Successful development of a marine wave energy converter (WEC) relies strongly on the development of the power generation device, which needs to be efficient and cost-effective. An innovative multi-input approach based on the Convolutional Neural Network (CNN) is investigated to predict the power generation of a WEC system using a double-buoy oscillating body device (OBD). The results from the experimental data show that the proposed multi-input CNN performs much better at predicting results compared with the conventional artificial network and regression models. Through the power generation analysis of this double-buoy OBD, it shows that the power output has a positive correlation with the wave height when it is higher than 0.2 m, which becomes even stronger if the wave height is higher than 0.6 m. Furthermore, the proposed approach associated with the CNN algorithm in this study can potentially detect the changes that could be due to presence of anomalies and therefore be used for co... [more]

Artificial Intelligence (AI) has been widely used in Short-Term Load Forecasting (STLF) in the last 20 years and it has partly displaced older time-series and statistical methods to a second row. However, the STLF problem is very particular and specific to each case and, while there are many papers about AI applications, there is little research determining which features of an STLF system is better suited for a specific data set. In many occasions both classical and modern methods coexist, providing combined forecasts that outperform the individual ones. This paper presents a thorough empirical comparison between Neural Networks (NN) and Autoregressive (AR) models as forecasting engines. The objective of this paper is to determine the circumstances under which each model shows a better performance. It analyzes one of the models currently in use at the National Transport System Operator in Spain, Red Eléctrica de España (REE), which combines both techniques. The parameters that are tes... [more]

Presently, Thailand runs various sustainable development-based policies to boost the growth in economy, society, and environment. In this study, the economic and social growth was found to continuously increase and negatively deteriorate the environment at the same time due to a more massive final energy consumption in the petroleum industries sector than any other sectors. Therefore, it is necessary to establish national planning and it requires an effective forecasting model to support Thailand’s policy-making. This study aimed to construct a forecasting model for a final energy consumption prediction in Thailand’s petroleum industry sector for a longer-term (2018⁻2037) at a maximum efficiency from a certain class of methods. The Long Term-Autoregressive Integrated Moving Average with Exogeneous variables and Error Correction Mechanism model (LT-ARIMAXS model) (p, d, q, Xi, ECT(t−1)) was adapted from the autoregressive and moving average model incorporating influential variables toge... [more]

Recent electricity price forecasting (EPF) studies suggest that the least absolute shrinkage and selection operator (LASSO) leads to well performing models that are generally better than those obtained from other variable selection schemes. By conducting an empirical study involving datasets from two major power markets (Nord Pool and PJM Interconnection), three expert models, two multi-parameter regression (called baseline) models and four variance stabilizing transformations combined with the seasonal component approach, we discuss the optimal way of implementing the LASSO. We show that using a complex baseline model with nearly 400 explanatory variables, a well chosen variance stabilizing transformation (asinh or N-PIT), and a procedure that recalibrates the LASSO regularization parameter once or twice a day indeed leads to significant accuracy gains compared to the typically considered EPF models. Moreover, by analyzing the structures of the best LASSO-estimated models, we identify... [more]

Load forecasting models are of great importance in Electricity Markets and a wide range of techniques have been developed according to the objective being pursued. The increase of smart meters in different sectors (residential, commercial, universities, etc.) allows accessing the electricity consumption nearly in real time and provides those customers with large datasets that contain valuable information. In this context, supervised machine learning methods play an essential role. The purpose of the present study is to evaluate the effectiveness of using ensemble methods based on regression trees in short-term load forecasting. To illustrate this task, four methods (bagging, random forest, conditional forest, and boosting) are applied to historical load data of a campus university in Cartagena (Spain). In addition to temperature, calendar variables as well as different types of special days are considered as predictors to improve the predictions. Finally, a real application to the Span... [more]

An analysis of the variability of wave climate and energy within the Black Sea for the period 1960⁻2011 was made using field data from the Voluntary Observing Ship Program. Methods using wavelet analysis were applied. It was determined that the power flux of wave energy in the Black Sea fluctuates: the highest value is 4.2 kW/m, the lowest is 1.4 kW/m. Results indicate significant correlations among the fluctuations of the average annual wave heights, periods, the power flux of wave energy, and teleconnection patterns of the North Atlantic Oscillation (NAO), the Atlantic Multi-decadal Oscillation (AMO), the Pacific Decadal Oscillation (PDO) and the East Atlantic/West Russia (EA/WR). It was revealed that, in positive phases of long-term periods of AMO (50⁻60 years) as well as PDO, NAO, and AO (40 years), a decrease of wave energy was observed; however, an increase in wave energy was observed in the positive phase of a 15-year period of NAO and AO. The positive phase of changes of EA/WR... [more]

