Search

Load Forecasting plays a key role in making today's and future's Smart Energy Grids sustainable and reliable. Accurate power consumption prediction allows utilities to organize in advance their resources or to execute Demand Response strategies more effectively, which enables several features such as higher sustainability, better quality of service, and affordable electricity tariffs. It is easy yet effective to apply Load Forecasting at larger geographic scale, i.e. Smart Micro Grids, wherein the lower available grid flexibility makes accurate prediction more critical in Demand Response applications. This paper analyses the application of short-term load forecasting in a concrete scenario, proposed within the EU-funded GreenCom project, which collect load data from single loads and households belonging to a Smart Micro Grid. Three short-term load forecasting techniques, i.e. linear regression, artificial neural networks, and radial basis function network, are considered, compared, and evaluated through absolute forecast errors and training time. The influence of weather conditions in Load Forecasting is also evaluated. A new definition of Gain is introduced in this paper, which innovatively serves as an indicator of short-term prediction capabilities of time spam consistency. Two models, 24- and 1-hour-ahead forecasting, are built to comprehensively compare these three techniques., {"references":["M. T. Hagan, S. M. Behr, \"The time series approach to short term load\nforecasting\" IEEE Trans. Power Sys., vol. PWRS-2, no.3, Aug. 1987, pp.\n785-791.","Papalexopoulos, A. D., Hesterberg, T.C., \"A regression-based approach\nto short-term load forecasting\" IEEE Trans. Power Sys., vol.5, no.4, Nov.\n1990, pp 1535-1537.","H. S. Hippert, C. E. Pedreira, and R. C. Souza, \"Neural networks for\nshort-term load forecasting: A review and evaluation\" IEEE Trans. Power\nSys., 16:44-55, 2001.","J. W. Taylor, R. Buizza, \"Neural network load forecasting with weather\nensemble predictions\" IEEE Trans. Power Sys., 17:626-632, 2002.","W. Charytoniuk, M. S. Chen, \"Very short-term load forecasting using\naritificial neural networks\" IEEE Trans Power Sys., 2000, pp15(1):\n263-268.","X. F. Li, E. Zou, T. S. Zhang, \"Optimization design of feed-forward\nneural network structure based on chaos wariables\" Control and Decision,\n2003, 18(6):703-707.","G. Bugmann, \"Normalized Gaussian radial basis function networks\"\nNeurocomputing (Special Issue on Radial Basis Function Networks), vol.\n20, no.1, pp.97-110, 1998.","G. B. Huang, P. Saratchandran, N. Sundararajan, \"A generalized growing\nand pruning RBF neural network for function approximation\" IEEE Trans.\non Neural Networks, vol. 16, no.1, pp. 57-67, 2005.","K. Z. Mao, G. B. Huang, \"Neural slection for RBF neural network\nclassifier based on data structure preserving criterion\" IEEE Trans. on\nNeural Networks, vol. 16, no.6, pp. 1531-1540, 2005.\n[10] Gontar Z., Hatziargyriou N., \"Short-term load forecasting with radial\nbasis function network\" IEEE Porto Power Tech Conference, vol. 3, Sep\n2001.\n[11] S. J. Kiartzis, A. G. Bakirtzis, \"A fuzzy expert system for peak load\nforecasting: application to the Greek Power System\" Proceedings of the\n10th Mediterranean Electrotechnical Conference, 3:1097-1100, 2000.\n[12] Bretthauer G., Handschin E., Hoffmann W., \"Expert systems application\nto power systems--state-of-the-art and future trends\" IFAC Symposium\non Control of Power Plants and Power Systems, Munich, Germany, 1992,\np.463-68.\n[13] Adapa R., \"Expert system applications in power system planning and\noperations\" IEEE Power Eng. Rev, 1994, 14(2):15-8.\n[14] Liu C., Ma T., Liou K., Tsai M., \"Practical use of expert systems in power\nsystems\" Int J Eng Intelligent Sys. Electr. Eng. Commun 1994;\n2(1):11-22.\n[15] Bann J., Irisarri G., Kirschen D., Miller B., Mokhtari S., \"Integration of\nartificial intelligence applications in the EMS: issues and solutions\" IEEE\nTrans. Power Sys., 1996, pp11(1):475-82.\n[16] Madan S., Bollinger K., \"Applications of artificial intelligence in power\nsystems\" Electric Power Sys. Res., 1997, pp 41:117-31.\n[17] Barbato, A., Capone, A., Rodolfi, M., Tagliaferri D., \"Forecating the\nusage of household appliances through power meter sensors for demand\nmanagement in the smart grid,\" Smart Grid Communications, 2011 IEEE\nInternational Conference on, vol., no., pp.404,409, 17-20 Oct. 2011.\n[18] Fernandez, I., Borges, C.E., Penya, Y.K., \"Efficient building load\nforecasting,\" Emerging Technologies & Factoy Automation (ETFA),\n2011 IEEE 16th Conference on, vol., no., pp.1,8,5-9 Sep. 2011.\n[19] Berardino, J., Nwankpa, C.O., \"Interval-specific building load forecasting\nmodels for demand resource planning,\" Power System Technology\n(POWERCON), 2012 IEEE International Conference on, vol., no., pp.1.5.\nOct. 30 2012-Nov. 2 2012.\n[20] Canbing Li, Meiping Fu, Jincheng Shang, Peng Cheng, \"A novel\nprobabilistic short-term load forecasting method for large power grid,\"\nPower and energy Engineering Conference (APPEEC), 2010 Asia-Pacific,\nvol., no., pp.1,4,28-31 Mar. 2010.\n[21] GreenCom project http://www.greencom-project.eu.\n[22] Lean Y., Shouyang W., K. K. Lai, \"An integrated data preparation scheme\nfor neural network data analysis\" IEEE Tansactions on Knowledge and\nData Engineering, vol. 18, no.2, Feb. 2006.\n[23] X. Hu, \"DB-H reduction: a data preprocessing algorithm for data mining\napplications\" Applied Math. Letters, vol. 16, pp. 889-895, 2003\n[24] M. Lou, \"Preprocessing data for neural networks\" Technical Analysis of\nStocks Commodities Magazine, Oct. 1993.\n[25] GreenCom pilot, Island of Fur.\nhttp://www.greencom-project.eu/island-of-fur.html."]}

