Indonesian Journal of Electrical Engineering and Computer Science Vol. 31, No. 2, August 2023, pp. 1164~1170 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v31.i2.pp1164-1170  1164 Journal homepage: http://ijeecs.iaescore.com Efficient automated car parking system based modified internet of spatial things in smart cities Noor Alsaedi, Ali Sadeq Abdulhadi Jalal Department of Information and Communication Engineering, College of Information Engineering, Al-Nahrain University, Baghdad, Iraq Article Info ABSTRACT Article history: Received Dec 11, 2022 Revised Mar 20, 2023 Accepted Apr 2, 2023 The technological advances of smart cities have been progressively increasing to improve the quality of life to humans, especially in urban mobility. Parking appears to be a major issue, with residents needing to find a suitable parking space among many parking areas, resulting in time and fuel waste as well as environmental pollution. We propose in this paper a new automated system model that integrates reinforcement learning (RL), Q-learning, and image processing algorithms based on modified internet of spatial things (IoST) architecture to optimize automated parking in smart cities. For demonstrating the efficiency of the proposed model, iFogSim simulation is used to reduce network usage and latency. Moreover, it deploys heterogeneous devices in multi layers and different scenarios. The experimental results show that the suggested system for automated car parking in fog-based placement-IoST network is feasible and effective. It minimizes latency and the total network usage compared to the cloud-based placement of the implemented system. Keywords: Cloud-based placement Fog-based placement Internet of spatial things Load balancing Q-learning This is an open access article under the CC BY-SA license. Corresponding Author: Noor Alsaedi Department of Information and Communication Engineering, College of Information Engineering Al-Nahrain University, Baghdad, Iraq Email: nlight1124@gmail.com 1. INTRODUCTION The development of smart cities has emerged as a trend worldwide. It utilizes information and communication technologies to raise the citizens' quality of life and their interactions with the government. Therefore, one of the main issues with urban development is the amount of traffic and urban mobility. They encounter numerous obstacles to sustainable mobility due to the city's transportation, traffic, and parking systems' capacity issues, as well as the rising demand for parking systems [1]. The internet of things (IoT) is used to reduce the traffic problem and vehicle parking congestion. IoT is a rapidly evolving technology that allows devices to connect and exchange data with one another. It comprises various "devices" with internet connectivity and networking capabilities [2]. Researchers have created a number of IoT-based online and remote monitoring systems as in [3], which help the driver to find available parking space. It suggested a technique that was deployed online using a website application, helping users locate free parking spaces. Since the system had an ultrasonic sensor, it served as a detector that transmitted information to the microcontroller for updating into the cloud server for access to the data. Using the IoT, researchers in [4] proposed a smart parking system using field-programmable gate arrays (FPGA) depending on emergency status. Singh and Vaidya [5] proposed an automated vehicle parking system to identify the license plate number to manage vehicle billing and parking by using image processing. While authors used one of the fundamental machine learning methods, kernel nearest neighbors (KNN), to recognize the license plate [6]. Introduced a smart vehicle parking system using fog computing in IoT environments [7], [8].