Accession Number : AD1051615


Title :   Using Markov Decision Processes with Heterogeneous Queueing Systems to Examine Military MEDEVAC Dispatching Policies


Descriptive Note : Technical Report,01 Sep 2015,31 Mar 2017


Corporate Author : Air Force Institute of Technology WPAFB United States


Personal Author(s) : Jenkins,Phillip R


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/1051615.pdf


Report Date : 23 Mar 2017


Pagination or Media Count : 113


Abstract : A major focus of the Military Health System is to provide efficient and timely medical evacuation (MEDEVAC) to battlefield casualties. The objective of this research is to determine how to optimally dispatch MEDEVAC units in response to requests to maximize system performance. A Markov decision process model is developed to examine the MEDEVAC dispatching problem. A representative planning scenario is utilized to investigate the differences between the optimal policy and three practitioner-friendly myopic baseline policies. Two computational experiments, a two-level, five-factor screening design and a subsequent three-level, three-factor full factorial design, are conducted to examine the impact of selected MEDEVAC problem features on the optimal policy and the system level performance measure. Results indicate that dispatching the closest available MEDEVAC unit is not always optimal. These results inform the development and implementation of MEDEVAC tactics, techniques, and procedures by military medical planners. Moreover, an open question exists concerning the best exact solution approach for solving Markov decision problems due to recent advances in performance by commercial linear programming(LP) solvers. An analysis of solution approaches for the MEDEVAC dispatching problem reveals that the policy iteration algorithm substantially outperforms the LP algorithms executed by CPLEX 12.6 in regards to computational eort.


Descriptors :   markov processes , decision making , military medicine , medical evacuation , systems engineering , urban areas , therapy , regression analysis , random variables , blood transfusions , hospitals , combat casualty care , dynamic programming


Subject Categories : Escape, Rescue and Survival
      Statistics and Probability


Distribution Statement : APPROVED FOR PUBLIC RELEASE