Predicting Wind Turbine Power and Load Outputs by Multi-task Convolutional LSTM Model

During recent years, wind energy has moved from an emerging technology to a nearly competitive technology. This fact, coupled with an increasing global focus on environmental concern and a political desire of a certain level of diversification in the energy supply, ensures wind energy an important role in the future electricity market. For this challenge to be met in a cost-efficient way, a substantial part of new wind turbine installations is foreseen to be erected in big onshore or offshore wind farms. This fact makes the production, loading and reliability of turbines operating under such conditions of particular interest.

The instantaneous wind speed variations are ignored in the wind turbine power curves. Hence, the output power of the wind turbines becomes a function of only the average wind speed. In the variable-speed wind turbines, the output power is a function of wind speed as well as the wind dynamics because in order to extract the maximum amount of electrical energy, the control system in these turbines will adjust the rotor speed and blades' pitch angle according to the instantaneous wind speed. Since the wind dynamics is not taken into account in the power curve, the power generated by the controllers is overlooked and therefore the turbine output power is not represented accurately by the power curve. In this paper, a new method is proposed using a new index called wind turbine controllability factor in order to make it possible to calculate precisely the output power of wind turbines based on the wind dynamics. In this method, the energy pattern factor is used as an indicator of the amount of instantaneous wind speed variations and power curve is modified corresponding to the values of the energy pattern factor.

Wind velocity distribution differences in wind wheel rotation plane caused by wind shear and tower shadow, not only causes load fluctuations of wind turbine blades, but also leads to pulsations of wind turbine aerodynamic torque and output power. In order to reduce the influence of wind shear and tower shadow on the fluctuations of three-bladed wind turbine, an individual pitch control strategy based on the pitch angle signal adjusted jointly by wind turbine output power and rotor azimuth angle is proposed. A band-pass filter is designed to filter out the three times pulsating component of the wind turbine output power, and a PID controller is used to obtain regulatory signal of pitch angle, which is then converted to tiny variable of each blade combining with the azimuth angle signal and superimposed to the reference pitch angle of the collective pitch control. Simulation results on GH Bladed platform show that the proposed individual pitch control strategy is effective to smooth blade load fluctuation, diminish aerodynamic torque ripple, reduce rotor fatigue damage, and prolong life time of wind turbine.

This article investigates the impact of the pitch-to-stall and pitch-to-feather control concepts on horizontal axis wind turbines (HAWTs) with different blade designs. Pitch-to-feather control is widely used to limit the power output of wind turbines in high wind speed conditions. However, stall control has not been taken forward in the industry because of the low predictability of stalled rotor aerodynamics. Despite this drawback, this article investigates the possible advantages of this control concept when compared to pitch-to-feather control with an emphasis on the control performance and its impact on the pitch mechanism and structural loads. In this study, three HAWTs with different blade designs, i.e., untwisted, stall-regulated, and pitch-regulated blades, are investigated. The control system is validated in both uniform and turbulent wind speed. The results show that pitch-to-stall control enhances the constant power control for wind turbines with untwisted and stall-regulated blade designs. Stall control alleviates the fore-aft tower loading and the blades flapwise moment of the wind turbine with stall-regulated blades in uniform winds. However, in turbulent winds, the flapwise moment increases to a certain extent as compared to pitch-to-feather control. Moreover, pitch-to-stall control considerably reduces the summed blade pitch movement, despite that it increases the risk of surface damage in the rolling bearings due to oscillating movements with a small amplitude.

Abstract. Wind energy harvesting from the atmosphere takes place in the atmospheric boundary layer. The boundary layer shear and buoyancy create three-dimensional turbulent eddies spanning a range of scales that form a continuous forward cascade of kinetic energy to the smallest scales of motion where energy is dissipated. Large-scale atmospheric circulations modulate the boundary layer turbulence, characterized by coherence and intermittency. As wind turbines grow in size and the integrated control of both turbines and wind farms spans greater distances, the relationship between the scales of atmospheric turbulence and the design and operation of wind energy facilities has entered new territory. The boundary layer turbulence impacts both wind turbine power production and turbine loads. Optimizing wind turbine and wind farm performance requires an understanding of how turbulence affects both wind turbine efficiency and reliability. While the characteristics of atmospheric boundary layer turbulence have been observed and studied in detail over the last few decades, there are still significant gaps in our understanding of the impact of turbulence on wind power resources and wind farm operations. This paper outlines the current state of turbulence research relevant to wind energy applications and points to gaps in our knowledge that need to be addressed to effectively utilize wind resources.

