SCOPUS

Permanent URI for this collection

https://irepository.uniten.edu.my/handle/123456789/21812

SCOPUS

Browse

Now showing 1 - 20 of 101

An adaptive te-pv hybrid energy harvesting system for self-powered iot sensor applications
(MDPI AG, 2021)
Mishu M.K.
;
Rokonuzzaman M.
;
Pasupuleti J.
;
Shakeri M.
;
Rahman K.S.
;
Binzaid S.
;
Tiong S.K.
;
Amin N.
;
57192669693
;
57190566039
;
11340187300
;
55433849200
;
56348138800
;
24824151500
;
15128307800
;
7102424614
In this paper, an integrated thermoelectric (TE) and photovoltaic (PV) hybrid energy harvesting system (HEHS) is proposed for self-powered internet of thing (IoT)-enabled wireless sensor networks (WSNs). The proposed system can run at a minimum of 0.8 V input voltage under indoor light illumination of at least 50 lux and a minimum temperature difference, ?T = 5? C. At the lowest illumination and temperature difference, the device can deliver 0.14 W of power. At the highest illumination of 200 lux and ?T = 13? C, the device can deliver 2.13 W. The developed HEHS can charge a 0.47 F, 5.5 V supercapacitor (SC) up to 4.12 V at the combined input voltage of 3.2 V within 17 s. In the absence of any energy sources, the designed device can back up the complete system for 92 s. The sensors can successfully send 39 data string to the webserver within this time at a two-second data transmission interval. A message queuing telemetry transport (MQTT) based IoT framework with a customised smartphone application �MQTT dashboard� is developed and integrated with an ESP32 Wi-Fi module to transmit, store, and monitor the sensors data over time. This research, therefore, opens up new prospects for self-powered autonomous IoT sensor systems under fluctuating environments and energy harvesting regimes, however, utilising available atmospheric light and thermal energy. � 2021 by the authors. Licensee MDPI, Basel, Switzerland.
Analysis of thermal models to determine the loss of life of mineral oil immersed transformers
(Institute of Advanced Engineering and Science, 2021)
Askari M.T.
;
Mohammadi M.J.
;
Pasupuleti J.
;
Tahmasebi M.
;
Raveendran S.K.
;
Ab Kadir M.Z.A.
;
36103897600
;
57288829600
;
11340187300
;
55945605900
;
57064141200
;
25947297000
Hot spot as well as top oil temperatures have played the most effective parameters on the life of the electrical transformers. The prognostication of these factors is very vital for determining the residual life of the electrical transformers in the transmission and distribution systems. Thus, an accurate mathematical method is required to calculate the critical temperature such as hot spot and top oil temperature based on the different types of thermal models. In this study calculates the service life of the transformers based on an accurate top oil temperature. Accordingly, An approach solution is given for calculating the thermal model. Also, findings are validated with true temperatures. Finally, this method is implemented on 2500 KVA electrical transformer. � 2021, Institute of Advanced Engineering and Science. All rights reserved.
Anticipatory response model for multi-agent based energy management system in a standalone microgrid
(Institute of Electrical and Electronics Engineers Inc., 2017)
Khan M.R.B.
;
Pasupuleti J.
;
Jidin R.
;
55812128900
;
11340187300
;
6508169028
In this paper, multi-agent architecture was used to provide control for standalone microgrid with distributed generations. Therefore, to achieve a faster control compared to the centralized controller, each agent incorporated with a local prediction or forecasting model to provide anticipatory responses. To accomplish their common goals successfully, the agents cooperated based on facilitator architecture with game-theory. Initially, the agents estimate its own parameters and dynamically adjust them by playing non-cooperative game with other agents. The predictive algorithm is based on autoregressive model where each agent will predict the load demand alongside renewable energy resources in order to dynamically regulate the control parameters. This will provide a faster response where the agents will anticipate future load demand and available renewable resources and adjust their parameters beforehand. Hence, this will minimize the fluctuations of voltage and frequency in the microgrid leading to more efficient power dispatch and lower power losses. � 2016 IEEE.
