Distributed modeling of smart parking system using LSTM with stochastic periodic predictions

  • Theodoros AnagnostopoulosEmail author
  • Petr Fedchenkov
  • Nikos Tsotsolas
  • Klimis Ntalianis
  • Arkady Zaslavsky
  • Ioannis Salmon
Original Article


Parking in contemporary cities is a time- and fuel-consuming process. It affects daily stress levels of drivers and citizens. To design the future cities, parking process should be handled efficiently to improve drivers’ time comfort and fuel economy toward a green smart city (SC) ecosystem. In this paper, we propose to model smart parking (SP) with multiagent system (MAS) using long short-term memory (LSTM) neural network. Our model outperforms similar approaches as evidenced from the presented results using an online dataset from the SC of Aarhus, Denmark. We use LSTM for stochastic prediction based on periodic data provided by parking sensors. A SP provides such data on daily basis over a short period of time in the SC. We evaluate the proposed MAS with the prediction accuracy metric and compare it with other approaches in the literature. The proposed system achieves higher prediction accuracy per daily basis than the compared approaches due to our stochastic periodic prediction design and input to the proposed MAS and LSTM model. In addition, LSTM is used more efficiently under the proposed architecture of MAS, which enables online scaling thanks to dynamic and distributed nature of MAS.


Smart parking Cyber-physical systems Stochastic prediction Multiagent modeling LSTM 



The part of this work has been carried out in the scope of the project bIoTope which is co-funded by the European Commission under the Horizon-2020 program, Contract Number H2020-ICT-2015/688203 – bIoTope.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.


