IEEE COMMUNICATIONS SURVEYS & TUTORIALS, ACCEPTED FOR PUBLICATION 1 A Survey on Electric Power Demand Forecasting: Future Trends in Smart Grids, Microgrids and Smart Buildings Luis Hernandez, Carlos Baladr´ on, Javier M. Aguiar, Bel´ en Carro, Antonio J. Sanchez-Esguevillas, Jaime Lloret, and Joaquim Massana Abstract—Recently there has been a significant proliferation in the use of forecasting techniques, mainly due to the increased availability and power of computation systems and, in particular, to the usage of personal computers. This is also true for power network systems, where energy demand forecasting has been an important field in order to allow generation planning and adaptation. Apart from the quantitative progression, there has also been a change in the type of models proposed and used. In the 70s, the usage of non-linear techniques was generally not popular among scientists and engineers. However, in the last two decades they have become very important techniques in solving complex problems which would be very difficult to tackle otherwise. With the recent emergence of smart grids, new environments have appeared capable of integrating demand, generation, and storage. These employ intelligent and adaptive elements that require more advanced techniques for accurate and precise demand and generation forecasting in order to work optimally. This review discusses the most relevant studies on electric demand prediction over the last 40 years, and presents the different models used as well as the future trends. Additionally, it analyzes the latest studies on demand forecasting in the future environments that emerge from the usage of smart grids. Index Terms—Electric demand forecasting, short-term load forecasting, smart grid, microgrid, smart building. I. I NTRODUCTION This introduction aims at setting the background for under- standing the demand forecasting problem in modern day and future power networks by taking three different approaches. First, in subsection A, the importance of demand forecasting is explained, presenting the reasons why it is an important step in the energy generation process of utilities, and the role it plays for each of the components of the grids and smart grids of today. Secondly, in subsection B, a brief historical Manuscript received April 2, 2013; revised October 16, 2013. L. Hernandez is with Centro de Investigaciones Energ´ eticas, Medioambien- tales y Tecnol´ ogicas (CIEMAT), Centro de Desarrollo de Energas Renovables (CEDER), Autov´ ıa de Navarra A15, salida 56, 42290 Lubia, Soria, (Spain), (e-mail: luis.hernandez@ciemat.es). C. Baladr´ on, J. M. Aguiar, B. Carro, and A. J. Sanchez-Esguevillas are with Universidad de Valladolid, E.T.S.I. Telecomunicaci´ on, Cam- pus Miguel Delibes, Paseo de Bel´ en 15, 47011 Valladolid (Spain) (e-mail: cbalzor@ribera.tel.uva.es, javagu@tel.uva.es, belcar@tel.uva.es, antsan@tel.uva.es). J. Lloret is with Universidad Polit´ ecnica de Valencia, Departamento de Comunicaciones, Camino Vera, s/n, 46022, Valencia (e-mail: jl- loret@dcom.upv.es). J. Massana is with eXiT Research Group, Institute of Informatics and Applications, University of Girona, Campus Montilivi, Building P4, 17071 Girona (Spain) (e-mail: quim.massana@hotmail.com). Digital Object Identifier 10.1109/SURV.2014.032014.00094 perspective of the evolution of demand forecast is given since its beginning, and third, in subsection C, a justification is given of why demand forecasting will continue being a hot topic in the future energy distribution networks. Then, before moving onto Section II, the global structure of this paper is presented. A. The importance of demand forecasting From its onset, the electric system has been based on three levels: generation, transport, and distribution and marketing. With the exception of marketing activities, the rest have focused on solving problems from an electrical perspective. As networks grew bigger and bigger, they started to be very difficult to control and lost efficiency due to electric loss. In addition, traditionally the final consumers have not been taken into account in the system except when the moment comes to pay the bill (large-scale consumers received a separate treatment). The bill, in most cases, is based on estimates and not on real data, and the suppliers have a period of time to issue the invoices. Recently, new players (Electric Vehicle (EV ), Smart Cus- tomers, Renewable Energy) have emerged in the electrical system scene that have caused demand forecasting to gain special interest. Currently, EVs are gradually being introduced into the electrical system, and it is expected that the increasing influence of these elements will eventually change overall load profile significantly. This impact comes from the fact that EVs are mobile elements that do not only consume power, but can potentially also contribute electricity to the grid. Additionally, it is expected that most of the residential charge operations will take place during the night, in a typical valley period of the demand curve, where the usage of vehicles is reduced. It is believed that EVs would then be seized to flatten the consumption curve, taking energy from the grid overnight, and providing energy during peak periods. In any case, it is evident that the massive introduction of these new elements will in any case modify the behaviour of the grid at a very significant scale. Apart from demand forecasting, electrical generation fore- casting models have also received increasing attention, espe- cially when it comes to renewable generation sources, which in turn depend on the forecasting of a particular energy resource (solar radiation, wind, etc.). Next, the main changes occurred in the electrical system, and the actors they have brought in, are explained. 1553-877X/14/$31.00 c  2014 IEEE This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination.