A Hybrid Metaheuristic for the Optimal Design of Photovoltaic Installations
We consider the Photovoltaic Installation Design Problem (PIDP) were photovoltaic modules must be organized in strings and wired to a set of electronic devices. The aim is to minimize installation costs and maximize power production considering “mismatch losses” caused by non-uniform irradiation (shading) and directly related to design decisions. We relate the problem to the known class of location routing problems and thanks to the existing knowledge on the problem, we design a route-first cluster-second heuristic. We propose an efficient machine learning approach to evaluate the installation performances accounting for mismatch losses. We prove that our approach is effective on real-world instances provided by our industrial partner.
KeywordsMetaheuristic Machine learning Photovoltaic installation design
- 3.Di Dio, V., La Cascia, D., Miceli, R., Rando, C.: A mathematical model to determine the electrical energy production in photovoltaic fields under mismatch effect. In: 2009 International Conference on Clean Electrical Power, pp. 46–51. IEEE (2009)Google Scholar
- 6.Friedman, J., Hastie, T., Tibshirani, R.: The Elements of Statistical Learning, vol. 1. Springer (2001)Google Scholar