Abstract One of the most important problems in directional sensor networks is coverage problem. The coverage can be measured in two ways: positional or temporal. In temporal coverage, the directional sensors rotate periodically round themselves in a repetitive process. Thus, in each time slot, those targets that are positioned within the sensor nodes radius receive their desired coverage. In this model, if a target is left uncovered, it is said that the target has remained in darkness. The main task defined for the temporal coverage model is the minimization of the total dark time for all the targets in the network. This problem has been solved by greedy‐based algorithms in last studies. Greedy‐based algorithms are able to solve the temporal coverage problem in real time. Remember that the performance of greedy algorithms is extremely dependent on the closeness of optimal solution and initial candidates. For this reason, greedy algorithms may obtain local minima due to heuristic search. As far as we know meta‐heuristic algorithms have not been used in past researches to solve such problems. For solving this problem, in this paper two algorithms were developed, GA‐based and hybridized model comprising genetic algorithms and tabu search. A new model was suggested for the chromosome in genetic algorithm. To evaluate the performance of the developed algorithms, they were compared with randomized scenario and greedy‐based algorithm presented in last studies. For better comparison, several parameters, including total dark time, number of sensors, number of targets, sector angle, sensing range were taken into account. The results obtained from the comparison of the algorithms indicated that the developed algorithms are effective in solving the temporal coverage problem in terms of minimizing the total dark time of the targets.

Abstract The target coverage problem is considered as one of the major issues in directional sensor networks (DSNs), which is caused by the nature of these networks, including their limited angle of view. Due to the fault tolerance characteristic of some coverage applications, the target coverage is required to be performed using multiple sensors. This challenge is discussed in the literature under the title of k ‐coverage problem. Under certain conditions, the number of sensors may suffer some changes due to various factors such as power depletion of the sensors, sensors' malfunctioning, and harshness of the environment. This can result in unavailability of adequate sensors for providing k ‐coverage for all targets. The network suffering from such problem is referred to as under‐provisioned network. This paper was aimed at studying such networks by adopting the network conditions to the real environments. To solve this problem, the present paper proposes a hybrid model integrating the genetic algorithm (GA) and Tabu search (TS). The proposed algorithm generally aimed to identify a subset of sensors with appropriate working directions in order to provide a balanced coverage for all the targets available in the network. In order to evaluate the performance of the algorithm several experiments were conducted and the results have been compared with greedy and learning automat‐abased algorithms. . The results of the experiments show the superiority of the algorithm.

Abstract Today, a directional sensor network is a popular environment for solving the target coverage problem. Monitoring all targets in a DSN is a crucial challenge to scholars working in this field of study. Adjusting the angle and range of the sensors can be an efficient technique for improving the network performance. In this way, the network has the most extended lifespan and, at the same time, spends the least time to find the best cover set. In this method, each sensor dynamically adjusts its own sensing angle in order to find the targets by choosing the best range. The present study proposed a continuous learning automata‐based method to choose the optimum sensing angle for the sensors in a DSN. Then, to evaluate the proposed algorithm performance, its results were compared to those of a conventional automata‐based method whose algorithm worked based on continuous automata. The comparative analysis confirmed the superiority of the proposed method over the conventional automata‐based method regarding the extension of the network lifespan.