Application and assessment of internet of things toward the sustainability of energy systems: Challenges and issues
(Elsevier Ltd, 2020)
Khatua P.K.
;
Ramachandaramurthy V.K.
;
Kasinathan P.
;
Yong J.Y.
;
Pasupuleti J.
;
Rajagopalan A.
;
57211987923
;
6602912020
;
57194393495
;
56119339200
;
11340187300
;
57194865787
The availability of renewable energy sources along with the advancement of sensing and communication technologies has resulted in the sustainable operation of modern energy systems. An intelligent grid system is the integration of sensors and actuators, which enables the system to connect and exchange energy-related data from renewable sources to a computer system and end-users in a communication network. This data can be monitored in real-time with the help of the Internet of Things (IoT). However, several challenges exist in IoT, such as security, bandwidth management, interfacing interoperability, connectivity, packet loss, and data processing. In this paper, the key challenges and outstanding issues with the IoT when incorporated with energy systems are reviewed. The objective of this paper is to assess the suitability of different data transfer and communication protocols of IoT for deployment in the modern grid system. Moreover, several wireless IoT communication technologies are compared for their suitability in the multilayer network architecture and applications of energy systems. � 2019 Elsevier Ltd
Application Contingency Analysis of An IEEE 30 Bus System Using Matpower
(Institute of Physics, 2022)
Abedin T.
;
Aini N.
;
Sivanyanam D.D.
;
Pasupuleti J.
;
57226667845
;
57220356725
;
57884005400
;
11340187300
Contingency analysis is significant for power system protection. Internal component failures or external causes such as lightning and equipment overloading can cause power system contingencies. Multiple outage scenarios are crucial in today's deregulated environment for how the transmission network is utilized. The transmission network is highly pressured due to rising load demand and the need to operate economically. Contingency analysis of an IEEE 30 bus system is provided in this article utilizing Matpower software, which includes the source code. Matlab and Matpower are suggested as platforms for developing a screening process that examines the severity of each non-islanding branch failure, generator outage, MVA, and voltage violation. The generator terminal voltages will be permitted to fluctuate between 0.95 per unit and 1.05 per unit, as specified in the case30 input data files, to provide a broader practical zone. The performance index (PI) value is generated by adding the apparent performance index and the voltage performance index to rank the severity of the line outages. For the extreme contingency situation, a load flow study was performed. The four most severe scenarios, generator 22, generator 13, generator outage 23, and branch outage 28, should be constantly monitored to keep the electrical system safe. � Published under licence by IOP Publishing Ltd.
Assessing the Performance of Smart Inverter Functionalities in PV-Rich LV Distribution Networks
(Institute of Electrical and Electronics Engineers Inc., 2020)
Almeida D.
;
Pasupuleti J.
;
Ekanayake J.
;
57211718103
;
11340187300
;
7003409510
The overvoltage issue has been deemed as a significant technical challenge owing to the high integration of solar photovoltaic (PV) systems into the low voltage (LV) distribution networks. As a promising solution to this problem, smart inverter controls have gained attention in facilitating localized voltage control. In this paper, the effectiveness of three smart inverter functionalities namely; Volt-Var, Volt-Watt, and simultaneous Volt-Var and Volt-Watt controls have been analyzed and quantified in terms of multiple performance criterion. A detailed analysis has been conducted using a generic, Malaysian LV distribution network in order to demonstrate the applicability of adopting smart inverter controls in alleviating overvoltage issues in PV-rich LV networks. Results reveal that the usage of smart inverter controls help to mitigate overvoltage issues and support network operation conditions. Further, the results highlight the importance of selecting the most suitable control technique for a better network performance. � 2020 IEEE.
