SUMMARYThis paper presents an arti"cial neural network (ANN) approach to electric energy consumption (EEC) forecasting in Lebanon. In order to provide the forecasted energy consumption, the ANN interpolates among the EEC and its determinants in a training data set. In this study, four ANN models are presented and implemented on real EEC data. The "rst model is a univariate model based on past consumption values. The second model is a multivariate model based on EEC time series and a weather-dependent variable, namely, degree days (DD). The third model is also a multivariate model based on EEC and a gross domestic product (GDP) proxy, namely, total imports (TI). Finally, the fourth model combines EEC, DD and TI. Forecasting performance measures such as mean square errors (MSE), mean absolute deviations (MAD), mean percentage square errors (MPSE) and mean absolute percentage errors (MAPE) are presented for all models.
Abstract-In a classical mobile video streaming architecture, the server is responsible for processing each request from the mobile clients even if those requests are for the same content in the same geographical area. This tends to be resource exhaustive in terms of complexity, radio resources, and energy consumption especially when delivering high bit rate multimedia content. In this paper, we exploit cooperation between network technologies to reduce the load placed on a given multimedia server and reduce the overall energy drain of mobile devices. We consider a set of mobile devices that wish to receive a common video content from a designated video server. The mobile devices organize themselves into multiple Bluetooth piconets. The master in each piconet receives an H.264 encoded video content from the server via an IEEE 802.11 WLAN access point and relays it to its slave mobile devices using standard Bluetooth connections. A prototypical implementation of the proposed model in an experimental testbed is used to perform energy and video quality measurements in real conditions. Results demonstrate notable energy consumption gains while maintaining video quality in various scenarios.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.