Prediction of energy demands using neural network with model identification by global optimization

Yokoyama, Ryohei; Wakui, Tetsuya; Satake, Ryoichi

doi:10.1016/j.enconman.2008.09.017

Cited by 148 publications

(50 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Azadeh et al [3] and Maia et al [4] forecasted electrical energy consumption through analyzing the varying inner targets without any contributory variable involved. Yokoyama et al [5] considered only two features, air temperature and…”

Section: Introductionmentioning

confidence: 99%

Feature Selection for Predicting Building Energy Consumption Based on Statistical Learning Method

Zhao

Magoulès

2012

Journal of Algorithms & Computational Technology

View full text Add to dashboard Cite

Machine learning methods are widely studied and applied to predict building energy consumption. Since the factors associated with building energy behaviors are quite abundant and complex, this paper investigates for the first time how the selection of subsets of features influence the model performance when statistical learning method is adopted to derive the model. In this paper the optimal features are selected based on the feasibility of obtaining them and on the scores they provide under the evaluation of some filter methods. The selected subset is then evaluated on three data sets by support vector regression involving two kernel functions: radial basis function and polynomial function. Experimental results confirm the validity of the selected subset and show that the proposed feature selection method can guarantee the prediction accuracy and reduces the computational time for data analyzing.

show abstract

Section: Introductionmentioning

confidence: 99%

Feature Selection for Predicting Building Energy Consumption Based on Statistical Learning Method

Zhao

Magoulès

2012

Journal of Algorithms & Computational Technology

View full text Add to dashboard Cite

show abstract

“…In this paper, the modal trimming method proposed for nonlinear programming problems is adopted as a global optimization one (Yokoyama and Ito, 2005). This method has been applied to a neural network model for energy demand prediction, and its validity and effectiveness have been ascertained (Yokoyama et al, 2009).…”

Section: Identification Of Model Parameter Valuesmentioning

confidence: 99%

Performance Estimation and Optimal Operation of a CO2 Heat Pump Water Heating System

Yokoyama¹

2013

Int. J. Thermo

Self Cite

View full text Add to dashboard Cite

IntroductionHot water demand occupies about one-third of the energy consumption in the residential sector in Japan, and energy saving in hot water supply has been an important issue. Under this situation, water heating systems each of which is composed of a heat pump using CO 2 as a natural refrigerant and a hot water storage tank have been developed and commercialized widely (Saikawa, 2004;Hashimoto, 2006). The performance of CO 2 heat pumps has been enhanced dramatically through the technological development of their components such as compressors and gas coolers. On the other hand, importance has also been given to the performance of water heating systems in case they are operated under a daily change in hot water demand.The performance of the CO 2 heat pump only, or coefficient of performance (COP) is affected by the air temperature as well as the inlet and outlet water temperatures. Many theoretical and experimental studies have been conducted for the performance analysis on CO 2 heat pumps (Hwang and Radermacher, 1998;Nekså et al., 1998; Saikawa et al., 1999;Saikawa and Hashimoto, 2001;Nekså, 2002;White et al., 2002;Skaugen et al., 2002;Richter et al., 2003;Yokoyama et al., 2006;Laipvadit et al., 2008;Yan et al., 2010;Sarkar et al., 2010;Yamaguchi et al., 2011). On the other hand, the performance of the water heating system composed of the CO 2 heat pump and storage tank is affected by many conditions. The ambient conditions such as air and feed water temperatures, the hot water demand, and the operating conditions such as startup and shutdown, and outlet water temperature during operation of the CO 2 heat pump affect the inlet water temperature and resultantly the COP through the temperature distribution in the storage tank. In addition to the COP, the storage and system efficiencies, and the volumes of stored and unused hot water are considered as system performance values, and these are also affected by the aforementioned various conditions through the temperature distribution in the storage tank. As a result, the system performance is affected by the operational history on past several days, and changes complexly with days. Therefore, in order to attain the maximum system performance, it is necessary to estimate the daily changes in system performance values accurately in relation to those in the ambient conditions, hot water demand, and operating conditions, and determine the operating conditions optimally based on them.Some studies have been conducted for the performance analysis on water heating systems (Cecchinato et al., 2005;Stene, 2005;Minetto, 2011). However, few studies have been conducted in consideration of daily changes in the aforementioned conditions. In order to investigate the daily changes in system performance values, laboratory and field tests have been tried under simulated and practical hot water demands, respectively. However, hot water demands depend on residential houses, and it takes extremely long time to conduct the tests. Thus, it is not necessarily easy to investigate the ...

show abstract

“…In some of these works [14][15][16][17][18][19][20][21][22][23] the ANN approach was also compared with other methods used for the evaluation of energy consumptions; Tso et al [18] compared three different methods (regression analysis, decision trees and Neural Network) for predicting energy consumptions, highlighting how both decision tree, and Neural Network approaches are viable alternatives to the regression method.…”

Section: Introductionmentioning

confidence: 99%

“…Several studies were carried out for predicting the thermal behavior of buildings envelope [7][8][9][10][11][12][13] and for evaluating the energy demand [14][15][16][17][18][19][20][21][22][23] by using Artificial Neural Network (ANN). Pandey et al [7] evaluated the indoor temperature using two prototype rooms (1m × 1m × 1m) in which different cooling techniques were built and tested; specifically ANN was developed using different training functions and considering the external climate conditions (outdoor temperature, wind speed, and solar intensity).…”

Section: Introductionmentioning

confidence: 99%

Building Behavior Simulation by Means of Artificial Neural Network in Summer Conditions

et al. 2014

View full text Add to dashboard Cite

Many studies in Italy showed that buildings are responsible for about 40% of total energy consumption, due to worsening performance of building envelope; in fact, a great number of Italian buildings were built before the 1970s and 80s. In particular, the energy consumptions for cooling are considerably increased with respect to the ones for heating. In order to reduce the cooling energy demand, ensuring indoor thermal comfort, a careful study on building envelope performance is necessary. Different dynamic software could be used in order to evaluate and to improve the building envelope during the cooling period, but much time and an accurate validation of the model are required. However, when a wide experimental data is available, the Artificial Neural Network (ANN) can be an alternative, simple and fast tool to use. In the present study, the indoor thermal conditions in many dwellings built in Umbria Region were investigated in order to evaluate the envelope performance. They were recently built and have very low energy consumptions. Based on the experimental data, a feed forward network was trained, in order to evaluate the different envelopes performance. As input parameters the outdoor climatic conditions and the thermal characteristics of building envelopes were set, while, as a target parameter, the indoor air temperature was provided. A good training of network was obtained with a high regression value (0.9625) and a very small error (0.007 °C) on air temperature. The network was also used to simulate the envelope behavior with new innovative glazing systems, in order to evaluate and to improve the energy performance.

show abstract

Prediction of energy demands using neural network with model identification by global optimization

Cited by 148 publications

References 13 publications

Feature Selection for Predicting Building Energy Consumption Based on Statistical Learning Method

Feature Selection for Predicting Building Energy Consumption Based on Statistical Learning Method

Performance Estimation and Optimal Operation of a CO2 Heat Pump Water Heating System

Building Behavior Simulation by Means of Artificial Neural Network in Summer Conditions

Contact Info

Product

Resources

About