Safety and Conflict Resolution in Smart Cities

Learn more »

CitywithCityGuard
CitywithCityGuard

CityGuard:

A Watchdog for Safety-Aware Conflict Detection and Resolution in Smart Cities


CitywithCityGuard

Increasingly, cities are deploying smart services. IoT platforms are available to integrate smart services and city devices and improve city performance in the domains of transportation, emergency, environment, public safety, etc. Despite the increasing intelligence of smart services and the sophistication of platforms, the safety issues in smart cities are not addressed adequately, especially the safety issues arising from the integration of smart services. Therefore, CityGuard, a safety-aware watchdog architecture is developed. To the best of our knowledge, it is the first architecture that detects and resolves conflicts among actions of different services considering both safety and performance requirements. To start with, safety and performance requirements and a spectrum of conflicts are specified. Sophisticated models are used to analyze secondary effects, and detect device and environmental conflicts. A simulation based on New York City is used for the evaluation. The results show that CityGuard (i) identifies unsafe actions and thus helps to prevent the city from safety hazards, (ii) detects and resolves two major types of conflicts, i.e., device and environmental conflicts, and (iii) improves the overall city performance.

View details »





CityGuard Architecture


CityGuardStructure

CityResolver:

A Decision Support System for Conflict Resolution in Smart Cities


CitywithCityGuard

Resolution of conflicts across services in smart cities is an important yet challenging problem. We present CityResolver -- a decision support system for conflict resolution in smart cities. CityResolver uses an Integer Linear Programming based method to generate a small set of resolution options, and a Signal Temporal Logic based verification approach to compute these resolution options' impact on city performance. The trade-offs between resolution options are shown in a dashboard to support decision makers in selecting the best resolution. We demonstrate the effectiveness of CityResolver by comparing the performance with two baselines: a smart city without conflict resolution, and CityGuard which uses a priority rule-based conflict resolution. Experimental results show that CityResolver can reduce the number of requirement violations and improve the city performance significantly.

View details »





Violation Degree and Dashboard


violationdegree dashboard

Demos


Demo 1: Normal City without any service

A simulation for a normal city without any smart service is shown below. It is a part of Manhattan, New York City, NY. Traffic data is generated based on the real data from New York city. In the simulation, the yellow objectives are normal vehicles (e.g. cars, buses, trucks), and the red objectives are emergency vehicles. There are traffic signals in each intersection. The red lane is a blocked lane. As shown in the video, there are traffic congestions, blocked emergency vehicles and high air pollution emission when there is no smart service.



explain

Demo 2: Comparison between without and with smart traffic service

Performances of a smart city without and with a smart traffic service are compared in the below videos. The initial states are the same for the two simulations. As it is shown in the videos, the city with the smart traffic service has a much better traffic performance. However, as shown in the zoom-in pictures below, pedestrians are blocked in the intersection because of the smart traffic service, i.e. the secondary effect of this smart service.

City without Smart Traffic Service


City with Smart Traffic Service

CityGuardStructure CityGuardStructure

Demo 3: Comparison between without and with smart air pollution service

Performances of a smart city without and with a smart air pollution service are compared in the below videos. The initial states are the same for the two simulations. The red lane indicates the level of air pollutions. It is shown that the level of the air pollution is controlled with the smart air pollution service, however, traffic congestions are caused in the meanwhile.

City without Air Pollution Service


City with Air Pollution Service


Demo 4: Smart city without CityGuard

A smart city with 5 smart services are deployed in the simulation below. (S1: Traffic Congestion Service; S2: Pedestrian Service; S3: Air Pollution Service; S4: Noise Service; S5: Emergency Service). Without CityGuard, the performance of services is affected by the conflicts among them. It has a worse performance than the simulation with single service running. As a result, high traffic congestion, blocked emergency vehicles and air pollution are caused.



Demo 5: Smart city with CityGuard

A smart city with 5 smart services and CityGuard are deployed in the simulation below. (S1: Traffic Congestion Service; S2: Pedestrian Service; S3: Air Pollution Service; S4: Noise Service; S5: Emergency Service). Comparing with the previous simulation, it is shown that with CityGuard, (i) conflicts among services are detected and resolved, (ii) traffic has a much better performance, (iii) emergency vehicles have a shorter travel time, and most importantly, (iv) fewer conflicts happened when the previous conflicts are resolved by CityGuard. Therefore, overall city performance is improved by CityGuard.



Publications

  • Ma, Meiyi, S. Masud Preum, W. Tärneberg, M. Ahmed, M. Ruiters, and J. Stankovic. Detection of Runtime Conflicts among Services in Smart Cities, Smart Computing (SMARTCOMP), 2016 IEEE International Conference on. IEEE, 2016. [pdf] [link]

  • Ma, Meiyi, Sarah Masud Preum, and John A. Stankovic. "CityGuard: A Watchdog for Safety-Aware Conflict Detection in Smart Cities." Proceedings of the Second International Conference on Internet-of-Things Design and Implementation. ACM, 2017.[pdf] [link] [Slides]

  • Ma, Meiyi, John A. Stankovic and Lu Feng. "CityResolver: A desicion support system for conflict resolution in smart cities" The 9th ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS). ACM/IEEE, 2018.
    [pdf] [link] [Slides]
  • Ma, Meiyi, John A. Stankovic, and Lu Feng. "Runtime Monitoring of Safety and Performance Requirements in Smart Cities." Proceedings of the 1st ACM Workshop on the Internet of Safe Things. ACM, 2017.[pdf] [link] [Slides]

  • Ma, Meiyi, Preum, S. M., Stankovic, J. A. (2017, April). Demo Abstract: Simulating Conflict Detection in Heterogeneous Services of a Smart City. In Internet-of-Things Design and Implementation (IoTDI), 2017 IEEE/ACM Second International Conference on (pp. 275-276). IEEE.[link]



People

John A. Stankovic (PI)

BP America Professor, Director, Link Lab

Department of Computer Science

University of Virginia


Meiyi Ma

Ph.D. Student

Department of Computer Science

University of Virginia


Sarah Masud Preum

Ph.D. Student

Department of Computer Science

University of Virginia


Mohsin Ahmed

Ph.D. Student

Department of Computer Science

University of Virginia