Satisfactory Design of Cogeneration System using Genetic Algorithm Satoshi Hirai Graduate School of Engineering, Doshisha University 1-3 Tatara Miyakodani Kyotanabe, Kyoto 610-0394 Email: hirai@mikilab.doshisha.ac.jp Tomoyuki Hiroyasu Department of Engineering, Doshisha University 1-3 Tatara Miyakodani Kyotanabe, Kyoto 610-0394 Email: tomo@is.doshisha.ac.jp Mitsunori Miki Department of Engineering, Doshisha University 1-3 Tatara Miyakodani Kyotanabe, Kyoto 610-0394 Email: mmiki@mail.doshisha.ac.jp Hisashi Shimosaka Graduate School of Engineering, Doshisha University 1-3 Tatara Miyakodani Kyotanabe, Kyoto 610-0394 Email: hisashi@mikilab.doshisha.ac.jp Yoichi Tanaka Toho Gas Co.,Ltd. 507-2 Sinpoumachi Tokai, Aichi 476-0005 Email: y tanaka@tohogas.co.jp Syuichi Aoki Toho Gas Co.,Ltd. 507-2 Sinpoumachi Tokai, Aichi 476-0005 Email: saoki@tohogas.co.jp Yoshito Umeda Toho Gas Co.,Ltd. 507-2 Sinpoumachi Tokai, Aichi 476-0005 Email: umeda@tohogas.co.jp Abstract— This paper introduces the optimum design of Co- generation System (CGS) using the Genetic Algorithm (GA). CGS is the energy reusing system which generates more than two energies from one energy source. To design CGS, the types of machines and load scheduling should be determined. However, the optimum design of CGS is too complicated even for the Expert. One of the solutions for this problem is using GA. GA is the optimization model imitating evolution of life. If the coding of the problems is proper, GA can be applicable to many problems. However, proper coding for the problems is difficult, especially for CGS, because it has three different design variables which consist of integer values and real values. To discuss the effective coding, this paper considers four models. First is simplest coding model. Second is two-step optimization model with integer coding. Third is two-step optimization model with the integer coding and the penalty method. Last is three-step optimization model with the integer. As a result of the experiments, three-step optimization model could achieve the higher energy efficiency design of CGS than the expert. I. I NTRODUCTION Recently, Cogeneration System (CGS)[1] has been paid attention, because CGS generates the energies effectively. In general, CGS means a continuous production of more than two energies from a single energy source. The key issue in the CGS design is the selection of proper machines and load factor per each time in plural energy demands. If CGS works under the proper machines and load factor, it can supply target energies from less energy source. However, CGS design is generally very complex and a very difficult problem. Conventionally, CGS design was based on the experience and technical instinct of design projector, and it was researched by using Hamiltonian Algorithm (HA)[2]. On the other hand, Genetic Algorithm (GA)[3] is an opti- mization technique based on natural genetics. GA is versatile optimum model which is applicable to many actual problems. For example, there are the optimum control of a Flexible Ma- nipulator [4], and the Prediction of Protein Tertiary Structures [5] and so on. GA shows great results among them. Therefore, it is expected that GA is effective for CGS design problem too. This research examines the optimization with adopting GA to CGS design problem. The coding for the problem is the key issue of optimization by GA. Especially, CGS design problem has various design valuables, such as Operation Time, the Number and Type of Machine, and the Load Factor per each time. CGS design problem consists of two factors. One is compound optimiza- tion problem searching proper selection of machines. Another is the continuous problem searching proper load factor in each machine. Therefore, designing effective coding for the CGS design problem is very difficult. This paper proposes effective coding for CGS design problems, and optimum design of CGS supplying energies from less energy source. II. COGENERATION SYSTEM A. Overview of CGS CGS consists of Generator, Exhaust Heat Unit and Boiler. These machines generate Electricity, Air Conditioner, Heater