A smart grid facilitates more effective energy management of an electrical grid system. Because both energy consumption and associated building operation costs are increasing rapidly around the world, the need for flexible and cost-effective management of the energy used by buildings in a smart grid environment is increasing. In this paper, we consider an energy management system for a smart energy building connected to an external grid (utility) as well as distributed energy resources including a renewable energy source, energy storage system, and vehicle-to-grid station. First, the energy management system is modeled using a Markov decision process that completely describes the state, action, transition probability, and rewards of the system. Subsequently, a reinforcement-learning-based energy management algorithm is proposed to reduce the operation energy costs of the target smart energy building under unknown future information. The results of numerical simulation based on the data... [more]

Deep neural networks are proposed for short-term natural gas load forecasting. Deep learning has proven to be a powerful tool for many classification problems seeing significant use in machine learning fields such as image recognition and speech processing. We provide an overview of natural gas forecasting. Next, the deep learning method, contrastive divergence is explained. We compare our proposed deep neural network method to a linear regression model and a traditional artificial neural network on 62 operating areas, each of which has at least 10 years of data. The proposed deep network outperforms traditional artificial neural networks by 9.83% weighted mean absolute percent error (WMAPE).

In this paper, a maintenance cost study of transformers based on the Markov Model (MM) utilizing the Health Index (HI) is presented. In total, 120 distribution transformers of oil type (33/11 kV and 30 MVA) are examined. The HI is computed based on condition assessment data. Based on the HI, the transformers are arranged according to its corresponding states, and the transition probabilities are determined based on frequency of a transition approach utilizing the transformer transition states for the year 2013/2014 and 2012/2013. The future states of transformers are determined based on the MM chain algorithm. Finally, the maintenance costs are estimated based on future-state distribution probabilities according to the proposed maintenance policy model. The study shows that the deterioration states of the transformer population for the year 2015 can be predicted by MM based on the transformer transition states for the year 2013/2014 and 2012/2013. Analysis on the relationship between t... [more]

Demographic shift is a worldwide phenomenon, which is mainly common among industrialized nations. However, in the age of fast technology transfer and globalization policy makers cannot undervalue population aging in developing countries, like Pakistan. The relationship between population aging, combined with joint family system, and energy demand has gained importance in Pakistan during the recent times. On the basis of a detailed analysis of micro data spanning over period of 16 years, this study explores the role of generational behavior towards energy consumption, while considering the effects of cohort and age, along with other determinants of energy demand. The decomposition of energy consumption exhibits significant differences in cohort and age effects. The study concludes that, in addition to aging effects, policy makers cannot ignore the recent generation’s trends of spending increasingly more on energy than previous generations.

Implementing energy-efficient solutions in a built environment is important for reaching international energy reduction targets. For advanced energy efficiency-related solutions, computer-based decision support systems are proposed and rapidly used in a variety of spheres relevant to a built environment. Present research proposes a novel artificial neural network-based decision support system for development of an energy-efficient built environment. The system was developed by integrating methods of the multiple criteria evaluation and multivariant design, determination of project utility and market value, and visual data mining by artificial neural networks. It enables a user to compose up to 100,000,000 combinations of the energy-efficient solutions, analyze strengths and weaknesses of a built environment projects, provide advice for stakeholders, and calculate market value and utility degree of the projects. For visual data mining, self-organizing maps (type neural networks) are use... [more]

The period of industrialization and modernization has increased energy demands around the world. As with other countries, the Taiwanese government is trying to increase the proportion of renewable energy, especially solar energy resources. Thus, there are many solar power plants built in Taiwan. One of the most important components of a solar power plant is the solar panel. The solar panel supplier selection process is a complex and multi-faceted decision that can reduce the cost of purchasing equipment and supply this equipment on time. In this research, we propose fuzzy MCDM approach that includes fuzzy analytical hierarchy process model (FAHP) and data envelopment analysis (DEA) for evaluation and selection of solar panel supplier for a photovoltaic system design in Taiwan. The main objective of this work is to design a fuzzy MCDM approach for solar panel supplier selection based on qualitative and quantitative factors. In the first step of this research, FAHP is applied to define t... [more]

Distributed PV power generation necessitates both intra-hour and day-ahead forecasting of solar irradiance. The UTSA SkyImager is an inexpensive all-sky imaging system built using a Raspberry Pi computer with camera. Reconfigurable for different operational environments, it has been deployed at the National Renewable Energy Laboratory (NREL), Joint Base San Antonio, and two locations in the Canary Islands. The original design used optical flow to extrapolate cloud positions, followed by ray-tracing to predict shadow locations on solar panels. The latter problem is mathematically ill-posed. This paper details an alternative strategy that uses artificial intelligence (AI) to forecast irradiance directly from an extracted subimage surrounding the sun. Several different AI models are compared including Deep Learning and Gradient Boosted Trees. Results and error metrics are presented for a total of 147 days of NREL data collected during the period from October 2015 to May 2016.

