Analysis of wind power generation and prediction using ANN: A case study

Many developing nations, such as India have embarked upon wind energy programs for areas experiencing high average wind speeds throughout the year. One of the states in India that is actively pursuing wind power generation programs is Tamil Nadu. Within this state, Muppandal area is one of the identified regions where wind farm concentration is high. Wind energy engineers are interested in studies that aim at assessing the output of wind farms, for which, artificial intelligence techniques can be usefully adapted. The present paper attempts to apply this concept for assessment of the wind energy output of wind farms in Muppandal, Tamil Nadu (India). Field data are collected from seven wind farms at this site over a period of 3 years from April 2002 to March 2005 and used for the analysis and prediction of power generation from wind farms. The model has been developed with the help of neural network methodology. It involves three input variables—wind speed, relative humidity and generation hours and one output variable-energy output of wind farms. The modeling is done using MATLAB toolbox. The model accuracy is evaluated by comparing the simulated results with the actual measured values at the wind farms and is found to be in good agreement.     

Comparison of modeling methods for wind power prediction: a critical study

Prediction of power generation of a wind turbine is crucial, which calls for accurate and reliable models. In this work, six different models have been developed based on wind power equation, concept of power curve, response surface methodology (RSM) and artificial neural network (ANN), and the results have been compared. To develop the models based on the concept of power curve, the manufacturer’s power curve, and to develop RSM as well as ANN models, the data collected from supervisory control and data acquisition (SCADA) of a 1.5 MW turbine have been used. In addition to wind speed, the air density, blade pitch angle, rotor speed and wind direction have been considered as input variables for RSM and ANN models. Proper selection of input variables and capability of ANN to map input-output relationships have resulted in an accurate model for wind power prediction in comparison to other methods.     

Impact of wind power generating system integration on frequency stabilization in multi-area power system with fuzzy logic controller in deregulated environment

Among the available options for renewable energy integration in existing power system, wind power is being considered as one of the suited options for future electrical power generation. The major constraint of wind power generating system (WPGS) is that it does not provide inertial support because of power electronic converters between the grid and the WPGS to facilitate frequency stabilization. The proposed control strategy suggests a substantial contribution to system inertia in terms of short-term active power support in a two area restructured power system. The control scheme uses fuzzy logic based design and takes frequency deviation as input to provide quick active power support, which balances the drop in frequency and tie-line power during transient conditions. This paper presents a comprehensive study of the wind power impact with increasing wind power penetration on frequency stabilization in restructured power system scenario. Variation of load conditions are also analyzed in simulation studies for the same power system model with the proposed control scheme. Simulation results advocates the justification of control scheme over other schemes.     

Double diffusive Buoyancy-driven flow in a fluid-saturated elliptical annulus with a neural network-based prediction of heat and mass transfer

This paper presents a numerical study of buoyancy-driven double-diffusive convection within an elliptical annulus enclosure filled with a saturated porous medium. An in-house built FORTRAN code has been developed, and computations are carried out in a range of values of Darcy–Rayleigh number Ra_m (10 ≤ Ra_m ≤ 500), Lewis number Le (0.1 ≤ Le ≤ 10), and the ratio of buoyancy forces N (−5 ≤ N ≤ 5). In addition, three methods are used, namely the multi-variable polynomial regression, the group method of data handling (GMDH), and the artificial neural network (ANN) for the predictions of heat and mass transfer rates. First, results are successfully validated with existing numerical and experimental data. Then, the results indicated that temperature and concentration distributions are sensitive to the Lewis number and thermal and mass plumes are developing in proportion to the Lewis number. Two particular values of Lewis number Le = 2.735 and Le = 2.75 captured the flow's transition toward an asymmetric structure with a bifurcation of convective cells. The average Nusselt number tends to have an almost asymptotic value for Le » 5. For the case of aiding buoyancies N > 1, the average Nusselt Number $\overline{\mathit{Nu}}$ decreased by 33% when the Lewis number increased to its maximum value. Then, it increased by 10% when the Lewis number increased to Le = 1 for the case of opposing buoyancies N < 1 and then decreased by 33% when the Lewis number increased to its maximum value., contrary to the behavior of the average Sherwood number $\overline{\mathit{Sh}}$ that increased by 700% for both cases N > 1 and N < 1. New correlations of $\overline{\mathit{Nu}}$, and $\overline{\mathit{Sh}}$ as a function of Ra_m, Le, and N are derived and compared with GMDH and ANN methods, and the ANN method showed higher performance for the prediction of $\overline{\mathit{Nu}}$ and $\overline{\mathit{Sh}}$ with R² exceeding 0.99.     

