Turbine Layout Optimization Research Articles

Review on the Application of Artificial Intelligence Methods in the Control and Design of Offshore Wind Power Systems

As global energy crises and climate change intensify, offshore wind energy, as a renewable energy source, is given more attention globally. The wind power generation system is fundamental in harnessing offshore wind energy, where the control and design significantly influence the power production performance and the production cost. As the scale of the wind power generation system expands, traditional methods are time-consuming and struggle to keep pace with the rapid development in wind power generation systems. In recent years, artificial intelligence technology has significantly increased in the research field of control and design of offshore wind power systems. In this paper, 135 highly relevant publications from mainstream databases are reviewed and systematically analyzed. On this basis, control problems for offshore wind power systems focus on wind turbine control and wind farm wake control, and design problems focus on wind turbine selection, layout optimization, and collection system design. For each field, the application of artificial intelligence technologies such as fuzzy logic, heuristic algorithms, deep learning, and reinforcement learning is comprehensively analyzed from the perspective of performing optimization. Finally, this report summarizes the status of current development in artificial intelligence technology concerning the control and design research of offshore wind power systems, and proposes potential future research trends and opportunities.

Research on a random search algorithm for wind turbine layout optimization

Wind turbine layout design has an important impact on the energy production and economic benefits of wind farms. The wind resource grid data include the realistic wind distributions of the wind farm. Combined with the Jensen wake model, it can be used to calculate the net production considering the wake effect of turbines. Based on the wind resource grid data and taking net energy production as the objective function, this paper proposes a random search algorithm for wind turbine layout optimization. The algorithm couples the random function with multiple optimization parameters and optimizes the wind turbine layout by considering restriction conditions of area and minimum turbine spacings. According to the results of the case study in an actual wind farm, the optimization processes using the proposed algorithm have high calculation efficiency and stability. The sensitivity analysis of parameters indicates that the effect of optimization calculation can be effectively improved by appropriately increasing the turbine coordinate searching range or the number of random operations within one single search.

Optimization of Wind Farm Design Layout based on the Non-Uniform Spacing Algorithm between Wind Turbines

The optimization of wind turbine layout is an important step during the design phase of wind farms, which directly influences the overall power performance and the profitability of the wind plants. The spacing distance between the wind turbines, which is often inconsistent in the prevailing wind direction and other directions, is the critical factor of wind turbine array layout optimization. With the considerations of the wind turbines’ safety in operation and the maximum utilization of wind energy resources comprehensively, an elliptic-constrained wind turbine layout optimization model is proposed in this paper. The stochastic optimal algorithm including the constraint checking and random searching processes is established to conduct the iterative calculation. It is proved that the annual energy production of the elliptic-constrained model with non-uniform spacing has increased in comparison with the conventional method. The proposed approach provides an effective engineering solution for improving the space utilization and the power output estimation of the wind farm.

A non-intrusive reduced-order model for wind farm wake analysis based on SPOD-DNN

Wind farm wake modeling is of great significance for wind turbine layout optimization design and yaw control strategy. In this work, we combine deep neural network (DNN) with spectral proper orthogonal decomposition (SPOD) to discover dynamic characteristics of wake under different inflow conditions. Then an assessment of the proposed SPOD-DNN surrogate modeling method of parameterized fluid is performed by comparing the predicted results. Meanwhile, we demonstrate the robustness of the SPOD-DNN through a comparison with POD-DNN, where SPOD produces fewer modes than POD but can achieve the same cumulative contribution rate and wake prediction accuracy. In the end, the method is developed to predict the wake of single wind turbine in untrained inflow condition and Wake of six wind turbines with different yaw angles. The results reveals that the model has good generalization performance and can robustly reconstruct the wake of multiple wind turbines in different directions.

Comparison of SAGA and GA in Wind Turbine Layout Optimization Based on Modified Two-dimensional Wake Model or Jensen Model

In this paper, Simulated Annealing Genetic Algorithm (SAGA) and a new two-dimensional wake model called 2D_k Jensen model are adopted for optimal wind turbine layout (WTL) in the wind farms and are compared with Genetic Algorithm (GA) and Jensen model, respectively, aiming to minimize the investment cost and maximize the wind power generation as much as possible. The influence of the radial distribution of wake on the equivalent wind speed in the wake superposition region is considered. In the case of single wind direction and single speed, total output power and energy extraction efficiency are both improved when SAGA is applied to the two model conditions respectively, especially for the WTL using the 2D_k Jensen model, these two aspects are significantly improved by 13.75% and 24.10%, respectively, and the objective function is reduced by 19.05%. The results demonstrate that SAGA is more conducive to solving the practical configuration optimization of wind turbines, compared with the original GA.

