Context-Driven Operational Decision Support in Megadisaster Response Operations Management [004-0159]

In recent years mankind experienced several "megadisasters" such as hurricane Katrine and tsunami in Indian Ocean in 2004. They showed that conventional tiered response to disasters does not work well in this case. Megadisasters require application of new technologies including context-aware interoperability of participants, on-the-fly decision support assistance and other. The paper describes a context-driven decision making schema based on the above technologies that originates from decision support in supply chain management. Ontologies and contexts are used to provide for interoperability at the level of semantics and current situation analysis; open services enable interoperability at the technological level. On-the-fly service generation makes possible to operatively solve problems based on constraint satisfaction technology. The paper is due to research carried out as part of CRDF partner project #RUM2-1554-ST-05 with US ONR and US AFRL, grant #05 01 00151 of the Russian Foundation for Basic Research, and project with Ford Motor Company. Introduction The number of annual natural and human-made disasters (including terrorism) has tripled since 1970. The strains on humanitarian organizations responding to emergencies showed that in 2004 256 million people were reported affected by disasters, while the annual average was 210 million (Humanitarian Logistics, 2005). Furthermore, in recent years we experienced several "megadisasters" such as hurricane Katrine and tsunami in Indian Ocean in 2004. Earth quakes and large scale acts of terrorism can also be related to this kind of disasters. The practice shows that one of the most difficult steps in responding for such situations is providing for the right relief supplies to the people in need at the right time. At the same time delivering of too much supplies or wrong supplies means loosing time and money. Therefore, humanitarian logistics standing for processes and systems involved in mobilizing people, resources, skills and knowledge to help vulnerable people affected by natural disasters and complex emergencies, is central for disaster relief (Scott and Rogova, 2004). Importance of intelligent systems in the area of humanitarian logistics has been widely recognized recently, particularly, in the context of decision making. Decision support systems for such problem domains have to meet a number of requirements including: • robustness: the system should continue to operate even if some of its elements stop; • sensitivity and adaptability: relationships between the system's elements organization's units has to be able to be easily and quickly readjusted in accordance with changes in the environment; • intensive knowledge / information exchange between the system's elements: knowledge management de facto has become essential for decision making processes. Among the various types of system architectures the networked distributed architecture best meets the above requirements (Scerri et al., 2000). Such systems link together independent