Estimation of wind speed profile using adaptive neuro-fuzzy inference system (ANFIS)

Abstract

a b s t r a c tWind energy has become a major competitor of traditional fossil fuel energy, particularly with the successful operation of multi-megawatt sized wind turbines. However, wind with reasonable speed is not adequately sustainable everywhere to build an economical wind farm. The potential site has to be thoroughly investigated at least with respect to wind speed profile and air density. Wind speed increases with height, thus an increase of the height of turbine rotor leads to more generated power. Therefore, it is imperative to have a precise knowledge of wind speed profiles in order to assess the potential for a wind farm site. This paper proposes a clustering algorithm based neuro-fuzzy method to find wind speed profile up to height of 100 m based on knowledge of wind speed at heights 10, 20, 30, 40 m. The model estimated wind speed at 40 m based on measured data at 10, 20, and 30 m has 3% mean absolute percent error when compared with measured wind speed at height 40 m. This close agreement between estimated and measured wind speed at 40 m indicates the viability of the proposed method. The comparison with the 1/7th law and experimental wind shear method further proofs the suitability of the proposed method for generating wind speed profile based on knowledge of wind speed at lower heights.

Wind Energy Study and Energy Cost of Wind Electricity Generation in Nigeria: Past and Recent Results and a Case Study for South West Nigeria

“…These include the application of Artificial Neural Networks (ANNs), Adaptive neuro-fuzzy, Mixture probability distribution functions, Autoregressive Integrated Moving Average (ARIMA) the Bayesian model averaging, the ARIMA-ANN and the ARIMA-Kalman hybrid methods to model wind speed distributions [47,[51][52][53][54][55][56][57]. Despite the significance of these methods in predicting wind speeds profiles of a place, they also fall short in their inability to determine the two very important site specific wind speeds.…”

Horizontal Axis Wind Turbine Blade Design Methodologies for Efficiency Enhancement—A Review

“…These studies include the understanding wind speed trends and inherent properties over long period using modern techniques such as wavelets and power spectrum Zheng et al [8], Alam et al [9], and Siddiqi et al [10]; wind farm layout design optimization and wind turbine selection using multi-criteria algorithms Rehman et al [11] and Rehman and Khan [12]; wind speed distribution analysis using maximum entropy principal Shoaib et al [13] and artificial neural network for vertical estimation of wind speed Mohandes and Rehman [14] and Mohandes et al [15]; spatial estimation of wind speed Mohandes et al [16]; and prediction of wind speed ahead of time Mohandes and Rehman [17], Mohandes et al [18] and Mohandes et al [19]. The local research team has also worked on wind power resources assessment and wind characteristics for offshore locations in collaboration with Greek scientists Bagiorgas et al [20][21][22][23] and Rehman et al [24] and with Algerian researchers on wind power potential utilization for onshore locations Himri et al [25][26][27].…”

Daily Average Wind Power Interval Forecasts Based on an Optimal Adaptive-Network-Based Fuzzy Inference System and Singular Spectrum Analysis

“…Jang [28] restructured FISs with two contributions: proposing a standard method for transforming ill-defined factors into identifiable rules of FIS and using an adaptive network to tune the membership functions. This restructuring yields the ANFIS, which has been validated for its availability in the wind energy area [35,36]. We assume the system contains two fuzzy if-then rules [37], two inputs (x and y) and one output (z), and the processes of ANFIS are described in Figure 1.…”