Optimization knowledge base: an open database for algorithm and problem characteristics and optimization results

Andreas Scheibenpflug, Stefan Wagner, Erik Pitzer, Michael Affenzeller

Abstract: This paper describes the optimization knowledge base (OKB), a database for storing information about algorithms and problems. The optimization knowledge base allows to save results of algorithm executions as well as problem-specific information of fitness landscape analyses. This database can be queried and gives researchers a tool for gaining a better understanding of problems and algorithms and their behavior. Therefore the OKB supports parameter tuning and keeping track of tested algorithm and parameter settings as well as their results. Furthermore, the OKB and fitness landscape analysis can be used to not only explain the behavior of algorithms but to calculate similarities between problem instances and algorithms. Based on similarities and already captured knowledge, parameter settings can be extracted that could work well for new problem instances. Additionally, the OKB can be used to publish results of experiments for a broader audience, which advocates transparency of scientific work in the area of metaheuristics.