جستجو در تالارهای گفتگو

Extreme learning machine for prediction of heat load in district heating systems Shahin Sajjadia, Shahaboddin Shamshirbandb, , , Meysam Alizamirc, Por Lip Yeeb, Zulkefli Mansord, Azizah Abdul Manafe, Torki A. Altameeme, , Ali Mostafaeipourf aDepartment of Construction Management, University of Houston, Houston, TX, USA bDepartment of Computer System and Technology, Faculty of Computer Science and Information Technology, University of Malaya, 50603 Kuala Lumpur, Malaysia cYoung Researchers and Elite Club, Hamedan Branch, Islamic Azad University, Hamedan, Iran dResearch Center for software technology and management (SOFTAM), Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia (UKM), Malaysia eAdvanced Informatics School, Universiti Teknologi Malaysia, Malaysia fIndustrial Engineering Department, Yazd University, Yazd, Iran Received 25 January 2016, Revised 23 March 2016, Accepted 9 April 2016, Available online 12 April 2016 Energy and Buildings Volume 122, 15 June 2016, Pages 222–227 Highlights • District heating systems for increase in fuel efficiency. • Control and prediction future improvement of district heating systems operation. • To predict the heat load for individual consumers in district heating systems. • A process which simulates the head load conditions. • Soft computing methodologies. Abstract District heating systems are important utility systems. If these systems are properly managed, they can ensure economic and environmental friendly provision of heat to connected customers. Potentials for further improvement of district heating systems’ operation lie in improvement of present control strategies. One of the options is introduction of model predictive control. Multistep ahead predictive models of consumers’ heat load are starting point for creating successful model predictive strategy. In this article, short-term, multistep ahead predictive models of heat load of consumer attached to district heating system were created. Models were developed using the novel method based on Extreme Learning Machine (ELM). Nine different ELM predictive models, for time horizon from 1 to 24 h ahead, were developed. Estimation and prediction results of ELM models were compared with genetic programming (GP) and artificial neural networks (ANNs) models. The experimental results show that an improvement in predictive accuracy and capability of generalization can be achieved by the ELM approach in comparison with GP and ANN. Moreover, achieved results indicate that developed ELM models can be used with confidence for further work on formulating novel model predictive strategy in district heating systems. The experimental results show that the new algorithm can produce good generalization performance in most cases and can learn thousands of times faster than conventional popular learning algorithms. Keywords District heating systems; Heat load; Estimation; Prediction; Extreme Learning Machine (ELM) 1-s2.0-S0378778816302766-main.pdf

Prediction of economic growth by extreme learning approach based on science and technology transfer Petra Karanikic´1 • Igor Mladenovic´2 • Svetlana Sokolov-Mladenovic´2 • Meysam Alizamir3 Springer Science+Business Media Dordrecht 2016 Abstract The purpose of this research is to develop and apply the extreme learning machine (ELM) to forecast gross domestic product (GDP) growth rate. Economic growth may be developed on the basis on combination of different factors. In this investigation was analyzed the economic growth prediction based on the science and technology transfer. The main goal was to analyze the influence of number of granted European patents on the economic growth by field of technology. GDP was used as economic growth indicator. The ELM results are compared with genetic programming (GP) and artificial neural network (ANN). The reliability of the computational models were accessed based on simulation results and using several statistical indicators. Coefficient of determination for ELM method is 0.9841, for ANN method it is 0.7956 and for the GP method it is 0.7561. Based upon simulation results, it is demonstrated that ELM can be utilized effectively in applications of GDP forecasting. Keywords GDP Forecasting Extreme learning machine Economic growth SP_3881_10.1007%2Fs11135-016-0337-y.pdf