Experimental investigation and ANN modeling on improved performance of an innovative method of using heave response of a non-floating object for ocean wave energy conversion

To convert wave energy into usable forms of energy by utilizing heaving body, heaving bodies (buoys) which are buoyant in nature and float on the water surface are usually used. The wave exerts excess buoyancy force on the buoy, lifting it during the approach of wave crest while the gravity pulls it down during the wave trough. A hydraulic, direct or mechanical power takeoff is used to convert this up and down motion of the buoy to produce usable forms of energy. Though using a floating buoy for harnessing wave energy is conventional, this device faces many challenges in improving the overall conversion efficiency and survivability in extreme conditions. Up to the present, no studies have been done to harness ocean waves using a non-floating object and to find out the merits and demerits of the system. In the present paper, an innovative heaving body type of wave energy converter with a non-floating object was proposed to harness waves. It was also shown that the conversion efficiency and safety of the proposed device were significantly higher than any other device proposed with floating buoy. To demonstrate the improvements, experiments were conducted with non-floating body for different dimensions and the heave response was noted. Power generation was not considered in the experiment to observe the worst case response of the heaving body. The device was modeled in artificial neural network (ANN), the heave response for various parameters were predicted, and compared with the experimental results. It was found that the ANN model could predict the heave response with an accuracy of 99%.     

Sustainable personnel scheduling supported by an artificial neural network model in a natural gas combined cycle power plant

Despite the impact of personnel scheduling on the sustainability of production processes, it is a rarely studied problem in the electricity generation sector, whose main purpose is sustainable energy generation. From this point of view, personnel scheduling problem is handled in this study based on the impact of this problem, which focuses on fair and balanced job distribution according to the personnel qualifications, on the sustainable generation in the power plants. With its advantages such as ease of operation and maintenance, fast commissioning, lower greenhouse gas emissions compared to other fossil fuels and etc. one of the biggest Natural Gas Combined Cycle Power Plant (NGCCPP) in Turkey is chosen as application area. The main purpose of the study is to demonstrate the effect of fair, balanced and competency-based personnel scheduling on generation stoppages resulting from personnel planning in power plants, which have great importance in energy supply security of the countries. This study is the first in the literature in terms of three different aspects. Firstly, in the energy sector, it is different in that it is a personnel scheduling study that takes into consideration the job assignment of the personnel according to their abilities and minimizes costs. Secondly, the large size of the problem is different from that of previous studies in the literature. Finally, the number of personnel employed in this generation facility varies according to the season. At this point, the past generation data are analyzed using an Artificial Neural Network (ANN) method and an estimation is made, and personnel scheduling is performed in the light of this information. Consequently, the proposed multi-objective mathematical model supported with multi-criteria decision making and ANN, shutdown rate of the power plant due to operator error is reduced 67.3%, and personnel satisfaction level is increased from 42% to 89%as solution.     

Wind speed prediction in the mountainous region of India using an artificial neural network model

Measured wind speed data are not available for most sites in the mountainous regions of India. The objective of present study is to predict wind speeds for 11 locations in the Western Himalayan Indian state of Himachal Pradesh to identify possible wind energy applications. An artificial neural network (ANN) model is used to predict wind speeds using measured wind data of Hamirpur location for training and testing. Temperature, air pressure, solar radiation and altitude are taken as inputs for the ANN model to predict daily mean wind speeds. Mean absolute percentage error (MAPE) and correlation coefficient between the predicted and measured wind speeds are found to be 4.55% and 0.98 respectively. Predicted wind speeds are found to range from 1.27 to 3.78 m/s for Bilaspur, Chamba, Kangra, Kinnaur, Kullu, Keylong, Mandi, Shimla, Sirmaur, Solan and Una locations. A micro-wind turbine is used to assess the wind power generated at these locations which is found to vary from 773.61 W to 5329.76 W which is suitable for small lighting applications. Model is validated by predicting wind speeds for Gurgaon city for which measured data are available with MAPE 6.489% and correlation coefficient 0.99 showing high prediction accuracy of the developed ANN Model.     