The development and utilization of wind power to meet the electrical demand has recently received significant consideration. Additionally, one of the substantial roles of transmission system operators is to balance reactive power within a network in the sense that with the development of wind energy, wind turbines are expected to contribute towards reactive power generation. So far, there is not a wide range of attention being paid to reactive power in reliability evaluation including wind farms contribution. In this article, wind farms with several identical wind turbines are incorporated in reliability assessment while considering reactive power shortage. Fuzzy C-Means clustering method is used for the output power of wind turbines for analyzing power system reliability with wind farms integration. The application of this concept has been also utilized in developing multistep load levels in the illustrated load buses. Reactive power deficiency and the relevant voltage violations caused by the failure of reactive power generations are studied in this article. Load shedding and power injection techniques are employed to determine possible reactive power shortage required for alleviating network violations with and without wind power integration. Composite system reliability analysis in the existence of wind farms is implemented to assess indices affiliated with curtailed energy at various load points. The RBTS 6-bus system has been proportionally modified and studied to demonstrate the procedure. The results indicate the importance of wind power integration in improving both active and reactive reliability indices which in turn provide system planners with long-range planning for system development.

Advanced control of large-scale wind turbines: Structural load reduction and lifetime control

Optimal Spin-Up Motion of Wind Turbine using Deterministic Dynamic Programming

Abstract. Space–time correlations of power output fluctuations of wind turbine pairs provide information on the flow conditions within a wind farm and the interactions of wind turbines. Such information can play an essential role in controlling wind turbines and short-term load or power forecasting. However, the challenges of analysing correlations of power output fluctuations in a wind farm are the highly varying flow conditions. Here, we present an approach to investigate space–time correlations of power output fluctuations of streamwise-aligned wind turbine pairs based on high-resolution supervisory control and data acquisition (SCADA) data. The proposed approach overcomes the challenge of spatially variable and temporally variable flow conditions within the wind farm. We analyse the influences of the different statistics of the power output of wind turbines on the correlations of power output fluctuations based on 8 months of measurements from an offshore wind farm with 80 wind turbines. First, we assess the effect of the wind direction on the correlations of power output fluctuations of wind turbine pairs. We show that the correlations are highest for the streamwise-aligned wind turbine pairs and decrease when the mean wind direction changes its angle to be more perpendicular to the pair. Further, we show that the correlations for streamwise-aligned wind turbine pairs depend on the location of the wind turbines within the wind farm and on their inflow conditions (free stream or wake). Our primary result is that the standard deviations of the power output fluctuations and the normalised power difference of the wind turbines in a pair can characterise the correlations of power output fluctuations of streamwise-aligned wind turbine pairs. Further, we show that clustering can be used to identify different correlation curves. For this, we employ the data-driven k-means clustering algorithm to cluster the standard deviations of the power output fluctuations of the wind turbines and the normalised power difference of the wind turbines in a pair. Thereby, wind turbine pairs with similar power output fluctuation correlations are clustered independently from their location. With this, we account for the highly variable flow conditions inside a wind farm, which unpredictably influence the correlations.

