Comparison Accuracy W-NN and WD-SVM Method In Predicted Wind Power Model on Wind Farm Pandansimo

Background: The penetration level of a wind farm with transient stability constraint and static security constraint has been a key problem in wind power applications. Objective: The study explores maximum penetration level problem of wind considering transient stability constraint and uncertainty of wind power out, based on credibility theory and corrected energy function method. Methods: According to the corrected energy function, the transient stability constraint of the power grid is transferred to the penetration level problem of a wind farm. Wind speed forecast error is handled as a fuzzy variable to express the uncertainty of wind farm output. Then this paper builds a fuzzy chance-constrained model to calculate wind farm penetration level. To avoid inefficient fuzzy simulation, the model is simplified to a mixed integer linear programming model. Results: The results validate the proposed model and investigate the influence of grid-connection node, wind turbine characteristic, fuzzy reliability index, and transient stability index on wind farm penetration level. Conclusion: The result shows that the model proposed in this study can consider the uncertainty of wind power out and establish a quantitative transient stability constraint to determine the wind farm penetration level with a certain fuzzy confidence level.

Download Full-text

Numerical Weather Prediction and Artificial Neural Network Coupling for Wind Energy Forecast

Energies ◽

10.3390/en14020338 ◽

2021 ◽

Vol 14 (2) ◽

pp. 338

Author(s):

Lorenzo Donadio ◽

Jiannong Fang ◽

Fernando Porté-Agel

Keyword(s):

Machine Learning ◽

Wind Energy ◽

Wind Power ◽

Numerical Weather Prediction ◽

Wind Farm ◽

Weather Prediction ◽

Wind Power Forecasting ◽

Numerical Weather ◽

Artificial Neural ◽

Power Forecasting

In the past two decades, wind energy has been under fast development worldwide. The dramatic increase of wind power penetration in electricity production has posed a big challenge to grid integration due to the high uncertainty of wind power. Accurate real-time forecasts of wind farm power outputs can help to mitigate the problem. Among the various techniques developed for wind power forecasting, the hybridization of numerical weather prediction (NWP) and machine learning (ML) techniques such as artificial neural networks (ANNs) are attracting many researchers world-wide nowadays, because it has the potential to yield more accurate forecasts. In this paper, two hybrid NWP and ANN models for wind power forecasting over a highly complex terrain are proposed. The developed models have a fine temporal resolution and a sufficiently large prediction horizon (>6 h ahead). Model 1 directly forecasts the energy production of each wind turbine. Model 2 forecasts first the wind speed, then converts it to the power using a fitted power curve. Effects of various modeling options (selection of inputs, network structures, etc.) on the model performance are investigated. Performances of different models are evaluated based on four normalized error measures. Statistical results of model predictions are presented with discussions. Python was utilized for task automation and machine learning. The end result is a fully working library for wind power predictions and a set of tools for running the models in forecast mode. It is shown that the proposed models are able to yield accurate wind farm power forecasts at a site with high terrain and flow complexities. Especially, for Model 2, the normalized Mean Absolute Error and Root Mean Squared Error are obtained as 8.76% and 13.03%, respectively, lower than the errors reported by other models in the same category.

Download Full-text

Miniaturization of an Offshore Platform with Medium-Frequency Offshore Wind Farm and MMC-HVDC Technology

Energies ◽

10.3390/en14082058 ◽

2021 ◽

Vol 14 (8) ◽

pp. 2058

Author(s):

Zheren Zhang ◽

Yingjie Tang ◽

Zheng Xu

Keyword(s):

Wind Power ◽

Computer Aided Design ◽

Wind Farm ◽

Offshore Platform ◽

Offshore Wind ◽

Operating Frequency ◽

Offshore Wind Farm ◽

Medium Frequency ◽

Offshore Wind Power ◽

System Frequency

Offshore wind power has great development potential, for which the key factors are reliable and economical wind farms and integration systems. This paper proposes a medium-frequency wind farm and MMC-HVDC integration system. In the proposed scheme, the operating frequency of the offshore wind farm and its power collection system is increased from the conventional 50/60 Hz rate to the medium-frequency range, i.e., 100–400 Hz; the offshore wind power is transmitted to the onshore grid via the modular multilevel converter-based high-voltage direct current transmission (MMC-HVDC). First, this paper explains the principles of the proposed scheme in terms of the system topology and control strategy aspects. Then, the impacts of increasing the offshore system operating frequency on the main parameters of the offshore station are discussed. As the frequency increases, it is shown that the actual value of the electrical equipment, such as the transformers, the arm inductors, and the SM capacitors of the rectifier MMC, can be reduced, which means smaller platforms are required for the step-up transformer station and the converter station. Then, the system operation characteristics are analyzed, with the results showing that the power losses in the system increase slightly with the increase of the offshore AC system frequency. Based on time domain simulation results from power systems computer aided design/electromagnetic transients including DC (PSCAD/EMTDC), it is noted that the dynamic behavior of the system is not significantly affected with the increase of the offshore AC system frequency in most scenarios. In this way, the technical feasibility of the proposed offshore platform miniaturization technology is proven.

