Electronic Warfare in the Information Age
Electronic Warfare in the Information Age
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
A fast and elitist multiobjective genetic algorithm: NSGA-II
IEEE Transactions on Evolutionary Computation
Proceedings of the 11th Annual conference on Genetic and evolutionary computation
Spanning the pareto front of a counter radar detection problem
Proceedings of the 13th annual conference on Genetic and evolutionary computation
| Hi-index | 0.00 |
The next generation of advanced self-protection jammers is expected to deliver effective and energy efficient jamming against modern air tracking radars. However, optimizing such experimental jammers is a challenging task. In this paper the novelty and applicability of using genetic algorithms (GA) for developing advanced digital radio frequency memory jammer techniques against radars employing the constant false alarm rate detection algorithm are demonstrated. It is shown how GA can handle the large and complex solution space of the problem, finding a Pareto front in the problem domain of jammer transmitting power versus detectability, producing new jamming techniques and fresh insight into the complex radar-jammer dynamics. As a main result, it is demonstrated how GA is capable of producing effective multi-resistant jamming techniques. This is an important jamming property when operating against uncertain radar detection algorithms in real world scenarios. Furthermore, single- and multi-resistant jamming techniques are shown to handle noisy environments, and the important issue of jamming robustness against varying target radar cross section is addressed. The energy efficiency of GA jamming techniques is investigated by comparing the efficiency of more conventional noise jamming techniques.