A Multiobjective Optimization Approach to Obtain Decision Thresholds for Distributed Detection in Wireless Sensor Networks

Abstract

For distributed detection in a wireless sensor network, sensors arrive at decisions about a specific event that are then sent to a central fusion center that makes global inference about the event. For such systems, the determination of the decision thresholds for local sensors is an essential task. In this paper, we study the distributed detection problem and evaluate the sensor thresholds by formulating and solving a multiobjective optimization problem, where the objectives are to minimize the probability of error and the total energy consumption of the network. The problem is investigated and solved for two types of fusion schemes: 1) parallel decision fusion and 2) serial decision fusion. The Pareto optimal solutions are obtained using two different multiobjective optimization techniques. The normal boundary intersection (NBI) method converts the multiobjective problem into a number of single objective-constrained subproblems, where each subproblem can be solved with appropriate optimization methods and nondominating sorting genetic algorithm-II (NSGA-II), which is a multiobjective evolutionary algorithm. In our simulations, NBI yielded better and evenly distributed Pareto optimal solutions in a shorter time as compared with NSGA-II. The simulation results show that, instead of only minimizing the probability of error, multiobjective optimization provides a number of design alternatives, which achieve significant energy savings at the cost of slightly increasing the best achievable decision error probability. The simulation results also show that the parallel fusion model achieves better error probability, but the serial fusion model is more efficient in terms of energy consumption.

A Learning Automata-Based Multiobjective Hyper-Heuristic

“…One of the main advantages of MOEAs is that they are population based techniques, capable of obtaining a set of trade-off solutions with reasonable quality even in a single run [1]. Even though 'optimality' can not be guaranteed, empirical results indicate the success of MOEAs on a variety of problem domains, including planning and scheduling ( [2], [3]), data mining [4], and circuits and communications [5]. There are different types of MOEAs, each utilising different algorithmic components during the search process and so perform differently.…”

Multi-objective routing optimization using evolutionary algorithms

“…Hence, efficient routing techniques should be designed for ensuring that the data packets propagate in an 'optimal' manner in terms of several metrics, such as energy consumption, delay, delay jitter, bandwidth and packet loss ratio. In conventional multi-hop networks, only one of the desired objectives is optimized, whereas other objectives are assumed to be constraints of the problem [1]. Nonetheless, in some practical applications finding multiple solutions, each of which is optimal in terms of a single metric may be better than finding a single meritorious solution, which strikes a trade-off amongst several conflicting factors.…”

“…In certain applications Multi-objective Optimization (MO) algorithms that provide several optimal solutions may be preferred, since these methods do not necessarily require user-defined objective weights. Furthermore, the drawback of focusing on a single design objective, whilst ignoring other important objectives may be circumvented by multi-objective optimization techniques [1]. We can consider all the objectives simultaneously and generate a set of optimal solutions, which are known as the Pareto solutions [3] of multi-objective problems.…”

“…For example, Masazade et al [1] studied the distributed detection problem and the choice of appropriate sensor thresholds, which was also solved with the aid of MO. Minimizing both the error probability and energy consumption of the network were the two objectives the authors focused on.…”

Cluster-based Routing Performance Optimization Constraint of Energy, Delay and Connectivity Metrics in Wireless Sensor Network

“…In [17], the energy minimization and coverage maximization with connectivity are optimized simultaneously. In [18], global probability of error and energy consumption have been optimized, in their work, the optimization is investigated and solved for two types of fusion schemes which contain parallel decision and serial decision fusion. Mingdong Xu and Henry Leung proposed a cross-layer optimization of wireless sensor networks under the constraints of total energy consumption and transmission delay [19].…”