Data to decision: Pushing Situational Information Needs to the Edge of the Network Jurgo Preden, Jaanus Kaugerand, Erki Suurjaak, Sergei Astapov, Leo Motus, Raido Pahtma Research Laboratory for Proactive Technologies Tallinn University of Technology Tallinn, Estonia jurgo.preden@ttu.ee Abstract—Obtaining a high level of situation awareness while maintaining optimal utilization of resources is becoming increasingly important, especially in the context of asymmetric warfare, where information superiority is crucial for maintaining the edge over the opponent. Obtaining an adequate level of situational information from an ISR system is dependent on sensor capabilities as well as the ability to cue the sensors appropriately based on the current information needs and the ability to utilize the collected data with suitable data processing methods. Applying the Data to Decision approach for managing the behavior of sensor systems facilitates optimal use of sensor assets while providing the required level of situational information. The approach presented in the paper combines the Data to Decision approach with the Fog Computing paradigm, where the computation is pushed to the edge of the network. This allows to take advantage of Big Data potentially generated by the sensor systems while keeping the resource requirements in terms of bandwidth manageable. We suggest a System of Systems approach for assembling the ISR system, where individual systems have a high level of autonomy and the computational resources to perform the necessary computation tasks. To facilitate a composition of a System of Systems of sensors for tactical applications the proactive middleware ProWare is applied. The paper presents the results on the implementation of a sensor solution that facilitates on-line sensor cueing and collaboration between sensors by building upon the Fog Computing paradigm and utilizing the Data to Decision concepts in the context of the European Defense Agency project IN4STARS. Keywords—ISR; situation awareness; middelware; System of Systems; data to decision; fog computing I. INTRODUCTION Good situation awareness at all levels in military operations is more critical than ever as in the asymmetry of operations we have to rely on information superiority to maintain an advantage. Modern technology offers us tools for collecting abundant amounts of sensor data with relatively reasonable costs. The challenge is aggregation of the data, abstraction of data to information and identifying the data sources needed for generating situational information on the area and topic that is needed. To deliver an operational solution, one must look at the entire information processing chain from the sensor sources to the information consumer not just at the operation of individual components. As we must strive to provide the best situation awareness possible to every warfighter, the information consumers may be diverse, starting from dismounted soldiers to commanding officers in a base, the ISR system must be able to cope with the needs of these diverse users. It has previously been suggested that for efficient system operation one should start looking at the communication chain from the information consumer side, identifying the situational information needs of the information consumer. As the information needs of individual users change over time depending on their location and the type of mission the need to accomplish the system must adapt to the changing needs of the user. The high availability of ground sensor assets and communication technologies presents the opportunity to use the sensor assets for very high granularity sensing, achieving high quality of data with a large number of sensing nodes with relatively mediocre capabilities. However, pursuing this approach presents many theoretical and practical challenges, such as bandwidth allocation, asset management and coordination of data flows. One possible approach to be used is to push the computation to the edge of the network, thereby reducing bandwidth requirements and computational capabilities needed at central locations. The concept of Data to Decision (D2D) is used to characterize decision making scenarios, where potentially the data sources are able to provide an abundant amount of information and where it is difficult to assemble the appropriate collection of data for rapid decision making [1]. D2D highlights the collection and fusion of actionable information to provide adequate situational information for assessing options, threats and consequences of decisions [2]. Although D2D concepts can be applied at all levels of an organization, these concepts are in particular applicable to individuals on the edge, who, with the aid of modern mobile information and communication platforms, can potentially have access to real-time actionable information. In addition to military applications, providing actionable information to operators in the field is also very critical in emergency response and law enforcement, where adequate situation awareness (based on real-time correct information) to aid rapid decision making is critical. Combining the D2D approach with the Fog Computing paradigm proposed by Cisco [11] and also previously as a distributed computing approach by the authors of the current The work presented in this paper was partially supported by the Estonian Ministry of Defence and the European Defense Agency project IN4STARS..