Accurate generation prediction at multiple time-steps is of paramount importance for reliable and economical operation of wind farms. This study proposed a novel algorithmic solution using various forms of machine learning techniques in a hybrid manner, including phase space reconstruction (PSR), input variable selection (IVS), K-means clustering and adaptive neuro-fuzzy inference system (ANFIS). The PSR technique transforms the historical time series into a set of phase-space variables combining with the numerical weather prediction (NWP) data to prepare candidate inputs. A minimal redundancy maximal relevance (mRMR) criterion based filtering approach is used to automatically select the optimal input variables for the multi-step ahead prediction. Then, the input instances are divided into a set of subsets using the K-means clustering to train the ANFIS. The ANFIS parameters are further optimized to improve the prediction performance by the use of particle swarm optimization (PSO) algo... [more]

Wind energy is a commonly utilized renewable energy source, due to its merits of extensive distribution and rich reserves. However, as wind speed fluctuates violently and uncertainly at all times, wind power integration may affect the security and stability of power system. In this study, we propose an ensemble model for probabilistic wind speed forecasting. It consists of wavelet threshold denoising (WTD), recurrent neural network (RNN) and adaptive neuro fuzzy inference system (ANFIS). Firstly, WTD smooths the wind speed series in order to better capture its variation trend. Secondly, RNNs with different architectures are trained on the denoising datasets, operating as sub-models for point wind speed forecasting. Thirdly, ANFIS is innovatively established as the top layer of the entire ensemble model to compute the final point prediction result, in order to take full advantages of a limited number of deep-learning-based sub-models. Lastly, variances are obtained from sub-models and t... [more]

Medical data classification is an important factor in improving diagnosis and treatment and can assist physicians in making decisions about serious diseases by collecting symptoms and medical analyses. In this work, hybrid classification optimization methods such as Genetic Algorithm (GA), Particle Swam Optimization (PSO), and Fireworks Algorithm (FWA), are proposed for enhancing the classification accuracy of the Artificial Neural Network (ANN). The enhancement process is tested through two experiments. First, the proposed algorithms are applied on five benchmark medical data sets from the repository of the University of California in Irvine (UCI). The model with the best results is then used in the second experiment, which focuses on tuning the parameters of the selected algorithm by choosing a different number of iterations in ANNs with different numbers of hidden layers. Enhanced ANN with the three optimization algorithms are tested on biological gene sequence big dataset obtained... [more]

A phenomenological model was developed to describe the dynamic evolution of the batch suspension polymerization of methyl methacrylate in terms of reactor temperature, pressure, concentrations and molecular properties of the final polymer. Then, the phenomenological model was used as a process constraint in dynamic data reconciliation procedures, which allowed for the successful monitoring of reaction variables in real-time and on-line. The obtained results indicate that heat transfer coefficients change significantly during the reaction time and from batch to batch, exerting a tremendous impact on the process operation. Obtained results also indicate that it can be difficult to attain thermodynamic equilibrium conditions in this system, because of the continuous condensation of evaporated monomer and the large mass transfer resistance offered by the viscous suspended droplets.

Energy optimization in buildings by controlling the Heating Ventilation and Air Conditioning (HVAC) system is being researched extensively. In this paper, a model-free actor-critic Reinforcement Learning (RL) controller is designed using a variant of artificial recurrent neural networks called Long-Short-Term Memory (LSTM) networks. Optimization of thermal comfort alongside energy consumption is the goal in tuning this RL controller. The test platform, our office space, is designed using SketchUp. Using OpenStudio, the HVAC system is installed in the office. The control schemes (ideal thermal comfort, a traditional control and the RL control) are implemented in MATLAB. Using the Building Control Virtual Test Bed (BCVTB), the control of the thermostat schedule during each sample time is implemented for the office in EnergyPlus alongside local weather data. Results from training and validation indicate that the RL controller improves thermal comfort by an average of 15% and energy effici... [more]