Study of flow field,heat transfer,and entropy generation of nanofluid turbulent natural convection in an enclosure utilizing the computational fluid dynamics‐artificial neural network hybrid method

In this study, the turbulent natural convection of Ag‐water nanofluid in a tall, inclined enclosure has been investigated. The main objective of this study is finding the optimized angle of the enclosure with operational boundary condition in cooling from ceiling utilizing the computational fluid dynamics‐artificial neural network (CFD‐ANN) hybrid method, which has not been noticed in previous studies. To achieve this, we proposed two approaches. First, the simulations have been done with a deviation angle of 0 to 90° by using water and Ag‐water nanofluid. And second, a new prediction approach is proposed based on radial basis function artificial neural networks (RBF‐ANN) to predict the mean Nusselt number and entropy generation with the variation of Rayleigh numbers, deviation angles, and volume fractions as inputs. The results from the first approach indicate that the Rayleigh number has a considerable function in the determination of optimized angle. The results from the second approach, which used the first approach simulation results as training data set, could predict the mean Nusselt number and entropy generation with 1.4577e^?022 and 1.552e^?015 mean square error, respectively. Moreover, a new set of data for Rayleigh numbers, deviation angles, and volume fractions were used to test the performance of the prediction model, which shows promising and superior prospects for RBF‐ANN.     

Application of adaptive neuro-fuzzy inference system techniques and artificial neural networks to predict solid oxide fuel cell performance in residential microgeneration installation

This study applies adaptive neuro-fuzzy inference system (ANFIS) techniques and artificial neural network (ANN) to predict solid oxide fuel cell (SOFC) performance while supplying both heat and power to a residence. A microgeneration 5 kW_el SOFC system was installed at the Canadian Centre for Housing Technology (CCHT), integrated with existing mechanical systems and connected in parallel to the grid. SOFC performance data were collected during the winter heating season and used for training of both ANN and ANFIS models. The ANN model was built on back propagation algorithm as for ANFIS model a combination of least squares method and back propagation gradient decent method were developed and applied. Both models were trained with experimental data and used to predict selective SOFC performance parameters such as fuel cell stack current, stack voltage, etc.     

Maximum efficiency point tracking for an ocean thermal energy harvesting system

Limited energy is the most critical factor that restricts the persistent presence of underwater vehicles in the oceans; thus, harvesting the ocean's thermal energy that is stored in the water column between the sea surface and deep water is a particularly promising solution for the current power shortage. This paper has designed a new ocean thermal energy conversion system which using phase change material as energy storage medium, and proposed a novel maximum efficiency point tracking (MEPT) method for energy conversion. This new method, which is integrated with a radial basis function neural network (RBFNN), particle swarm optimization (PSO) and the proportion integration differentiation (PID) control method, could effectively improve the efficiency of energy conversion. Compared with the power generation system that does not use the MEPT method, experimental results show that the proposed method can improve the efficiency of the power generation from less than 19.05% to more than 34.3% and has higher stability (using this method: the efficiency changes from 34.3%-34.7%; without using this method: the efficiency changes from 13.56% -19.05%) when the load changes. This novel method can be used in many conditions, especially when the mathematical model of the generation system is unknown or researchers want to use fewer sensors for maximum efficiency point tracking.     

A novel sensorless current shaping control approach for SVPWM inverter with voltage disturbance rejection in a dc grid–based wind power generation system

A novel sensorless current shaping (CS) control strategy is proposed to avail better power quality (PQ) of a dc grid–based wind power generation system (WPGS) used on a poultry farm by generating an appropriate reference current for space vector pulse width modulation (SVPWM) inverter. The proposed CS strategy also offers adequate control for parallel operation of multiple generators and inverter applications, without requiring voltage and frequency synchronization. Further, to control the poultry farm–based WPGS, a two‐stage control loop is implemented such as energy flow control loop (EFCL) and harmonic control loop (HCL). The first loop is used to regulate the power flow, and the second loop is used to compensate harmonics. A mathematical current decomposition technique is suggested for an appropriate resistance emulation to realize a better power flow, higher harmonic rejection, and better inverter operation. In this planned approach for attaining constant wind speed, an electric ventilation fan in the poultry farm is used. A combined hybrid dc and ac grid approaches are suggested for facilitating variable load integration in a poultry farm–based microgrid system. Moreover, for achieving better power management during the islanded mode of operation, the battery energy storage (BES) device is integrated with the dc grid through a bidirectional converter. The proposed WPGS design and control approach has been simulated through MATLAB/Simulink software under various test conditions, to demonstrate the operational capability, to achieve better PQ, and to increase the flexibility and reliability in the microgrid operation.