International audience; In this work, the design of an event-driven user-centric middleware for monitoring and managing energy consumption in public buildings and spaces is presented. The main purpose is to increase the energy efficiency, reducing consumption, in buildings and public spaces. To reach it, the proposed service-oriented middleware has been designed to be event based exploiting also the user behaviours patterns of the people, which lives and works into the building. Furthermore, it allows an easy integration of heterogeneous technologies in order to enable a hardware independent interoperability between them. Moreover, a Heating Ventilation and Air Conditioning (HVAC) control strategy has been developed and the whole infrastructure has been deployed in a real-world case study consisting of a historical building. Finally the results will be presented and discussed.

International audience; In this paper we report a methodology, developed in the context of Smart Energy Efficient Middleware for Public Spaces (SEEMPubS) European Project, aimed at exploiting ICT monitoring and control services to reduce energy usage and CO2 footprint in existing buildings. The approach does not require significant construction work as it is based on commercialoff- the-shelf devices and, where present, it exploits and integrates existing Building Management Systems (BMS) with new sensors and actuator networks. To make this possible, the proposed approach leverages upon the following main contributions: (a) to develop an integrated building automation and control system; (b) to implement a middleware for the energy efficient buildings domain; (c) to provide a multi-dimensional Building Information Modelling (BIM)-based visualization; (d) to raise people's awareness about energy efficiency. The research approach adopted in the project started with the selection, as case studies, of representative test and reference rooms in modern and historical buildings chosen for having different requirements and constraints in term of sensing and control technologies. Then, according to the features of the selected rooms, the strategies to reduce the energy consumptions were defined, taking into account the potential savings related to lighting, heating, ventilation, and air conditioning (HVAC) systems and other device loads (PC, printers, etc.). The strategies include both the control of building services and devices and the monitoring of environmental conditions and energy consumption. In the paper the energy savings estimated through simulation, for both HVAC and lighting, are presented to highlight the potential of the designed system. After the implementation of the system in the demonstrator, results will be compared to the monitored data.