Automatic power factor correction using a harmonic-suppressed TCR equipped with a new adaptive current controller
(Korean Institute of Power Electronics, 2014)
Obais A.M.
;
Pasupuleti J.
;
53984961900
;
11340187300
In this paper, a new continuously and linearly controlled capacitive static VAR compensator is proposed for the automatic power factor correction of inductive single phase loads in 220V 50Hz power system networks. The compensator is constructed of a harmonic-suppressed TCR equipped with a new adaptive current controller. The harmonic-suppressed TCR is a new configuration that includes a thyristor controlled reactor (TCR) shunted by a passive third harmonic filter. In addition, the parallel configuration is connected to an AC source via a series first harmonic filter. The harmonic-suppressed TCR is designed so that negligible harmonic current components are injected into the AC source. The compensator is equipped with a new adaptive closed loop current controller, which responds linearly to reactive current demands. The no load operating losses of this compensator are negligible when compared to its capacitive reactive current rating. The proposed system is validated on PSpice which is very close in terms of performance to real hardware. © 2014 KIPE.
Automatic power factor correction using a modified statcom as a continuously controlled capacitive static VAR compensator
(Praise Worthy Prize S.r.l, 2012)
Obais A.M.
;
Pasupuleti J.
;
53984961900
;
11340187300
In this paper an automatic power factor correction system based on a new vision to statcom concept is presented. The reactive component of the load current is supplied by a statcom built of a halt-bridge voltage source inverter feeding a reactor and shunted by two dc capacitors. The passive components and control scheme of this configuration are approached in such a manner that the devised statcom behaves as pure capacitive impedance. The control strategy is based on governing the statcom current by its modulation index, while the passive components are designed such that all harmonic current harmonics are suppressed by the statcom reactor. The modulation index is controlled linearly by a precision gain-controlled linear amplifier which is specifically designed for this compensator and directly controlled by the load reactive current component. Modeling and performance of the proposed system was verified on PSpice. � 2012 Praise Worthy Prize S.r.l. - All rights reserved.
An Autonomous Home Energy Management System Using Dynamic Priority Strategy in Conventional Homes
(MDPI AG, 2020)
Shakeri M.
;
Amin N.
;
Pasupuleti J.
;
Mehbodniya A.
;
Asim N.
;
Tiong S.K.
;
Low F.W.
;
Yaw C.T.
;
Samsudin N.A.
;
Rokonuzzaman M.
;
Hen C.K.
;
Lai C.W.
;
55433849200
;
7102424614
;
11340187300
;
55954097400
;
55902096700
;
15128307800
;
56513524700
;
36560884300
;
57190525429
;
57190566039
;
36994481200
;
54879860000
With the growth in smart technology, customers have a chance to contribute to demand response programs and reduce their bills of electricity actively. This paper presents an intelligent wireless smart plug demonstration, which is designed to control the electrical appliances in the home energy management system (HEMS) application with a response to the utility company�s signal. Besides, a linear model of an energy management system utilizing a dynamic priority for electrical appliances is used as an energy management strategy. This can be useful for decreasing energy consumption in peak hours. Proposed hardware is tested with two different price strategies such as real-time pricing and a combination of this and incremental block rate (IBR) pricing. A small one-story house with ordinary electrical appliances is used as a test-bed for the proposed hardware and strategy. Initial results show that intelligent plugs can decrease the energy cost by 9% per day with an effective peak-to-average ratio deduction compared to the domicile without deploying intelligent plugs and controllers. � 2020 by the authors.
Battery Energy Storage System for PV Output Power Leveling
(Hindawi Limited, 2014)
Singh R.
;
Taghizadeh S.
;
Tan N.M.L.
;
Pasupuleti J.