Download Full-text

A Diode-MMC AC/DC Hub for Connecting Offshore Wind Farm and Offshore Production Platform

Energies ◽

10.3390/en14133759 ◽

2021 ◽

Vol 14 (13) ◽

pp. 3759

Author(s):

Kai Huang ◽

Lie Xu ◽

Guangchen Liu

Keyword(s):

Wind Power ◽

Wind Farm ◽

Offshore Wind ◽

System Control ◽

Dc Voltage ◽

Offshore Wind Power ◽

Offshore Production ◽

Production Platform ◽

In Series ◽

Dc Voltage Control

A diode rectifier-modular multilevel converter AC/DC hub (DR-MMC Hub) is proposed to integrate offshore wind power to the onshore DC network and offshore production platforms (e.g., oil/gas and hydrogen production plants) with different DC voltage levels. The DR and MMCs are connected in parallel at the offshore AC collection network to integrate offshore wind power, and in series at the DC terminals of the offshore production platform and the onshore DC network. Compared with conventional parallel-connected DR-MMC HVDC systems, the proposed DR-MMC hub reduces the required MMC converter rating, leading to lower investment cost and power loss. System control of the DR-MMC AC/DC hub is designed based on the operation requirements of the offshore production platform, considering different control modes (power control or DC voltage control). System behaviors and requirements during AC and DC faults are investigated, and hybrid MMCs with half-bridge and full-bridge sub-modules (HBSMs and FBSMs) are used for safe operation during DC faults. Simulation results based on PSCAD/EMTDC validate the operation of the DR-MMC hub.

Download Full-text

Operation Flexibility Evaluation and Its Application to Optimal Planning of Bundled Wind-Thermal-Storage Generation System

Electronics ◽

10.3390/electronics8010009 ◽

2018 ◽

Vol 8 (1) ◽

pp. 9

Author(s):

Yinghao Ma ◽

Hejun Yang ◽

Dabo Zhang ◽

Qianyu Ni

Keyword(s):

Wind Power ◽

Wind Farm ◽

Storage System ◽

Thermal Storage ◽

Dft Method ◽

Energy Storage System ◽

Planning Model ◽

Generation System ◽

System Operation ◽

Operation Flexibility

The growing penetration of wind power in a power system brings great challenges to system operation flexibility. For generation planning in presence of high wind power penetration, it is essential to take the operation flexibility of the system into account. Firstly, this paper developed the system operation flexibility metrics through considering the flexibility contribution of thermal generating units (TGUs) by operational state transition. Secondly, a planning model for the bundled wind-thermal-storage generation system (BWTSGS) that considers the operation flexibility constraints is proposed. The planning model is used to determine the power and energy rating of an energy storage system (ESS) as well as the type and number of TGUs. A daily scheduling simulation model of a BWTSGS is proposed to calculate the operation cost for the planning model and consider the sequential operation characteristics of the BWTSGS. Further, in order to accelerate the computation, a wind power sequential clustering technique based on the discrete Fourier transform (DFT) method is developed for improving the computational efficiency. Case studies have been conducted on a 1000-MW wind farm to demonstrate the validity and effectiveness of the proposed model.

Download Full-text

A Compound Wind Power Forecasting Strategy Based on Clustering, Two-Stage Decomposition, Parameter Optimization, and Optimal Combination of Multiple Machine Learning Approaches

Energies ◽

10.3390/en12183586 ◽

2019 ◽

Vol 12 (18) ◽

pp. 3586 ◽

Cited By ~ 1

Author(s):

Sizhou Sun ◽

Jingqi Fu ◽

Ang Li

Keyword(s):

