{"references": ["Tim Salsbury, Rick Diamond, \"Performance validation and energy\nanalysis of HVAC systems using simulation\", Energy and\nBuildings, vol. 32, pp. 5 - 17, 2000.", "Brian A. Smith, Ronald W. McClendon, Gerrit Hoogenboom,\n\"Improving Air Temperature Prediction with Artificial Neural\nNetworks\", International Journal of Computational Intelligence, vol 3,\npp. 179 - 186, 2006.", "Jian Sun and Agami Reddy, \"Optimal control of building HVAC&R\nsystems using complete simulation-based sequential quadratic\nprogramming (CSB-SQP)\", Building and Environment, vol. 40, pp. 657\n- 669, 2005.", "L. G. Caldas, L. K. Norford, \"Genetic algorithms for optimization of\nbuilding envelopes and the design and control of HVAC systems\",\nJournal of solar energy engineering, Transactions of the ASME, 2003.", "T. T. Chow, Z. Lin and C. L. Song, G. Q. Zhang, \"Applying neural\nnetwork and genetic algorithm in chiller system optimization\", Seventh\nInternational IBPSA Conference, Brazil, 2001.", "Jonathan A. Wright, A. Heather, Loosemore, Raziyeh Farmani.\n\"Optimization of building thermal design and control by multi-criterion\ngenetic algorithm\", Energy and Buildings, 34, pp. 959 - 972, 2002.", "Johnny N.Holst, \"Using whole building simulation models and\noptimizing procedures to optimize building envelope design with respect\nto energy consumption and indoor environment\", Eigth International\nConference, 2003.", "Yung-Chung Chang, Jui-Kun Lin, Meng-Hsuan Chuang, \"Optimal\nchiller loading by genetic algorithm for reducing energy consumption\",\nEnergy and Buildings, vol. 37, pp.147 - 155, 2005.", "Rafael Alcala, Antonio Gonzalez, Francisco Herrera, Jorge Casillas,\nOscar Cordon, \"A genetic rule weighting and selection process for fuzzy\ncontrol of heating, ventilation and air conditioning systems\",\nEngineering Applications of Artificial Intelligence, vol. 18, 279 - 296,\n2005.\n[10] Lu Lu and Wenjian Cai, \"Application of genetic algorithms for optimal\nchiller selection in HVCA systems\", 13th Int.Conference on Process\nControl, 2001.\n[11] C. Aprea, C. Renno, R. Mastrullo, \"Fuzzy control of the compressor\nspeed in a refrigeration plant\", International Journal of Refrigeration,\nvol. 27, pp. 639 - 648. 2004.\n[12] S. Wang, X. Jin, \"Model-based optimal control of VAV airconditioning\nsystem using genetic algorithm\", Building and\nEnvironment, vol. 35, pp. 471 - 487, 2000.\n[13] Timothy J.Ross (1995.), Fuzzy logic with engineering applications, Mc\nGraw Hill, Inc.\n[14] Igor Skrjanc, Borut Zupancic, Bostjan Furlan and Alas Krainer,\n\"Theoretical and experimental fuzzy modeling of building thermal\ndynamic response\", Building and Environment, vol. 36, 1023-1038,\n2001."]}

The objective of this study is to present the test results of variable air volume (VAV) air conditioning system optimized by two objective genetic algorithm (GA). The objective functions are energy savings and thermal comfort. The optimal set points for fuzzy logic controller (FLC) are the supply air temperature (Ts), the supply duct static pressure (Ps), the chilled water temperature (Tw), and zone temperature (Tz) that is taken as the problem variables. Supply airflow rate and chilled water flow rate are considered to be the constraints. The optimal set point values are obtained from GA process and assigned into fuzzy logic controller (FLC) in order to conserve energy and maintain thermal comfort in real time VAV air conditioning system. A VAV air conditioning system with FLC installed in a software laboratory has been taken for the purpose of energy analysis. The total energy saving obtained in VAV GA optimization system with FLC compared with constant air volume (CAV) system is expected to achieve 31.5%. The optimal duct static pressure obtained through Genetic fuzzy methodology attributes to better air distribution by delivering the optimal quantity of supply air to the conditioned space. This combination enhanced the advantages of uniform air distribution, thermal comfort and improved energy savings potential.