;
57189853244
;
56483025000
;
24537965000
;
11340187300
Fluctuating photovoltaic (PV) output power reduces the reliability in power system when there is a massive penetration of PV generators. Energy storage systems that are connected to the PV generators using bidirectional isolated dc-dc converter can be utilized for compensating the fluctuating PV power. This paper presents a grid connected energy storage system based on a 2 kW full-bridge bidirectional isolated dc-dc converter and a PWM converter for PV output power leveling. This paper proposes two controllers: a current controller using the d-q synchronous reference and a phase-shift controller. The main function of the current controller is to regulate the voltage at the high-side dc, so that the voltage ratio of the high-voltage side (HVS) with low-voltage side (LVS) is equal to the transformer turns ratio. The phase-shift controller is employed to manage the charging and discharging modes of the battery based on PV output power and battery voltage. With the proposed system, unity power factor and efficient active power injection are achieved. The feasibility of the proposed control system is investigated using PSCAD simulation. © 2014 Rajkiran Singh et al.
BBO algorithm-based tuning of PID controller for speed control of synchronous machine
(Turkiye Klinikleri Journal of Medical Sciences, 2016)
Kasilingam G.
;
Pasupuleti J.
;
55812078500
;
11340187300
A biogeography-based optimization (BBO) algorithm was used for tuning the parameters of a proportional integral derivative (PID) controller-based power system stabilizer (PSS). The proposed method minimizes the low frequency electromechanical oscillations (0.1-2.5 Hz) and enhances the stability of the power system by optimally tuning the PID parameters. This was achieved by minimizing the objective function of the integral square error for various disturbances. The performance of the BBO algorithm was tested on a single machine infinite bus system for a different range of operating conditions and the results were compared with particle swam optimization, adaptation law, and conventional PSS. The result analysis concluded that the BBO algorithm damps out the low frequency oscillations in the rotor of the synchronous machine effectively when compared to other methods. The algorithms were simulated with MATLAB/Simulink. The results from the simulation showed that the proposed controller yields a fast convergence rate and better dynamic performance. � 2016 T�bitak.
A Brief Review on Radiant Cooling Panel with Different Chilled Water Pipe Configurations
(Penerbit Akademia Baru, 2022)
Radzai M.H.M.
;
Lim C.W.
;
Yaw C.T.
;
Koh S.P.
;
Ahmad N.A.
;
Shakeri M.
;
Pasupuleti J.
;
57226596398
;
35722335000
;
36560884300
;
22951210700
;
57220974921
;
55433849200
;
11340187300
Radiant cooling systems are commonly applied in commercial applications because of their energy-saving potential. This potential can be further enhanced by evaluating the cooling performance of the radiant cooling panel in terms of flow configurations. Although studies have been conducted on the flow configurations of the radiant cooling panel, the most suitable flow configurations have yet to be determined. The conventional serpentine flow configuration does not bring out the best cooling performance of the radiant cooling panel, therefore different flow configurations are still needed to be explored. This study conducted a quick literature review on the different radiant cooling systems as well as radiant cooling panel with different chilled water pipe configurations. The objective of this review is to provide a brief comparison of the performance of radiant cooling panel with different chilled water pipe configurations and to suggest further studies for the system development. The cooling characteristics and heat transfer of the panel are investigated by using numerical study. A comparison between the designs of flow configurations is presented. In all of the cases, the plate area and flow volume are fixed. Based on the findings obtained, applying a different chilled water pipe configuration on the radiant cooling panel will affect the flow uniformity and also the temperature distribution uniformity. An optimized flow configurations for the radiant cooling panel is important for enhancing the overall efficiency of the system � 2022,Journal of Advanced Research in Fluid Mechanics and Thermal Sciences.All Rights Reserved
Building automation: Photovoltaic assisted thermal comfort management system for energy saving
(Institute of Physics Publishing, 2013)
Khan M.R.B.
;
Jidin R.
;
Pasupuleti J.
;
Shaaya S.A.
