Short-term forecasting tool for wind power generation (WPG) can effectively enhance the scheduling of dispatchable generation and avoid wind power (WP) curtailment. This paper presents a Group Method of Data Handling (GMDH)-Neural Network (NN) approach for forecasting wind speed (Ws) and wind power output (WPO) in the short-term. Wavelet denoising is used to filter the high frequency outliers in the Ws data, consequently, enabling a smooth training of NN on Ws. The performance of the wavelet denoising-GMDH-NN investigated using historical Ws and WPO. The results highlight that GMDH-NN performs well for Ws prediction and that the use of wavelet denoising with GMDH-NN results in a higher precision and lower errors, thus improving the prediction accuracy.
Forecasting of intermittent solar photovoltaic (PV) and wind resources is crucial for future power system efficient operation. This paper presents the use of Adaptive Neuro Fuzzy Inference System (ANFIS) approach for predicting wind and PV power outputs of the isolated Adrar's power system. The model formed by using real numerical weather measurements (wind speed, temperature, pressure, humidity, and solar irradiation), taken as input variables, and power outputs values as the output. Besides, metrics to calculate the Mean Absolute Error (MAE), Mean Square Error (MSE), and Root Mean Square Error (RMSE), have applied to denote forecast accuracy. The result verifies that ANFIS has a good perfection, and can be used as a reliable tool for modelling and prediction renewable energies.
This article presents a new efficient method for optimal placement and sizing of wind power generators (WPG) in power networks with an objective of coping maximum loadability margin and minimizing reactive power loss. A new total voltage stability based on continuation power flow (CPF) theorem is used to model the problem. The method also highlights the effects of random characteristics of wind resources on loadability margin. Cuckoo search algorithm is applied to find the optimum placement and sizing of WPG since it presents several advantages of few control parameters, high solution quality and fast computational time. The experiment results of IEEE 9-bus show that the optimum location and size of WPGs are different from those considering power system loss and voltage deviation in objective function of the optimization process. A significant effect of the random characteristic of wind resource during load demand growth is revealed. The simulation results show that the CSA can be an efficient and promising method for optimal placement and sizing of WPG in power networks problem.
New concepts of power generation have been modified since the advent of the terminology of the microgrid. In which the latter allows the clustering of many distributed generation units, storage systems along with power electronic converters and loads where all the previous units are connected to/disconnected from the distribution level at one point called point of common coupling (PCC) via a static transfer switch. This new paradigm enables to resolve many technical, economical, and environmental issues. However, the weakest link in the microgrid is the storage systems and how they work together to feed properly loads in islanded or grid-connected modes. In this context, this paper proposes a microgrid constituted of two flywheel energy storage systems (FESS) where each one of them can be connected either to a photovoltaic (PV) array or to a wind turbine. The sharing power within the studied microgrid is relied on the droop control method. The simulation results have been carried out using MATLAB/Simulink software and have proved the effectiveness of the proposed control to meet the load needs in an equal manner without resorting to the use to communications link between different units based mainly on FESS.