of sharing parking spots at residential area: Real‐time and fixed‐time allocation

“…③ Parking spots status matrix The meaning and value rules of the parking spots state matrix are the same as above. However, since the decision variables and the parking demand matrix are both changed from one-dimensional vectors to two-dimensional matrices, the calculation formula of the parking spots state variables is also converted accordingly, which are shown in formula (25) and formula (26).…”

“…To cope with the realtime updates of parking demands and shared parking spaces, achieve good allocation effect and high allocation speed, Ning et al designed a meta-heuristic algorithm Advanced and Adaptive Tabu Search (AATS) with an advanced initialization with multi-factor sequencing and an adaptive neighbourhood generation with bi-operator competition [24]. With the support of digital technology, shared transportation has developed greatly in recent years [25,26].…”

Real-time Allocation of Shared Parking Spaces Based on Deep Reinforcement Learning

“…In terms of parking space allocation, many scholars construct shared parking space allocation models with optimization objectives such as space utilization [9], social welfare [10], parking walking distance [11] and platform revenue [12], and solve them using multiple classes of intelligent algorithms, including genetic algorithms [13][14], ant colony algorithms [15] and particle swarm algorithms [16]. In addition, to ensure the robustness of parking space allocation, the literature [17] constructs a many-to-many structured recurrent neural network to achieve accurate prediction of parking space status; while the literature [18] constructs a time-of-day based parking probability function for random factors such as untimely parking.…”

Online parking space sharing system for residential areas based on intelligent algorithms

“…For instance, Zhang F. et al [9] study the optimal pricing strategy based on supply and demand to maximize the revenue or minimize the social cost. An D. et al [10] propose a novel destination privacy-preserving online parking-sharing incentive scheme, which solves the parking space-sharing problem while ensuring the privacy of the customer's parking destination location. This paper focuses on real application scenarios to provide parking space recommendations for parkers and path planning services to find parking spaces.…”