Novel Smoke-Aware Individual Evacuation and Congestion-Aware Group Evacuation Algorithms in IoT-Enabled Multi-Story Multi-Exit Buildings

Abstract

Because of toxic gases and fast propagation speed, smoke causes the major injuries and deaths than burns in the fire. Deploying IoT enabled smoke sensors not only help to sense, collect, and transmit the smoke data to the control station, but also enable a dynamic and real-time evacuation approach to increase the evacuation success probability. In this paper, two smoke-aware evacuation approaches are proposed. The individual evacuation mathematical model and the associated SIEP algorithm are first devised to identify a fastest smoke toxic safe evacuation path for an evacuee. Next, the group evacuation mathematical model and the associated SGEP algorithm are devised to evacuate as many evacuees as possible in considering the smoke toxicity and flow congestion along the evacuation routes. SGEP circumvents the congestion problem by scheduling the evacuation sequence according to evacuee’s accumulated smoke toxicity value, where higher accumulated smoke toxicity value has higher evacuation priority to prevent incapacitation at evacuation. The FDS simulations based on the real layout of Taipei 101 mall are performed to compare the evacuation success probability between SIEP and SGEP at methane fire and PVC fire. The simulation results show that smoke from PVC fire is more toxic than that of methane fire. In addition, enabling sprinklers can reduce the percentage of toxic nodes up to 41% at methane fire and up to 10% at PCV fire, as compared to not enabling them. These results indicate that it is more challenging to evacuate at PVC fire than at methane fire. The simulation results in SGEP and SIEP justify the above conclusions where the success evacuation probability differences between methane fire and PVC fire are up to 39% (i.e., 100% and 61%) and 52.5% (i.e., 82.5% and 30%) for SGEP and SIEP, respectively. The simulation results also show that SGEP outperforms SIEP in terms of evacuation success probability at all simulation settings, especially when large number of evacuees are to be evacuated. At methane fire, the largest evacuation success probability difference between SGEP and SIEP is 68.1% at 1000 evacuees, 0.3 FED threshold and without sprinklers. At PVC fire, the largest difference is 50% at 1000 evacuees, 0.5 FED threshold and with sprinklers. These significant differences in evacuation success probability come from the evacuation congestion in SIEP. The evacuation scheduling approach based on accumulated smoke toxicity policy enables SGEP to circumvent the evacuation congestion, and to get better evacuation success probability. Besides identifying safe evacuation route and evacuation scheduling policy during congestion to evacuate more evacuees, another contribution of this paper is to identify the critical percentage of toxic nodes for safe fire evacuation and rescue operations.

Keywords

• Individual evacuation
• group evacuation
• evacuation congestion
• smoke sensors
• fire evacuation planning and optimization