Non-intrusive energy-management (NIEM) techniques are based on energy signatures. While such approaches lack transient energy signatures, the reliability and accuracy of recognition results cannot be determined. By using neural networks (NNs) in combination with turn-on transient energy analysis, this study attempts to identify load demands and improve recognition accuracy of NIEM results. Case studies are presented that apply various methods to compare training algorithms and classifiers in terms of artificial neural networks (ANN) due to various factors that determine whether a network is being used for pattern recognition. Additionally, in combination with electromagnetic transient program (EMTP) simulations, calculating the turn-on transient energy facilitate load can lead to identification and a significant improvement in the accuracy of NIEM results. Analysis results indicate that an NIEM system can effectively manage energy demands within economic dispatch for a cogeneration system and power utility. Additionally, a new method based on genetic algorithms (GAs) is used to develop a novel operational strategy of economic dispatch for a cogeneration system in a regulated market and approach the global optimum with typical environmental constraints for a cogeneration plant. Economic dispatch results indicate that the NIEM system based on energy demands can estimate accurately the energy contribution from the cogeneration system and power utility, and further reduce air pollution. Moreover, applying the NIEM system for economic dispatch can markedly reduce computational time and power costs. (C) 2009 Elsevier Ltd. All rights reserved.