Power Performance Analysis Based on Savonius Wind Turbine Blade Design and Layout Optimization through Rotor Wake Flow Analysis

Savonius vertical axis wind turbines have simple structures, can self-start in environments with low wind speed and strong turbulence intensity, and can be installed at low costs. Therefore, installation is possible in urban centers with low wind speeds, which may contribute to the construction of a decentralized power system. Savonius wind turbines are operated by drag force, with the blades moving in the same direction as the flow current providing the thrust force and those moving in the opposite direction of the wind being rotated by the drag force. In this study, the Savonius wind turbine design was examined to develop a stable wind turbine for use in urban centers at low wind speeds. The Savonius rotor design variables (aspect and overlap ratios) and blade forms (semi-circular, Bach, and elliptical type) were examined using computational fluid dynamics analysis. Moreover, a rotor capable of providing the target output was designed and maximum rotor efficiency of 18% was realized. Further, changes to the flow corresponding with various turbine layouts were analyzed to determine the arrangement that would maximize turbine performance. The results showed that the maximum efficiency of the turbines was in the 17–19% range and without significant variation.

A synchronization methodology for 3D offshore wind farm layout optimization with multi-type wind turbines and obstacle-avoiding cable network

Offshore wind farms are increasingly becoming the focus of clean sources market because of the huge energy potential and fast-maturing technology. The existing researches normally optimize the wind turbine layout and two-dimensional cable routing independently. This work focuses on the synchronization optimization of site selection of the offshore wind farm, three-dimensional wind turbine layout and three-dimensional cable network routing based on meta-heuristic algorithms and geographic information systems. Several practical issues, i.e., restricted areas, power generation, cable network and energy loss, are taken into consideration. A two-layer model is proposed. The outer layer model is for the site selection and the wind turbine layout optimization. The inner layer model is for the obstacle-avoiding cable routing optimization. In this stage, the seabed terrain is considered for the first time. The proposed integrated model is complex and non-convex. Thus, a hybrid method including an improved ant colony optimization combined with genetic algorithm, dual-simplex method and Kruskal algorithm is proposed to search the solution more efficiently. The initialization stage of the hybrid method is improved from random assignment to directional assignment. The directional solution is obtained by the widely used genetic algorithm. A case study based on a real offshore wind farm is established to prove the effectiveness of the proposed methodology. The results show an over one million dollars increase in annual benefit compared with conventional methods.

Wind Farm Layout Optimization Using a Metamodel and EA/PSO Algorithm in Korea Offshore

This paper examines the solution to the problem of turbine arrangement in offshore wind farms. The two main objectives of offshore wind farm planning are to minimize wake loss and maximize annual energy production (AEP). There is more wind with less turbulence offshore compared with an onshore case, which drives the development of the offshore wind farm worldwide. South Korea’s offshore wind farms, which are deep in water and cannot be installed far off the coast, are affected by land complex terrain. Thus, domestic offshore wind farms should consider the separation distance from the coastline as a major variable depending on the topography and marine environmental characteristics. As a case study, a 60 MW offshore wind farm was optimized for the coast of the Busan Metropolitan City. For the analysis of wind conditions in the candidate site, wind conditions data from the meteorological tower and Ganjeolgot AWS at Gori offshore were used from 2001 to 2018. The optimization procedure is performed by evolutionary algorithm (EA) and particle swarm optimization (PSO) algorithm with the purpose of maximizing the AEP while minimizing the total wake loss. The optimization procedure can be applied to the optimized placement of WTs within a wind farm and can be extended for a variety of wind conditions and wind farm capacity. The results of the optimization were predicted to be 172,437 MWh/year under the Gori offshore wind potential, turbine layout optimization, and an annual utilization rate of 26.5%. This could convert 4.6% of electricity consumption in the Busan Metropolitan City region in 2019 in offshore wind farms.

Surrogate models for parameterized representation of wake‐induced loads in wind farms

AbstractA procedure for mapping wake‐induced load predictions computed with the dynamic wake meandering model to a computationally efficient surrogate model approximation is defined and demonstrated. Using the mapping function, the load variation can be efficiently estimated for a wind farm with arbitrary layout. The resulting load assessment procedure provides continuous, differentiable output with known analytical derivatives and can be used for applications such as wind turbine layout optimization, estimation of turbine lifetime, and uncertainty analysis.

