Abstract—This paper reports the results of applying discrete event simulation on firefighting operations in the State of Kuwait. The objective was reduce response times to reach fires in all districts to below five minutes. The Simulation of output runs were analyzed using ANOVA. The results were validated at 95% confidence level. Simulation turned to be an excellent tool for testing a major change without disturbing firefighting operations. I. INTRODUCTION In the United States of 2006, one person died in a fire accident approximately every 162 minutes and one person was injured every thirty two minutes [1]. Urban fire causes significant threat to the loss of lives and property. In the United States, building fires were responsible for over 3,000 deaths, 15,000 injuries and $9.2 billion in fire-related property damage in 2005 [2]. A common performance measure is the response time. It is a critical factor in the effectiveness of the firefighting services since well-set response time standards can minimize the risk to people and property loss. Response time is defined as the time from the receipt of a call of a fire incident to the arrival of the firefighting service to the incident site. Many Research efforts as in Huang et al. [3], Indriasari et al. [4], Erden and Coskun [5], and Wei and Juncheng [6], who conducted studies on optimal siting of Fire Stations in Singapore, South Jakarta, Istanbul and China, respectively, agreed on a response time of five minutes or less for firefighting services. Tzeng and Chen [7], on the other hand, who conducted their study in Taipei's international airport in Taiwan, aimed for a response time of no longer than three minutes for aircraft fire accidents. While Yang et al. [8] established response time ranges based on the fire risk category, ranging from four to five minutes for high risk fires to ten to twenty minutes for low risk ones, in the Derbyshire region, UK. Murray and Tong [9] conducted their study in North Boston, USA, aimed for a response time of six minutes, broken down as follows: one minutes for the dispatcher to handle the call of service, one minutes for a fire company to get into their gear and depart, and four minutes of travel time. Determining the proper response time is critical in order to Manuscript received November 5, 2012; revised January 30, 2013. This work was supported in part by the Kuwait University Research Administration for supporting the research titled Fire Station Location Analysis in a Metropolitan Area under the grant number EI02/11. The authors are with the Department of Industrial & Management Systems Engineering, Kuwait University, Safat 13060 Kuwait (e-mail: e.aleisa@ ku.edu.kw, mehmet@kuniv.edu.kw). Modeling of Firefighting Operations through Discrete Event Simulation Esra Aleisa and Mehmet Savsar International Journal of Computer Theory and Engineering, Vol. 5, No. 4, August 2013 678 DOI: 10.7763/IJCTE.2013.V5.774 Index Terms—Firefighting, response time, simulation ANOVA. beat flashovers. Flashovers is defined as the point in time at which a structure fire is fully developed, so people are not likely to survive and property is unsalvageable [9]. A simulation model is developed to study the firefighting system in detail and to determine the effects of implementing different changes on response time. Discrete event simulation was used due to its ability to incorporate many of the constraints commonly found in large-scale systems [10]-[12]. The simulation model was constructed using Arena software. The results of the system were validated at a 95% confidence level. This means that the simulation model is valid representation of reality, which qualifies it to be used as medium for diagnostics and improvements. II. LITERATURE REVIEW Most work on improving fire stations operations aim to reduce response time. One of the earliest work in this area was conducted on fire station location involved simulation [13]. In his research Hogg [13] discussed some methods of optimal siting of fire stations were he aimed to minimize the sum of the financial loss from fire and the cost of providing the fire brigade. Another early research conducted by Monarchi et al. [14] have also used simulation to analyze alternative deployment strategies for urban fire suppression systems. Fitzsimmons [15] have used computer models for disseminating emergency ambulances to fire stations in an attempt to reduce response time. His research was the first to consider the urgency of response time reduction. Hendrick and Plane [16] have analyzed the deployment strategies for Denver’s fire department. They used a simulation model to evaluate different fire companies’ configurations. An extension to the aforementioned research was presented by Plane and Hendrick [17]. Halpern et al.[18] analyzed the effect of manning level in one and two-family residential fires in the city of Calgary, Canada. They established a relationship between manning levels and time needed to extinguish the fire by using an activity network approach.Badri et al. [19] have considered multiple objectives that incorporate both travel times and travel distances from stations to demand sites. They also considered political criteria in their model and used a programming modeling technique to solve the problem. Tzeng and Chen [20] developed a location model based on a fuzzy multi‐objective approach to help in determining the optimal number and sites of fire stations at an international airport. Due to the combinatorial complexity of their formulation they employed a genetic algorithm (GA) to determine the optimal number and sites of fire stations in Taipei’s international airport. Later, Patricio Pedernera et al. [21] developed a dynamic programming model which