  1. 1.
    Fazio M, Paone M, Puliafito A, Villari M (2012) Heterogeneous sensors become homogenous things in smart cities. In: IEEE 6th international conference on innovative mobile and internet services in ubiquitous computing (IMIS), pp 775–780Google Scholar
  2. 2.
    Centre of Regional Science (2007) Smart cities. Ranking of European Medium-Sized Cities. Vienna University of Technology, Accessed 21 Oct 2019
  3. 3.
  4. 4.
    Yaseen ZM, Sulaiman SO, Deo RC, Chau KW (2019) An enhanced extreme learning machine model for river flow forecasting: state-of-the-art, practical applications in water resource engineering area and future research direction. J Hydrol 569:387–408CrossRefGoogle Scholar
  5. 5.
    Najafi B, Ardabili SF, Shamshirband S, Chau KW, Radzuk T (2018) Application of ANNs, ANFIS and RSM to estimating and optimizing the parameters that affect the yield and cost of biodiesel production. Eng Appl Comput Fluid Mech 12(1):611–624Google Scholar
  6. 6.
    Chuntian C, Chau KW (2002) Three-person multi-objective conflict decision in reservoir flood control. Eur J Oper Res 142:625–631CrossRefGoogle Scholar
  7. 7.
    Fotovatikhah F, Herrera M, Shamshirband S, Chau KW, Faizollahzadeh Ardabili S, Piran MJ (2018) Survey of computational intelligence as basis to big flood management: challenges, research directions and future work. Eng Appl Comput Fluid Mech 12(1):411–437Google Scholar
  8. 8.
    Wang WC, Chau KW, Qiu L, Chen YB (2015) Improving forecasting accuracy of medium and long-term runoff using artificial neural network based on EEMD decomposition. Environ Res 139:46–54CrossRefGoogle Scholar
  9. 9.
    Moazenzadeh R, Mohammadi B, Shamshirband S, Chau KW (2018) Coupling a firefly algorithm with support vector regression to predict evaporation in northern Iran. Eng Appl Comput Fluid Mech 12(1):584–597Google Scholar
  10. 10.
    The project - FastPrk2., H2020-SMEINST-2-2016-2017, Grant Agreement No 726607
  11. 11.
    Shao W, Zhang Y, Guo B, Qin K, Chan J, Salim FD (2018) Parking availability prediction with long short term memory model. In: Proceedings of the international conference on green, pervasive, and cloud computing, pp 124–113CrossRefGoogle Scholar
  12. 12.
    Tilahun SL, Di Marzo Serugendo G (2017) Cooperative multiagent system for parking availability prediction based on time varying dynamic markov chains. J Adv Transp. 15:17. CrossRefGoogle Scholar
  13. 13.
    de Castro LF, Borges AP, Alves GV, Grossa CP (2018) Developing a smart parking solution based on a holonic multiagent system using JaCaMo framework. In: Proceedings of the 12th workshop-school on agents, environments, and applications, Fortaleza - CE, BrazilGoogle Scholar
  14. 14.
    Dargaye H, Gobin-Rahimbux B, Sahib-Kaudeer NG (2019) Agent-based modelling for a smart parking system for mauritius. Information systems design and intelligent applications. Springer, Berlin, pp 367–377CrossRefGoogle Scholar
  15. 15.
    Boudali I, Ouada MB (2017) Smart parking reservation system based on distributed multicriteria approach. Appl Artif Intell 31:5–6CrossRefGoogle Scholar
  16. 16.
    Alkharabsheh ARA (2018) An intelligent cooperative multi-agents based parking system: design and implementation. J Theor Appl Inf Technol 96(10):2804–2815Google Scholar
  17. 17.
    Mudassar L, Byun Y (2018) Customer prediction on parking logs using recurrent neural network. In: SNPD 2018: software engineering, artificial intelligence, networking and parallel/distributed computing, pp. 123–136Google Scholar
  18. 18.
    Rong Y, Xu Z, Yan R, Ma X (2018) Du-parking: spatio-temporal big data tells you real-time parking availability. In: Proceedings the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pp. 646–654Google Scholar
  19. 19.
    Zheng Y, Rajasegarar S, Leckie C (2015) Parking availability prediction for sensor-enabled car parks in smart cities. In: Proceedings of the 10th IEEE international conference on intelligent sensors, sensor networks and information processing (ISSNIP)Google Scholar
  20. 20.
    Xiao J, Lou Y, Frisby J (2018) How likely am I to find parking? A practical model-based framework for predicting parking availability. Transp Res Part B Methodol 112:19–39CrossRefGoogle Scholar
  21. 21.
    Rajabioun T, Ioannou PA (2015) On-street and off-street parking availability prediction using multivariate spatiotemporal models. IEEE Trans Intell Transp Syst 16(5):2913CrossRefGoogle Scholar
  22. 22.
    Camero A, Toutouh J, Stolfi DH, Alba E (2018) Evolutionary deep learning for car park occupancy prediction in smart cities. In: Proceedings of the LION 12: learning and intelligent optimization, Kalamata, Greece, pp 386−401Google Scholar
  23. 23.
    Qiu J, Tian J, Chen H, Lu X (2018) Prediction method of parking space based on genetic algorithm and RNN. In: PCM 2018: advances in Multimedia Information Processing, pp. 865–876CrossRefGoogle Scholar
  24. 24.
    Vlahogianni EI, Kepaptsoglou K, Tsetsos V, Karlaftis MG (2016) A real-time parking prediction system for smart cities. J Intell Transp Syst 20(2):192–204CrossRefGoogle Scholar
  25. 25.
    Alajali W, Wen S, Zhou W (2017) On-street car parking prediction in smart city: a multi-source data analysis in sensor-cloud environment. In: SpaCCS 2017: security, privacy, and anonymity in computation, communication, and storage, pp. 641–652CrossRefGoogle Scholar
  26. 26.
    Mei Z, Zhang W, Zhang L, Wang D (2019) Real-time multistep prediction of public parking spaces based on Fourier transform–least squares support vector regression. J Intell Transp Syst. CrossRefGoogle Scholar