Coupled wind turbine design and layout optimization with nonhomogeneous wind turbines

Abstract. In this study, wind farms were optimized to show the benefit of coupling complete turbine design and layout optimization as well as including two different turbine designs in a fixed 1-to-1 ratio in a single wind farm. For our purposes, the variables in each turbine optimization include hub height, rotor diameter, rated power, tower diameter, tower shell thickness, and implicit blade chord-and-twist distributions. A 32-turbine wind farm and a 60-turbine wind farm were both considered, as well as a variety of turbine spacings and wind shear exponents. Structural constraints as well as turbine costs were considered in the optimization. Results indicate that coupled turbine design and layout optimization is superior to sequentially optimizing turbine design, then turbine layout. Coupled optimization results in an additional 2 %–5 % reduction in the cost of energy compared to optimizing sequentially for wind farms with turbine spacings of 8.5–11 rotor diameters. Smaller wind farms benefit even more from coupled optimization. Furthermore, wind farms with closely spaced wind turbines can greatly benefit from nonuniform turbine design throughout the farm. Some of these wind farms with heterogeneous turbine design have an additional 10 % cost-of-energy reduction compared to wind farms with identical turbines throughout the farm.

Small 500 kW onshore wind farm project in Kribi, Cameroon: Sizing and checkers layout optimization model

For the purpose of providing cheap, affordable and reliable electrical energy to communities in need and power-up new industries and enterprises, a small onshore wind farm with an estimated capacity of 500 kW is designed and studied. With the help of a wind rose, wind resource map, and results from Weibull statistics, a potential site is selected and the wind farm is positioned along Cameroon’s coastline for maximum energy capture. Using the PARK model for wind turbine layout optimization, two different layout patterns (Checkers pattern and column pattern) are studied for the purpose of minimizing the wake effect and thereby, maximizing the output power from the farm. The Checkers model was found suitable as compared to the column model to be used on Grand Batanga, a small locality South of the city of Kribi, Cameroon.

Three-dimensional structure of wind turbine wakes as measured by scanning lidar

Abstract. The lower wind speeds and increased turbulence that are characteristic of turbine wakes have considerable consequences on large wind farms: turbines located downwind generate less power and experience increased turbulent loads. The structures of wakes and their downwind impacts are sensitive to wind speed and atmospheric variability. Wake characterization can provide important insights for turbine layout optimization in view of decreasing the cost of wind energy. The CWEX-13 field campaign, which took place between June and September 2013 in a wind farm in Iowa, was designed to explore the interaction of multiple wakes in a range of atmospheric stability conditions. Based on lidar wind measurements, we extend, present, and apply a quantitative algorithm to assess wake parameters such as the velocity deficits, the size of the wake boundaries, and the location of the wake centerlines. We focus on wakes from a row of four turbines at the leading edge of the wind farm to explore variations between wakes from the edge of the row (outer wakes) and those from turbines in the center of the row (inner wakes). Using multiple horizontal scans at different elevations, a three-dimensional structure of wakes from the row of turbines can be created. Wakes erode very quickly during unstable conditions and can in fact be detected primarily in stable conditions in the conditions measured here. During stable conditions, important differences emerge between the wakes of inner turbines and the wakes of outer turbines. Further, the strong wind veer associated with stable conditions results in a stretching of the wake structures, and this stretching manifests differently for inner and outer wakes. These insights can be incorporated into low-order wake models for wind farm layout optimization or for wind power forecasting.

A Continuously Differentiable Turbine Layout Optimization Model for Offshore Wind Farms

This article presents a continuously differentiable modification of the commonly used Jensen wake model. This property is con- served in the wake combination model and, by formulating the turbine's power curve as a set of constraints, also in the computation of a turbine's power output. The resulting objective function, maximizing the total power production, and optimizing the turbine positions, is thus continuously differentiable, and gradient based solution methods can be applied. Numerical experiments are conducted with simulated wind data of six offshore wind farm locations.

Wind turbine layout optimization with multiple hub height wind turbines using greedy algorithm

Wind turbine layout optimization in wind farm is one of the most important technologies to increase the wind power utilization. This paper studies the wind turbine layout optimization with multiple hub heights wind turbines using greedy algorithm. The linear wake model and the particle wake model are used for wake flow calculation over flat terrain and complex terrain, respectively. Three-dimensional greedy algorithm is developed to optimize wind turbine layout with multiple hub heights for minimizing cost per unit power output. The numerical cases over flat terrain and complex terrain are used to validate the effectiveness of the proposed greedy algorithm for the optimization problem. The results reveal that it incurs lower computational costs to obtain better optimized results using the proposed greedy algorithm than the one using genetic algorithm. Compared to the layout with identical hub height wind turbines, the one with multiple hub height wind turbines can increase the total power output and decrease the cost per unit power output remarkably, especially for the wind farm over complex terrain. It is suggested that three-dimensional greedy algorithm is an effective method for more benefits of using wind turbines with multiple hub heights in wind farm design.