;
55812128900
;
6508169028
;
11340187300
;
16022846200
Building automation plays an important key role in the means to reduce building energy consumption and to provide comfort for building occupants. It is often that air conditioning system operating features ignored in building automation which can result in thermal discomfort among building occupants. Most automation system for building is expensive and incurs high maintenance cost. Such system also does not support electricity demand side management system such as load shifting. This paper discusses on centralized monitoring system for room temperature and photovoltaic (PV) output for feasibility study of PV assisted air conditioning system in small office buildings. The architecture of the system consists of PV modules and sensor nodes located at each room. Wireless sensor network technology (WSN) been used for data transmission. The data from temperature sensors and PV modules transmitted to the host personal computer (PC) wirelessly using Zigbee modules. Microcontroller based USB data acquisition device used to receive data from sensor nodes and displays the data on PC. � Published under licence by IOP Publishing Ltd.
Combined heat and power (CHP) economic dispatch solved using Lagrangian relaxation with surrogate subgradient multiplier updates
(2013)
Sashirekha A.
;
Pasupuleti J.
;
Moin N.H.
;
Tan C.S.
;
55363578100
;
11340187300
;
6507487566
;
55363559700
This paper presents a flexible algorithm to solve the combined heat and power (CHP) economic dispatch problem. The CHP economic dispatch is solved in two levels known as the lower level and higher level. The higher level is the optimization of the surrogate dual function for the relaxed global constraints in which the surrogate subgradient is used to update the Lagrangian multipliers. Coherently, the lower levels are the optimization of the subproblems taking in count each of its local constraints. Flexibility for the choice of algorithm is given at the lower levels optimization techniques with the condition that the algorithm is able to improve its search at each iteration. It is also seen that simple step size rules such as the 'square summable but not summable' and 'constant step size' could be used easily and leads the method to convergence. In addition this paper illustrates the ear clipping method used to modify the common nonconvex feasible region of CHP benchmark problems to a convex region which subsequently enhances the search for an optimal solution. The algorithm is then justified through a numerical test on three benchmark CHP problem with a nonconvex feasible region. Results prove that the algorithm is reliable and could be easily implemented even on a much complex and nonconvex problems. � 2012 Elsevier Ltd. All rights reserved.
Comparative Analysis of Smart Grid Solar Integration in Urban and Rural Networks
(Multidisciplinary Digital Publishing Institute (MDPI), 2023)
Maghami M.R.
;
Pasupuleti J.
;
Ling C.M.
;
56127745700
;
11340187300
;
58187587300
Solar photovoltaic (PV) power, a highly promising renewable energy source, encounters challenges when integrated into smart grids. These challenges encompass voltage fluctuations, issues with voltage balance, and concerns related to power quality. This study aims to comprehensively analyze the implications of solar PV penetration in Malaysian power distribution networks predominantly found in urban and rural areas. To achieve this, we employed the OpenDSS 2022 and MATLAB 2022b software tools to conduct static power flow analyses, enabling us to assess the effects of solar PV integration over a wide area under two worst-case scenarios: peak-load and no-load periods. Our investigation considered voltage violations, power losses, and fault analysis relative to the power demand of each scenario, facilitating a comprehensive evaluation of the impacts. The findings of our study revealed crucial insights. We determined that the maximum allowable power for both urban and rural networks during no-load and peak-load situations is approximately 0.5 MW and 0.125 MW, respectively. Moreover, as the percentage of PV penetration increases, notable reductions in power losses are observed, indicating the potential benefits of higher smart grid PV integration. � 2023 by the authors.
A Comparative Performance Analysis of ANN Algorithms for MPPT Energy Harvesting in Solar PV System
(Institute of Electrical and Electronics Engineers Inc., 2021)
Roy R.B.
;
Rokonuzzaman M.
;
Amin N.
;
Mishu M.K.
;
Alahakoon S.
;
Rahman S.
;
Mithulananthan N.
;
Rahman K.S.
;
Shakeri M.
;
Pasupuleti J.
