Abstract
This paper proposes an efficient data-driven approach to build models for predicting energy consumption in buildings. Data used in this research is collected by installing humidity and temperature sensors at different locations in a building. In addition to this, weather data from nearby weather station is also included in the dataset to study the impact of weather conditions on energy consumption. One of the main emphasize of this research is to make feature selection independent of domain knowledge. Therefore, to extract useful features from data, two different approaches are tested: one is feature selection through principal component analysis and second is relative importance-based feature selection in original domain. The regression model used in this research is gradient boosting regression and its optimal parameters are chosen through a two staged coarse-fine search approach. In order to evaluate the performance of model, different performance evaluation metrics like r2-score and root mean squared error are used. Results have shown that best performance is achieved, when relative importance-based feature selection is used with gradient boosting regressor. Results of proposed technique has also outperformed the results of support vector machines and neural network-based approaches tested on the same dataset.
Key Words
energy consumption; ensemble methods; gradient boosting regression
Address
Ali S. Al Bataineh: Department of Electrical Engineering and Computer Science, University of Toledo, 2801 Bancroft Street, Toledo, OH 43606, U.S.A.
Abstract
While global demand for energy increases annually, at the same time the demand for carbon-free, sulphur-free and NOx-free energy sources grows considerably. This state poses a challenge in the research for newer sources like biomass and shale gas as well as renewable energy resources such as solar, wind, geothermal and hydraulic energy.
Although wave energy also is a form of renewable energy it has not fully been exploited technically and economically so far. This study tries to explain those reasons in which it is beyond doubt that the demand for wave energy will soon increase as fossil energy resources are depleted and environmental concerns gain more importance.
The electrical energy supplied to the grid shall be produced from wave energy whose conversion devices can basically work according to three different systems.
i. Systems that exploit the motions or shape deformations of their mechanisms involved, being driven by the energy of passing waves.
ii. Systems that exploit the weight of the seawater stored in a reservoir or the changes of water pressure by the oscillations of wave height,
iii. Systems that convert the wave motions into air flow.
One of the aims of this study is to present the classification deficits of the wave energy converters (WECs) of the \"wave developers\" prepared by the European Marine Energy Center, which were to be reclassified. Furthermore, a new classification of all WECs listed by the European Marine Energy Center was arranged independently. The other aim of the study is to assess the technological state of the art of these WECs designed and/or produced, to obtain an overview on them.
Key Words
wave energy; wave converter; classification of converter; assessment of converter
Address
K. Turgut Gursel:Institute of Marine Sciences and Technology, Dokuz Eylül University, Baku Boulevard, No. 100, Inciralt
Abstract
Global Solar Radiation (GSR) is the key element for performance estimation of any Solar Power Plant (SPP). Its forecasting may help in estimation of power production from a SPP well in advance, and may also render help in optimal use of this power. Seasonal Auto-Regressive Moving Average (SARMA) and Artificial Neural Network (ANN) models are combined in order to develop a hybrid model (SARMA-ANN) conceiving the characteristics of both linear and non-linear prediction models. This developed model has been used for prediction of GSR at Gorakhpur, situated in the northern region of India. The proposed model is beneficial for the univariate forecasting. Along with this model, we have also used Auto-Regressive Moving Average (ARMA), SARMA, ANN based models for 1 – 6 day-ahead forecasting of GSR on hourly basis. It has been found that the proposed model presents least RMSE (Root Mean Square Error) and produces best forecasting results among all the models considered in the present study. As an application, the comparison between the forecasted one and the energy produced by the grid connected PV plant installed on the parking stands of the University shows the superiority of the proposed model.
Key Words
global solar radiation; Box-Jenkin\'s model; ANN; SARMA; hybridization
Address
Rachit Srivastava, A. N. Tiwari and V. K. Giri: Department of Electrical Engineering, Madan Mohan Malaviya University of Technology, Gorakhpur 273010, Uttar Pradesh, India
Abstract
The world population reaches to about 7.7 billion in 2018 from 6.2 billion in 2000. This much growth in population results in increased energy demand and increased food supply. As the conventional energy sources are limited. These may deplete soon if consumed at this rate. So, the world is switching towards the utilization of non-conventional sources of energy. Energy from sun is the best method as it can not only solve the energy issue but also helps in meeting food demand by conserving it. Greenhouses are made for the purpose of food conservation. Various types of solar dryers are developed by researchers till now and still the effort is being putted to make them more efficient. Hybrid greenhouse is also effort toward utilization of solar energy in more efficient way. The paper presents the heat and mass transfer analysis of hybrid greenhouse solar dryer developed by different researchers till now. The review helps the researcher in understanding the heat and mass transfer taking place inside the hybrid greenhouse and how it can be further improved.
Key Words
hybrid; greenhouse; solar dryer; dryer development; dryer
Address
Pushpendra Singh, Manoj K. Gaur and Anand Kushwah:Department of Mechanical Engineering, Madhav Institute of Technology and Science, Gwalior, 474005 India
G.N. Tiwari: Research and Development Cell, SRM University, Lucknow, Uttar Pradesh, 225003 India
Abstract
The principal intention of this experimental work is to confer upon the exergy study of GSHP associated with horizontal earth heat exchanger for space heating. The exergy analysis recognizes the assessment of the tendency of various energy flows and quantifies the extensive impression of inefficiencies in the system and its components. Consequently, this study intends to provide the enlightenment for well interpretation of exergy concept for GSHP. This GSHP system is composed of heat pump cycle, earth heat exchanger cycle and fan coil cycle. All the required data were measured and recorded when the experimental set up run at steady state and average of the measured data were used for exergy investigation purpose. In this study the rate at which exergy destructed at all the subsystems and system has been estimated using the analytical expression. The overall rational exergetic efficiency of the GSHP system was evaluated for estimating its effectiveness. Hence, we draw the exergy flow diagram by using the various calculated results. The result shows that in the whole system the maximum exergy destruction rate component was compressor and minimum exergy flow component was earth heat exchanger. Consequently, compressor and earth heat exchanger need to be pay more attention.
Key Words
exergy; earth heat exchanger; heat pump; exergetic efficiency
Address
Saif Nawaz Ahmad and Om Prakash: Department of Mechanical Engineering, National Institute of Technology, Patna,
Ashok Raj Path, Patna, 800005, India
