IoT Performance for Maritime Passenger Evacuation

TL;DR

The paper addresses the challenge of ensuring timely passenger evacuation on maritime vessels when IoT/ICT performance degrades guidance quality. It adopts the Adaptive Navigation Strategy (ANT) with guaranteed exit deadlines and implements a hybrid AnyLogic/Python simulation on the Yangtze Gold 7 to evaluate technology-induced delays. Key findings show that information lag and network congestion degrade evacuation performance, with average times increasing by about $1.5\times$ at $PoD=1$ relative to the ideal. The work highlights the need for robust, potentially decentralized ITS designs to maintain safe evacuation under adverse ICT conditions.

Abstract

The safe and swift evacuation of passengers from Maritime Vessels, requires an effective Internet of Things(IoT) as well as an information and communication technology(ICT) infrastructure. However, during emergencies, delays in IoT and ICT systems that guide evacuees, can impair the evacuation process. This paper presents explores the impact of the key IoT and ICT elements. The methodology builds upon the deadline-aware adaptive navigation strategy (ANT), which offers the path segment that minimizes the evacuation time for each evacuee at each decision instant. The simulations on a real cruise ship configuration, show that delays in the delivery of correct instructions to evacuees can significantly hinder the effectiveness of the evacuation. Our findings stress the need to design robust and computationally fast IoT and ICT systems to support the evacuation of passengers in ships, and underscores the key role played by the IoT in the success of passenger evacuation and safety.

Figures (5)

• Figure 1: Schematic description of the layout for the Yangtze Gold 7 Cruise ship over its three passenger floors (second, third, and fourth). This layout is used for simulating the effects that are studied in this paper, i.e., the delays in communicating the guidance information to the evacuees. Here (a) is the layout of the physical space of the second, third, and fourth floors, and (b) is the evacuation graph model of the physical space.
• Figure 2: The average evacuation time, in seconds, from all $346$ nodes to the exit (above), as a function of $PoD$ (x-axis), and (below) the performance ratio in average evacuation time as compared to the ideal case of $PoD=0$. Averages are over all nodes for $100$ distinct independent simulations, with the standard deviation (the black bars) for the evacuation time.
• Figure 3: The average evacuation time in seconds, taken by passengers in cabins to the exit (left), as a function of $PoD$ (x-axis), and (right) the performance ratio in average evacuation time as compared to the ideal case of $PoD=0$. Averages are taken over all passengers starting from cabins for $100$ distinct independent simulations, with the standard deviation (the black bars) for the evacuation time.
• Figure 4: The average evacuation time in seconds, taken of passengers in the restaurant to the exit (left), as a function of $PoD$ (x-axis), and (right) the performance ratio in average evacuation time as compared to the ideal case of $PoD=0$. Averages are taken over all passengers in the restaurant for $100$ distinct independent simulations, with the standard deviation (the black bars) for the evacuation time.
• Figure 5: The average evacuation time in seconds, with a $95\%$ confidence interval, taken by different numbers of passengers where half of them originate in the cabins, while the other half start from the restaurant (above), and (below) the performance ratio in average evacuation time as compared to the ideal case w$PoD=0$.