Since wind power is directly influenced by wind speed, long-term wind speed forecasting (WSF) plays an important role for wind farm installation. WSF is essential for controlling, energy management and scheduled wind power generation in wind farm. The proposed investigation in this paper provides 30-days-ahead WSF. Nonlinear Autoregressive (NAR) and Nonlinear Autoregressive Exogenous (NARX) Neural Network (NN) with different network settings have been used to facilitate the wind power generation. The essence of this study is that it compares the effect of activation functions (namely, tansig and logsig) in the performance of time series forecasting since activation function is the core element of any artificial neural network model. A set of wind speed data was collected from different meteorological stations in Malaysia, situated in Kuala Lumpur, Kuantan, and Melaka. The proposed activation functions tansig of NARNN and NARXNN resulted in promising outcomes in terms of very small error between actual and predicted wind speed as well as the comparison for the logsig transfer function results.

This study aims to review the potential benefits of peak load shaving in a microgrid system. The relevance of peak shaving for a microgrid system is presented in this research review at the outset to justify the peak load shaving efficacy. The prospective benefits of peak shaving in microgrid systems, including technological, economic, and environmental advantages, are thoroughly examined. This review study also presents a cost–benefit numerical analysis to illustrate the economic viability of peak load shaving for a microgrid system. Different peak shaving approaches are briefly discussed, as well as the obstacles of putting them into practice. Finally, this review study reveals some potential future trends and possible directions for peak shaving research in microgrid systems. This review paper lays a strong foundation for identifying the potential benefits of peak shaving in microgrid systems and establishing suitable projects for practical effectuation.

No abstract

No abstract

Blade design of the horizontal axis wind turbine (HAWT) is an important parameter that determines the reliability and efficiency of a wind turbine. It is important to optimize the capture of the energy in the wind that can be correlated to the power coefficient ( C p ) of HAWT system. In this paper, nature-inspired algorithms, e.g., ant colony optimization (ACO), artificial bee colony (ABC), and particle swarm optimization (PSO) are used to search for the blade parameters that can give the maximum value of C p for HAWT. The parameters are tip speed ratio, blade radius, lift to drag ratio, solidity ratio, and chord length. The performance of these three algorithms in obtaining the optimal blade design based on the C p are investigated and compared. In addition, an adaptive neuro-fuzzy interface (ANFIS) approach is implemented to predict the C p of wind turbine blades for investigation of algorithm performance based on the coefficient determination (R2) and root mean square error (RMSE). The optimized blade design parameters are validated with experimental results from the National Renewable Energy Laboratory (NREL). It was found that the optimized blade design parameters were obtained using an ABC algorithm with the maximum value power coefficient higher than ACO and PSO. The predicted C p using ANFIS-ABC also outperformed the ANFIS-ACO and ANFIS-PSO. The difference between optimized and predicted is very small which implies the effectiveness of nature-inspired algorithms in this application. In addition, the value of RMSE and R2 of the ABC-ANFIS algorithm were lower (indicating that the result obtained is more accurate) than the ACO and PSO algorithms.

No abstract

Peak load reduction is one of the most essential obligations and cost-effective tasks for electrical energy consumers. An isolated microgrid (IMG) system is an independent limited capacity power system where the peak shaving application can perform a vital role in the economic operation. This paper presents a comparative analysis of a categorical variable decision tree algorithm (CVDTA) with the most common peak shaving technique, namely, the general capacity addition technique, to evaluate the peak shaving performance for an IMG system. The CVDTA algorithm deals with the hybrid photovoltaic (PV)—battery energy storage system (BESS) to provide the peak shaving service where the capacity addition technique uses a peaking generator to minimize the peak demand. An actual IMG system model is developed in MATLAB/Simulink software to analyze the peak shaving performance. The model consists of four major components such as, PV, BESS, variable load, and gas turbine generator (GTG) dispatch models for the proposed algorithm, where the BESS and PV models are not applicable for the capacity addition technique. Actual variable load data and PV generation data are considered to conduct the simulation case studies which are collected from a real IMG system. The simulation result exhibits the effectiveness of the CVDTA algorithm which can minimize the peak demand better than the capacity addition technique. By ensuring the peak shaving operation and handling the economic generation dispatch, the CVDTA algorithm can ensure more energy savings, fewer system losses, less operation and maintenance (O&M) cost, etc., where the general capacity addition technique is limited.

In this work, the optimization of an off-grid micro-hybrid system is evaluated. This is conducted with the estimation of the proper sizing of each element and the steady-state voltage, frequency, and power responses of the microgrid. Kangaroo Island in South Australia is considered to be the test case location and the grid incorporates solar PV (photo-voltaic), diesel generator, battery storage, and wind turbine. Optimal sizing of the studied microgrid is carried out for four various power dispatch techniques: (i) cycle charging (CC), (ii) generator order (GO), (iii) load following (LF), and (iv) combined dispatch (CD). The proposed off-grid micro-hybrid is optimized for three performance indices; minimal Levelized Cost of Energy (LCOE), CO2 emission, and Net Present Cost (NPC). Using iHOGA (improved hybrid optimization by genetic algorithm), microgrid optimization software, all the above-mentioned dispatch strategies have been implemented and following this, MATLAB/Simulink platform has been used for the steady-state studies. The results show that the LF strategy is the utmost optimum dispatch technique in terms of the studied performance indices i.e. considering the optimal size and voltage and frequency responses. The results obtained from these studies provide a pathway for the estimation of the resource-generation-load combination for the islanded off-grid microgrid for its optimal operation with the various dispatch strategies.