The design of radio telescope array configurations using multiobjective optimization: Imaging performance versus cable length

The next generation of radio telescope interferometric arrays requires careful design of the array configuration to optimize the performance of the overall system. We have developed a framework, based on a genetic algorithm, for rapid exploration and optimization of the objective space pertaining to multiple objectives. We have evaluated a large space of possible designs for 27, 60, 100, and 160 station arrays. The 27 station optimizations can be compared to the well-known VLA case, and the larger array designs apply to arrays currently under design such as LOFAR, ATA, and the SKA. In the initial implementation of our framework we evaluate designs with respect to two metrics, array imaging performance and the length of cable necessary to connect the stations. Imaging performance is measured by the degree to which the sampling of the u-upsilon plane is uniform. For the larger arrays we find that well-known geometric designs perform well and occupy the Pareto front of optimum solutions. For the 27 element case we find designs, combining features of the well-known designs, that are more optimal as measured by these two metrics. The results obtained by the multiobjective genetic optimization are corroborated by simulated annealing, which also reveals the role of entropy in array optimization. Our framework is general, and may be applied to other design goals and issues, such as particular schemes for sampling the u-upsilon plane, array robustness, and phased deployment of arrays.