Heuristic Optimization of Electrical Energy Systems: Refined Metrics to Compare the Solutions
This work addresses the uncontrolled proliferation of heuristic solvers in electrical energy systems by improving comparison metrics, though it is incremental as it builds on existing concepts.
The paper tackles the problem of weak comparisons among heuristic optimization solvers in electrical energy systems by proposing refined metrics based on first-order stochastic dominance, which are demonstrated to make solver comparisons more robust through illustrative examples.
Many optimization problems admit a number of local optima, among which there is the global optimum. For these problems, various heuristic optimization methods have been proposed. Comparing the results of these solvers requires the definition of suitable metrics. In the electrical energy systems literature, simple metrics such as best value obtained, the mean value, the median or the standard deviation of the solutions are still used. However, the comparisons carried out with these metrics are rather weak, and on these bases a somehow uncontrolled proliferation of heuristic solvers is taking place. This paper addresses the overall issue of understanding the reasons of this proliferation, showing a conceptual scheme that indicates how the assessment of the best solver may result in the unlimited formulation of new solvers. Moreover, this paper shows how the use of more refined metrics defined to compare the optimization result, associated with the definition of appropriate benchmarks, may make the comparisons among the solvers more robust. The proposed metrics are based on the concept of first-order stochastic dominance and are defined for the cases in which: (i) the globally optimal solution can be found (for testing purposes); and (ii) the number of possible solutions is so large that practically it cannot be guaranteed that the global optimum has been found. Illustrative examples are provided for a typical problem in the electrical energy systems area-distribution network reconfiguration. The conceptual results obtained are generally valid to compare the results of other optimization problems.