;
56603588300
;
57190566039
;
7102424614
;
57192669693
;
6508134705
;
57194406794
;
56246076300
;
56348138800
;
55433849200
;
11340187300
In this paper, artificial neural network (ANN) based Levenberg-Marquardt (LM), Bayesian Regularization (BR) and Scaled Conjugate Gradient (SCG) algorithms are deployed in maximum power point tracking (MPPT) energy harvesting in solar photovoltaic (PV) system to forge a comparative performance analysis of the three different algorithms. A comparative analysis among the algorithms in terms of the performance of handling the trained dataset is presented. The MATLAB/Simulink environment is used to design the maximum power point tracking energy harvesting system and the artificial neural network toolbox is utilized to analyze the developed model. The proposed model is trained with 1000 dataset of solar irradiance, temperature, and voltages. Seventy percent data is used for training, while 15% data is employed for validation, and 15% data is utilized for testing. The trained datasets error histogram represents zero error in the training, validation, and test phase of data matching. The best validation performance is attained at 1000 epochs with nearly zero mean squared error where the trained data set is converged to the best training results. According to the results, the regression and gradient are 1, 1, 0.99 and 0.000078, 0.0000015739 and 0.26139 for Levenberg-Marquardt, Bayesian Regularization and Scaled Conjugate Gradient algorithms, respectively. The momentum parameters are 0.0000001 and 50000 for Levenberg-Marquardt and Bayesian Regularization algorithms, respectively, while the Scaled Conjugate Gradient algorithm does not have any momentum parameter. The Scaled Conjugate Gradient algorithm exhibit better performance compared to Levenberg-Marquardt and Bayesian Regularization algorithms. However, considering the dataset training, the correlation between input-output and error, the Levenberg-Marquardt algorithm performs better. � 2013 IEEE.
A comparative study of the Z-N, adaptation law and PSO methods of tuning the PID controller of a synchronous machine
(Praise Worthy Prize S.r.l, 2014)
Kasilingam G.
;
Pasupuleti J.
;
55812078500
;
11340187300
A proportional–integral–derivative (PID)-based power system stabilizer (PSS) was designed to damp low-frequency oscillations in power systems under different operating conditions. The parameters of the PID controller were tuned using a particle swarm optimization (PSO) algorithm. The performance of the PSO-PID-type PSS was thoroughly investigated and compared with those of the Ziegler–Nichols (Z-N) and adaptation law methods. The effectiveness of the PSO-PID with PSS is applied to a single-machine infinite-bus system connected to a nonlinear load with different kinds of faults. The variations in the speed deviation, rotor angle and load angle were compared in a Simulink based MATLAB environment. The damping performance of the PSO-PID controller over a wide range of operating conditions is excellent. © 2014 Praise Worthy Prize S.r.l. - All rights reserved.
Comparison of reactive power control techniques for solar pv inverters to mitigate voltage rise in low-voltage grids
(MDPI AG, 2021)
Almeida D.
;
Pasupuleti J.
;
Ekanayake J.
;
57211718103
;
11340187300
;
7003409510
The greater integration of solar photovoltaic (PV) systems into low-voltage (LV) distribution networks has posed new challenges for the operation of power systems. The violation of voltage limits attributed to reverse power flow has been recognized as one of the significant consequences of high PV penetration. Thus, the reactive power control of PV inverters has emerged as a viable solution for localized voltage regulation. This paper presents a detailed study on a typical Malaysian LV distribution network to demonstrate the effectiveness of different reactive power control techniques in mitigating overvoltage issues due to high PV integration. The performance of four reactive power control techniques namely, fixed power factor control, scheduled power factor control, power factor control as a function of injected active power, and voltage-dependent reactive power control were analyzed and compared in terms of the number of customers with voltage violations, reactive power compensation, and network losses. Three-phase, time-series, high-resolution power-flow simulations were performed to investigate the potential overvoltage issues and to assess the performance of the adoption of reactive power controls in the network. The simulation results re-vealed that the incorporation of reactive power controls of solar PV inverters aids in successfully mitigating the overvoltage issues of typical Malaysian networks. In particular, the Volt-Var control outperformed the other control techniques by providing effective voltage regulation while requir-ing less reactive power compensation. Furthermore, the comparative analysis highlighted the sig-nificance of employing the most appropriate control technique for improved network performance. � 2021 by the authors. Licensee MDPI, Basel, Switzerland.
