A Knapsack Approach to Sensor-Mission Assignment with Uncertain Demands Diego Pizzocaro a , Matthew P. Johnson b , Hosam Rowaihy c , Stuart Chalmers d , Alun Preece a , Amotz Bar-Noy b , Thomas La Porta c a School of Computer Science, Cardiff University, UK; b Department of Computer Science, City University of New York, US; c Department of Computer Science and Engineering, Pennsylvania State University, US; d Department of Computing Science, University of Aberdeen, UK ABSTRACT A sensor network in the field is usually required to support multiple sensing tasks or missions to be accomplished simultaneously. Since missions might compete for the exclusive usage of the same sensing resource we need to assign individual sensors to missions. Missions are usually characterized by an uncertain demand for sensing resource capabilities. In this paper we model this assignment problem by introducing the Sensor Utility Maxi- mization (SUM) model, where each sensor-mission pair is associated with a utility offer. Moreover each mission is associated with a priority and with an uncertain utility demand. We also define the benefit or profit that a sensor can bring to a mission as the fraction of mission’s demand that the sensor is able to satisfy, scaled by the priority of the mission. The goal is to find a sensor assignment that maximizes the total profit, while ensuring that the total utility cumulated by each mission does not exceed its uncertain demand. SUM is NP-Complete and is a special case of the well known Generalized Assignment Problem (GAP), which groups many knapsack-style problems. We compare four algorithms: two previous algorithms for problems related to SUM, an improved implementation of a state-of-the-art pre-existing approximation algorithm for GAP, and a new greedy algorithm. Simulation results show that our greedy algorithm appears to offer the best trade-off between quality of solution and computation cost. Keywords: sensor mission assignment, knapsack problem, uncertain demands, sensor allocation, generalized assignment problem, utility maximization, greedy algorithm, sensor networks. 1. INTRODUCTION AND MOTIVATIONS The sensor-mission assignment problem is a hard problem that occurs when we have a sensor network and multiple competing missions that will make use of those sensors. A sensor network consists of a large number of sensing devices that are able to gather certain facets of information regarding their surroundings (e.g. sound, motion, video, etc.). Usually this network of sensors is already deployed in the field and is used to satisfy the information requirements of multiple sensing tasks or missions. Since missions might compete for the exclusive usage of the same sensing resource we need to assign individual sensors to missions. Consider the example in Figure 1 where two missions require to identify two different targets (“Target 1” and “Target 2”) that are located in nearby regions on the map: these two missions are competing for the exclusive control of a particular video sensor which could identify either target. The mission to which the video sensor will be assigned will decide to point the camera in a direction that is completely opposite to where the other mission would require it, therefore the sensor can be assigned to only one mission. In this paper we focus on the cases in which sensors cannot be shared by multiple mission, and we assume an homogeneous sensor network (e.g. only video sensors all with the same sensing capabilities). In each scenario a single sensor will have a different degree of utility for a certain mission, since it will offer to it different quality/quantity of information depending on some factors (such as distance from a certain point where the task related to the mission is located). Missions may have different degrees of importance (priority ) and different levels of required utility from the sensor network (demand ). Correspondence email address: D.Pizzocaro@cs.cf.ac.uk