The operational environment of offshore wind turbines is much more complex than that of onshore wind turbines. Facing the persistent wind and wave forces, offshore wind turbines are prone to vibration problems, which are not conducive to their long-term operation. Under this background, first, how the wave affects the vibration characteristics of offshore wind turbines is analyzed. Based on the existing wave and wave load models, we analytically show that there exist fluctuating components related to the hydrodynamic frequency in the aerodynamic load and aerodynamic torque of offshore wind turbines. Simulation results based on a GH Bladed platform further validates the analysis. Second, in order to reduce the joint impacts of the wave, wind shear and tower shadow on the wind turbine, a variable pitch control method is proposed. The integrated tower top vibration acceleration signal is superimposed on the collective pitch reference signal, then the triple frequency (3P) fluctuating component of the wind turbine output power and the azimuth angle of each blade are converted into the pitch angle adjustment signal of each blade, which is superimposed on the collective pitch signal for individual pitch control. The simulation results show that the proposed pitch control strategy can effectively smooth the fluctuation of blade root flap-wise load caused by wind and wave, and significantly reduce the fluctuation of aerodynamic torque and output power of offshore wind turbines.

This study discusses the load mitigation of unbalanced wind turbines, including balanced and unbalanced loads. Regarding the wind turbine load reduction, it has been shown that individual pitch control (IPC) is more promising in comparison with collective pitch control. However, wind turbine unbalance will cause extra loads and fatigue on the wind turbine rotor, which has not been taken into consideration by the traditional IPC method. This study presents a new control strategy to mitigate the loads of the unbalance wind turbines. An IPC scheme consisting of a proportional–integral (PI) controller and two resonant (R) compensators is presented. The PI‐R regulator is implemented in the hub reference frame to reduce both the balanced and unbalanced loads of the turbine. The wind turbine code FAST (fatigue, aerodynamics, structures and turbulence) is used for the wind turbine load modelling. The simulations are conducted on the NREL upwind 1.5 MW wind turbine model. Elimination of both the balanced and unbalanced loads of the wind turbine has been achieved, so that PI‐R IPC is demonstrated as an effective means for load mitigation of unbalanced wind turbines.

A comprehensive review of wind resource assessment

Wind energy is one of the best important sources of renewable energy and an excellent alternative for the transition to sustainable energy that the planet earth needs. The wind energy is contained in the air particles in movement, forming kinetic energy. This energy could be transformed into another type of energy such as electricity, through the use of wind turbines. It is known that horizontal axis wind turbines are more efficient energetically, the power output of a horizontal axis wind turbine depends of it aerodynamic performance; therefore, the correct geometric design of the propeller is essential for an optimum wind turbine. This article analyzes the most relevant aspects in the design of a wind propeller, using MATLAB® software to illustrate its behavior, suggests an ideal airfoil for wind applications to use in the 3D modeling of the blades using the computer assisted design, this blades has been built with a 3D printer.

The article discusses the possibilities of improving the energy efficiency of wind turbines. A brief analysis of the current state of development of alternative energy, in particular wind energy in Kazakhstan, is considered. It is shown that an increase in the power of a wind - power plant is possible due to the use of a system of simultaneously rotating rotors. A brief description of the Bidarier-2 wind turbine construction, which can significantly increase the power removed from the wind flow, is given. The possibility of further increasing the efficiency of the Bidarrieus-2 wind turbine by means of a concentrator is discussed. The unique method for the speed controlling of the wind flow with the help of sliding flaps of the guide concentrator in order to improve the performance of the wind turbine at high wind speed is proposed first time.

ABSTRACTWind power is one of the most widely available renewable energy sources (RES). However, due to the intermittent nature of wind, the output power of wind turbines (WTs) is always variable. In WTs, at speeds lower than the rated wind speed, the goal is to maximise the power extracted from the wind. At higher wind speeds, the goal is to keep the WT's power constant at rated value; that is typically done by the WT's pitch control system. The operation of the pitch system has a delay due to WT's blades and rotor inertia and limited pitch rate, which may lead to output power fluctuations. Superconducting magnetic energy storage (SMES) has fast response and high efficiency. This paper explores the application of SMES to compensate for the pitch system delay in output power smoothing of a permanent magnet synchronous generator (PMSG)‐based WT. It is verified that the SMES properly compensates for the pitch lag by absorbing the surplus power and releasing it at power shortage intervals, particularly when pitch control returns the blades to their initial position. In the meantime, the pitch system reduces the SMES coil current and prevents it from saturation, which allows selecting an optimal/practical coil size for the SMES.