Comprehensive learning particle swarm optimization for sizing and placement of distributed generation for network loss reduction
(Institute of Advanced Engineering and Science, 2020)
Karunarathne E.
;
Pasupuleti J.
;
Ekanayake J.
;
Almeida D.
;
57216633155
;
11340187300
;
7003409510
;
57211718103
With the technological advancements, distributed generation (DG) has become a common method of overwhelming the issues like power losses and voltage drops which accompanies with the leaf of the feeders of radial distribution networks. Many researchers have used several optimization techniques and tools which could be used to locate and size the DG units in the system. Particle swarm optimization (PSO) is one of the famous optimization techniques. However, the premature convergence is identified as a fundamental adverse effect of this optimization technique. Therefore, the optimization problem can direct the objective function to a local minimum. This paper presents a variant of PSO techniques, "comprehensive learning particle swarm optimization (CLPSO)"to determine the optimal placement and sizing of the DGs, which uses a novel learning strategy whereby all other particles' historical best information and learning probability value are used to update a particle's velocity. The CLPSO particles learn from one exampler for few iterations, instead of learing from global and personal best values in every iteration in PSO and this technique retains the swarm's variability to avoid premature convergence. A detailed analysis was conducted for the IEEE 33 bus system. The comparison results have revealed a higher convergence and an accuracy than the PSO. Copyright � 2020 Institute of Advanced Engineering and Science. All rights reserved.
A comprehensive study and performance analysis of deep neural network-based approaches in wind time-series forecasting
(Springer Science and Business Media Deutschland GmbH, 2022)
Rahman M.M.
;
Shakeri M.
;
Khatun F.
;
Tiong S.K.
;
Alkahtani A.A.
;
Samsudin N.A.
;
Amin N.
;
Pasupuleti J.
;
Hasan M.K.
;
57207730841
;
55433849200
;
57516189300
;
15128307800
;
55646765500
;
57190525429
;
7102424614
;
11340187300
;
55057479600
The increasing energy demand and expansion of power plants are provoking the effects of greenhouse gas emissions and global warming. To mitigate these issues, renewable energies (like solar, wind, and hydropower) are blessings for modern energy sectors. The study focuses on wind-speed prediction in energy forecasting applications. This paper is a comprehensive review of deep neural network based approaches, like the �nonlinear autoregressive exogenous inputs (NARX)�, �nonlinear input-output (NIO)� and �nonlinear autoregressive (NAR)� neural network models, in time-series forecasting applications. This study proposed NARX based prediction models in wind-speed forecasting for short-term scheme. The meteorological parameters related to wind time-series have been analyzed, and used for evaluating the performance of the proposed models. The experiments revealed the best performance of the prediction models in terms of �mean square error (MSE)�, �correlation-coefficient (R2)�, �auto-correlation�, �error-histogram�, and �input-error cross-correlation�. Comparing with the other neural network models, like �recurrent neural network (RNN)� and �curve fitting neural network (CFNN)� models, the NARX-based prediction model achieved better performance in regard to �auto-correlation�, �error-histogram�, �input-error cross-correlation�, and training time. The results also showed that the RNN and CFNN models performed better prediction accuracy with R2 and MSE values. While this performance index is slightly higher, it is negligible in forecasting applications and concluded that the proposed NARX-based model achieved the better prediction accuracy in terms of other performance evaluation measures. � 2022, The Author(s), under exclusive licence to Springer Nature Switzerland AG.

Browse

Browsing SCOPUS by Author "11340187300"

Results Per Page

Sort Options