Harmony search is a metaheuristic optimization algorithm that models the improvisation process of jazz musicians searching for a pleasing harmony. The algorithm keeps a fixed size collection of candidate solutions called the harmony memory, and generates each new candidate by drawing, for every variable, either an existing value from the harmony memory, itself possibly adjusted by a small random pitch change, or an entirely new random value, in rough analogy to a musician choosing a note from memory or improvising a new one; a newly generated candidate that improves on the worst solution currently held in the harmony memory replaces it, so the collection improves over successive iterations, drawing on every stored solution to guide the search rather than only a pair of parent solutions the way a genetic algorithm does. Zong Woo Geem, Joong Hoon Kim and G. V. Loganathan introduced harmony search in 2001, and it has since been applied to problems including water distribution network design, structural design, electrical load dispatch, clustering and feature selection.
Reader Challenges (0)
No disputes yet. Spotted an error or a better source? Open the first one.
Sign in to dispute this or suggest a correction.