Optimization of wind turbine layout position in a wind farm using a newly-developed two-dimensional wake model

The development and validation of a 2D analytical wind turbine wake model based on Jensen’s wake model using Gaussian function is presented in this paper. The velocity deficit predicted by the newly-developed Jensen–Gaussian wake model is compared with wind tunnel experimental measured data in literatures and results show that, the velocity deficit predicted by the model fits well with the measured data at different downwind distances of X=2.5D, X=5D, X=7.5D and X=10D. Considering the turbulence inside the turbine wake, a new turbulence model is developed and based on this, the Jensen–Gaussian wake model was improved and validated. The 2D Jensen–Gaussian wake model is then applied in the wind turbine layout optimizing process within a wind farm based on the multiple populations genetic algorithm (MPGA). The performance of this newly 2D model in the optimization process is validated and compared with the results presented in some typical studies on the turbine layout optimization. The comparison is performed for ‘constant wind speed of 12m/s with variable wind directions’. Using the 2D Jensen–Gaussian wake model instead of Jensen’s wake model in the MPGA turbine layout optimization program, both the total power generation and wind farm efficiency decreased. The wind farm efficiency drop to 77.83%, 78.47% and 81.84% from 96.83%, 96.34% and 96.23% for 38, 39 and 40 wind turbines, respectively which is in accordance with the literatures on the power losses caused by wake effect in large wind farm. The development and application of the 2D Jensen–Gaussian wake model means moretheorysignificance and practicalvalues in wind energy utilization.

Wind turbine layout optimization using multi-population genetic algorithm and a case study in Hong Kong offshore

This paper proposes a multi-population genetic algorithm (MPGA) program for wind turbine layout optimization in a wind farm which aims at extracting the maximum power in a minimum investment cost. The MPGA program is applied to a 2km×2km wind farm considering three different wind scenarios, i.e. (a): constant wind speed of 12m/s with fixed wind direction; (b): constant wind speed of 12m/s with variable wind direction and (c): variable wind speed of 8m/s, 12m/s, 17m/s with variable wind directions. Compared with previous studies, the results of power generation cost of energy and wind farm efficiency are improved in the paper using MPGA which validate that MPGA works effectively in wind turbine layout optimization with wind farm. Additionally, a case study of wind turbine layout configuration op1timization using the MPGA program in a hypothetical offshore wind farm located in Hong Kong southeastern water is attempted using the 20 years׳ wind data from 1992 to 2011. The optimization result is beneficial for the assessment of the offshore wind power potential in Hong Kong. It is indicated that, under the optimization of wind turbines layout in the wind farm, 39.14×108kWh/year electricity can be converted from the offshore wind farm, which occupies 9.09% of the 2012 electricity consumption in Hong Kong. Results show that the multi-population genetic algorithm program can be applied in any real-world wind farms for wind turbine layout optimization when the wind farm boundary is determined as well as the local wind condition is obtained.

Proximity search heuristics for wind farm optimal layout

A heuristic framework for turbine layout optimization in a wind farm is proposed that combines ad-hoc heuristics and mixed-integer linear programming. In our framework, large-scale mixed-integer programming models are used to iteratively refine the current best solution according to the recently-proposed proximity search paradigm. Computational results on very large scale instances involving up to 20,000 potential turbine sites prove the practical viability of the overall approach.

Quantifying Wind Turbine Wake Characteristics from Scanning Remote Sensor Data

Abstract Because of the dense arrays at most wind farms, the region of disturbed flow downstream of an individual turbine leads to reduced power production and increased structural loading for its leeward counterparts. Currently, wind farm wake modeling, and hence turbine layout optimization, suffers from an unacceptable degree of uncertainty, largely because of a lack of adequate experimental data for model validation. Accordingly, nearly 100 h of wake measurements were collected with long-range Doppler lidar at the National Wind Technology Center at the National Renewable Energy Laboratory in the Turbine Wake and Inflow Characterization Study (TWICS). This study presents quantitative procedures for determining critical parameters from this extensive dataset—such as the velocity deficit, the size of the wake boundary, and the location of the wake centerline—and categorizes the results by ambient wind speed, turbulence, and atmospheric stability. Despite specific reference to lidar, the methodology is general and could be applied to extract wake characteristics from other remote sensor datasets, as well as computational simulation output. The observations indicate an initial velocity deficit of 50%−60% immediately behind the turbine, which gradually declines to 15%−25% at a downwind distance x of 6.5 rotor diameters (D). The wake expands with downstream distance, albeit less so in the vertical direction due to the presence of the ground: initially the same size as the rotor, the extent of the wake grows to 2.7D (1.2D) in the horizontal (vertical) at x = 6.5D. Moreover, the vertical location of the wake center shifts upward with downstream distance because of the tilt of the rotor.