  27. 27.
    Fang X, Xiang R, Peng L, Li H, Sun Y (2018) SAW: a hybrid prediction model for parking occupancy under the environment of lacking real-time data. In: Proceedings of IECON 2018—44th annual conference of the IEEE industrial electronics societyGoogle Scholar
  28. 28.
    Monteiro FV, Ioannou P (2018) On-street parking prediction using real-time data. In: Proceedings of the 21st international conference on intelligent transportation systems (ITSC), Maui, HI, USA, Nov 2018Google Scholar
  29. 29.
    Xiao J, Lou Y (2018) A smartphone-based parking guidance system with predictive parking availability information. In: 2018 Transportation research annual meetingGoogle Scholar
  30. 30.
    Lu EH-C, Liao C-H (2018) A parking occupancy prediction approach based on spatial and temporal analysis. In: ACIIDS 2018: intelligent information and database systems, Feb 2018, pp 500–509Google Scholar
  31. 31.
    Stolfi DH, Alba E, Yao X (2017) Predicting car park occupancy rates in smart cities. In: Smart-CT 2017: smart cities, May 2017, pp 107–117Google Scholar
  32. 32.
    Lenka RK, Barik RK, Das NK, Agarwal K, Mohanty D, Vipsita S (2017) PSPS: an IoT based predictive smart parking system. In: Proceedings of the 4th IEEE Uttar Pradesh section international conference on electrical, computer and electronics (UPCON), Oct 2017Google Scholar
  33. 33.
    Bock F, Di Martino S, Origlia A (2017) A 2-step approach to improve data-driven parking availability predictions. In: Proceedings of the 10th ACM SIGSPATIAL workshop on computational transportation science, Nov 2017, pp 13–18Google Scholar
  34. 34.
    Sun M, Li Z, Peng L, Li H, Fang X (2018) FLOPS: an efficient and high-precision prediction on available parking spaces in a long time-span. In: Proceedings of the 21st international conference on intelligent transportation systems (ITSC), Maui, HI, USA, Nov 2018Google Scholar
  35. 35.
    Li J, Li J, Zhang H (2018) Deep learning based parking prediction on cloud platform. In: Proceedings of the 4th international conference on big data computing and communications (BIGCOM), Chicago, IL, USA, Aug 2018Google Scholar
  36. 36.
    Venkanna U, Sharma S, Katiyar B, Prashanth Y (2018) A wireless sensor node based efficient parking slot availability detection system for smart cities. In: Proceedings of the recent advances on engineering, technology and computational sciences (RAETCS), Allahabad, India, Feb 2018Google Scholar
  37. 37.
    Fan J, Hu Q, Tang Z (2018) Predicting vacant parking space availability: an SVR method with fruit fly optimisation. IET Intell Transp Syst 12(10):1414–1420CrossRefGoogle Scholar
  38. 38.
    Ionita A, Pomp A, Cochez M, Meisen T, Decker S (2018) Where to park?: Predicting free parking spots in unmonitored city areas. In Proceedings of the 8th international conference on web intelligence, mining and semantics, Novi Sad, Serbia, June 2018Google Scholar
  39. 39.
    Tiedemann T, Vögele T, Krell MM, Metzen JH, Kirchner F (2015) Concept of a data thread based parking space occupancy prediction in a berlin pilot region. In: Proceedings of the AAAI workshop: artificial intelligence for transportation: advice, interactivity and actor modeling, twenty-ninth AAAI conference on artificial intelligence, Austin, Texas, USA, Jan 2015Google Scholar
  40. 40.
    Lan T, Kang Q, An J, Yan W, Wang L (2013) Sitting and sizing of aggregator controlled park for plug-in hybrid electric vehicle based on particle swarm optimization. Neural Comput Appl 22(2):249–257CrossRefGoogle Scholar
  41. 41.
    Tilahun SL, Serugendo GDM (2017) Cooperative multiagent system for parking availability prediction based on time varying dynamic markov chains. J Adv Transp 2017:1–14CrossRefGoogle Scholar
  42. 42.
    Bura H, Lin N, Liu K (2018) An edge based smart parking solution using camera networks and deep learning. In: Proceedings of the IEEE conference on cognitive computing (ICCC), pp 17–24Google Scholar
  43. 43.
    Mudaliar S, Agali S, Mudhol S, Jambotkar C (2019) IoT based smart car parking system. Int J Sci Adv Res Technol 5(1):270–272Google Scholar
  44. 44.
    Pham TN, Tsai MF, Deng DJ (2015) A cloud-based smart-parking system based on Internet-of-Things technologies. IEEE Access 3:1581–1591CrossRefGoogle Scholar
  45. 45.
    Khanna A, Anand R (2016) IoT based smart parking system. In: The proceedings of the international conference on Internet of Things and applications (IOTA), pp 266–270Google Scholar
  46. 46.
    Fedchenkov P, Anagnostopoulos T, Zaslavsky A, Ntalianis K, Sosunova I, Sadov O (2018) An artificial intelligence based forecasting in smart cities parking with IoT. In: LNCS, vol 11118. Springer, pp 33–40, September 2018Google Scholar
  47. 47.
  48. 48.
  49. 49.
    Dietterich TG (1998) Approximate statistical tests for comparing supervised classification leraning algorithms. Neural Comput 10(7):1895–1923CrossRefGoogle Scholar
  50. 50.
    Chung J, Gulcehre C, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. ArXiv, abs/1412.3555Google Scholar
  51. 51.
    Colace F, Loia V, Tomasiello S (2019) Revising recurrent neural networks form a granular perspective. Appl Soft Comput J 82:1–9CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Business AdministrationUniversity of West AtticaAthensGreece
  2. 2.Department of Infocommunication TechnologiesITMO UniversitySt. PetersburgRussia
  3. 3.School of Information TechnologyDeakin UniversityMelbourneAustralia

Personalised recommendations