Short-Term Load Forecasting in Hospital Systems

Short-term load forecasting can provide information which is applicable for the possible energy interchange with other utilities.Load forecasting is also advantegeous for system security,in fact if applied to the system security assessment problem,it can provide valuable information to detect many vulnerable situations in advance.In addition if the work environment is in a hospital reality,where a continuous energy and electricity utilization is required,all the problems previously listed are amplified and of a greater importance,because of the continuous use of new technological instruments.In this study a neural network approach for the hospital energy load forecast is illustrated.The data sets belong to the University Eye Clinic of Genoa,S.Martino Hospital,Genoa,Italy,and to the Department of Internal Medicine and Medical Specialties (DIMI) of the University of Genoa,Italy.These two environments represent different approaches in patient treatment and this study aims to determine if the same tool is beneficial in load forecasting for both wards.In both realities the presented approach reached a target of more than 75% of correct forecasts.
load forecasting in health environments duration curves artificial neural network optimization in electrical power use
S. Bertolini S. Massucco F. Silvestro S. Grillo G. Giacomini
Department of Communication, Computer and System Sciences, University of Genoa, Genoa, Italy Department DYNATECH, University of Genoa, Genoa, Italy Department of Electrical Engineering, Polytechnic of Milano, Milan, Italy
国际会议
World Congress on Medical Physics and Biomedical Engineering (2012年医学物理及生物医学工程国际会议(IFMBE))
北京
英文
684-687
2012-05-26(万方平台首次上网日期,不代表论文的发表时间)