A Two-Phase Multiobjective Local Search for the Device Allocation in the Distributed Integrated Modular Avionics

In the distributed integrated modular avionics (DIMA), it is desirable to assign the DIMA devices to the installation locations of the aircraft for obtaining the optimal quality and cost, subject to the resource and safety constraints. Currently, the routine device assignments in DIMA are conducted manually or by experience, which becomes more and more difficult with the increasing number of devices. Especially, in the face of large-scale device assignment problems (DAPs), the manual allocation will become an almost impossible task. In this paper, a bi-objective safety-constraint device assignment model in DIMA is formulated with the integer encoding for better scalability. A two-phase multiobjective local search (2PMOLS) is proposed for addressing it. In the first phase of 2PMOLS, the fast convergence of the population toward the Pareto front (PF) is achieved by the weighted sum approach. In the second phase, Pareto local search is conducted on the solutions delivered in the first phase for the extension of the PF approximation. 2PMOLS is compared with three decomposition-based approaches and one domination-based approach on DAPs of different sizes in the experimental studies. The experimental results show that 2PMOLS outperforms all the compared algorithms, in terms of both the convergence and diversity. It has also been demonstrated that the solution obtained by 2PMOLS is better in terms of both objectives (mass and ship set costs), compared with the solution designed by the domain expert. The experimental results show that 2PMOLS performs increasingly better with the increase of the problem size, compared with other algorithms, which indicates it has better scalability.