Wind Power ◽

Large Scale ◽

Wind Farm ◽

Search Algorithm ◽

Interpolation Method ◽

Least Square ◽

Support Vector ◽

Two Stage ◽

Wind Power Forecasting ◽

Power Forecasting

Given the large-scale exploitation and utilization of wind power, the problems caused by the high stochastic and random characteristics of wind speed make researchers develop more reliable and precise wind power forecasting (WPF) models. To obtain better predicting accuracy, this study proposes a novel compound WPF strategy by optimal integration of four base forecasting engines. In the forecasting process, density-based spatial clustering of applications with noise (DBSCAN) is firstly employed to identify meaningful information and discard the abnormal wind power data. To eliminate the adverse influence of the missing data on the forecasting accuracy, Lagrange interpolation method is developed to get the corrected values of the missing points. Then, the two-stage decomposition (TSD) method including ensemble empirical mode decomposition (EEMD) and wavelet transform (WT) is utilized to preprocess the wind power data. In the decomposition process, the empirical wind power data are disassembled into different intrinsic mode functions (IMFs) and one residual (Res) by EEMD, and the highest frequent time series IMF1 is further broken into different components by WT. After determination of the input matrix by a partial autocorrelation function (PACF) and normalization into [0, 1], these decomposed components are used as the input variables of all the base forecasting engines, including least square support vector machine (LSSVM), wavelet neural networks (WNN), extreme learning machine (ELM) and autoregressive integrated moving average (ARIMA), to make the multistep WPF. To avoid local optima and improve the forecasting performance, the parameters in LSSVM, ELM, and WNN are tuned by backtracking search algorithm (BSA). On this basis, BSA algorithm is also employed to optimize the weighted coefficients of the individual forecasting results that produced by the four base forecasting engines to generate an ensemble of the forecasts. In the end, case studies for a certain wind farm in China are carried out to assess the proposed forecasting strategy.

Download Full-text

The Research of Wind Power Fluctuation in Different Time Intervals

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.953-954.458 ◽

2014 ◽

Vol 953-954 ◽

pp. 458-461

Author(s):

Yi Hui Zhang

Keyword(s):

Wind Speed ◽

Probability Distribution ◽

Wind Power ◽

Wind Farm ◽

Time Window ◽

Missing Information ◽

Power Fluctuation ◽

Time Intervals ◽

Trend Pattern ◽

Length Of Interval

Power from wind turbines is mainly related to the wind speed. Due to the influence of the uncertainty of the wind, intermittent and wind farm in units of the wake, wind power has fluctuations. Based on the field measurement, it is found that t location-scale distribution is suitable to identify the probability distribution of wind power variations. By analyzing the fluctuation of a single in different time intervals, we find that the distribution of wind power fluctuation possesses a certain trend pattern. With the length of the time window increasing, the fluctuations increase and some information has been missed. We define an index to calculate the quantity of missing information and can use that to evaluate whether a certain length of interval is acceptable.

Download Full-text

Performance Enhancement of Proposed Namaacha Wind Farm by Minimising Losses Due to the Wake Effect: A Mozambican Case Study

Energies ◽

10.3390/en14144291 ◽

2021 ◽

Vol 14 (14) ◽

pp. 4291

Author(s):

Paxis Marques João Roque ◽

Shyama Pada Chowdhury ◽

Zhongjie Huan

Keyword(s):

Wind Speed ◽

Wind Power ◽

Wind Turbines ◽

Power Output ◽

Wind Farm ◽

Wind Farms ◽

Operating Conditions ◽

Wake Effect ◽

Wind Generators ◽

Wind Potential

District of Namaacha in Maputo Province of Mozambique presents a high wind potential, with an average wind speed of around 7.5 m/s and huge open fields that are favourable to the installation of wind farms. However, in order to make better use of the wind potential, it is necessary to evaluate the operating conditions of the turbines and guide the independent power producers (IPPs) on how to efficiently use wind power. The investigation of the wind farm operating conditions is justified by the fact that the implementation of wind power systems is quite expensive, and therefore, it is imperative to find alternatives to reduce power losses and improve energy production. Taking into account the power needs in Mozambique, this project applied hybrid optimisation of multiple energy resources (HOMER) to size the capacity of the wind farm and the number of turbines that guarantee an adequate supply of power. Moreover, considering the topographic conditions of the site and the operational parameters of the turbines, the system advisor model (SAM) was applied to evaluate the performance of the Vestas V82-1.65 horizontal axis turbines and the system’s power output as a result of the wake effect. For any wind farm, it is evident that wind turbines’ wake effects significantly reduce the performance of wind farms. The paper seeks to design and examine the proper layout for practical placements of wind generators. Firstly, a survey on the Namaacha’s electricity demand was carried out in order to obtain the district’s daily load profile required to size the wind farm’s capacity. Secondly, with the previous knowledge that the operation of wind farms is affected by wake losses, different wake effect models applied by SAM were examined and the Eddy–Viscosity model was selected to perform the analysis. Three distinct layouts result from SAM optimisation, and the best one is recommended for wind turbines installation for maximising wind to energy generation. Although it is understood that the wake effect occurs on any wind farm, it is observed that wake losses can be minimised through the proper design of the wind generators’ placement layout. Therefore, any wind farm project should, from its layout, examine the optimal wind farm arrangement, which will depend on the wind speed, wind direction, turbine hub height, and other topographical characteristics of the area. In that context, considering the topographic and climate features of Mozambique, the study brings novelty in the way wind farms should be placed in the district and wake losses minimised. The study is based on a real assumption that the project can be implemented in the district, and thus, considering the wind farm’s capacity, the district’s energy needs could be met. The optimal transversal and longitudinal distances between turbines recommended are 8Do and 10Do, respectively, arranged according to layout 1, with wake losses of about 1.7%, land utilisation of about 6.46 Km2, and power output estimated at 71.844 GWh per year.

Download Full-text