Utilization of machine‐learning algorithms for wind turbine site suitability modeling in Iowa,USA

Because of the current shift away from fossil fuels and toward renewable energy sources, it is necessary to plan for the installation of new infrastructure to meet the demand for clean energy. Traditional methods for determining wind turbine site suitability suffer from the selection of arbitrary criteria and model parameters by experts, which may lead to a degree of uncertainty in the models produced. An alternative empirically based methodology for building a wind turbine siting model for the state of Iowa is presented in the study. We employ ‘ecological niche’ principles traditionally utilized to model species allocation to develop a new multicriteria, spatially explicit framework for wind turbine placement. Using information on suitability conditions at existing turbine locations, we incorporate seven variables (wind speed, elevation, slope, land cover, distance of infrastructure and settlements, and population density) into two machine‐learning algorithms [maximum entropy method (Maxent) and Genetic Algorithm for Rule Set Prediction (GARP)] to model suitable areas for installation of wind turbines. The performance of this method is tested at the statewide level and a six‐county region in western Iowa. Maxent and GARP identified areas in the Northwest and North Central regions of Iowa as the optimum location for new wind turbines. Information on variable contributions from Maxent illuminates the relative importance of environmental variables and its scale‐dependent nature. It also allows validating existing assumptions about the relationship between variables and wind turbine suitability. The resultant models demonstrate high levels of accuracy and suggest that the presented approach is a possible methodology for developing wind turbine siting applications. Copyright © 2014 John Wiley & Sons, Ltd.     

Low‐cost mounting arrangements for building‐integrated wind turbines

Micro‐generation is being widely promoted as a way for householders in the UK and elsewhere to take part in ‘the Green Revolution’. Building‐integrated wind turbines (BIWTs) provide a way to do this, enabling people to reduce their contribution to the problems of both climate change and decreasing fossil fuel availability. Although energy yields from BIWTs for many householders have been shown to be low, there are still situations where such turbines can make a useful contribution to electricity generation, e.g. in windier areas and for isolated detached buildings. The standards for the installation of BIWTs are still being developed including those for the safe mounting of turbines on domestic buildings. This paper investigates the current trend for mounting small wind turbines on the walls of domestic premises and compares this with an approach which uses roof timbers. It identifies the main characteristics of building construction which affect the integrity of such installations. European and British standards have been used to calculate wind and gravitational loads. Finite element models are used to derive working stresses and, hence, some basic principles of good design. The likely costs of wall and roof mounting are then compared. Installation and health and safety issues are also examined briefly. Copyright © 2010 John Wiley & Sons, Ltd.     

Power loss in the upper cut‐out wind speed interval

Time series of mean wind speeds at several sites in Denmark have been used to estimate the power loss for wind turbines in the wind speed interval from where the operation has to stop at high winds to where a lower wind speed allows the operation to resume. For inland wind turbines the fractional loss is less than 0·25%. For offshore wind turbines it may be as high as about 1·5%. To facilitate the estimation of ‘dead zone’ power loss for offshore wind turbines, an engineering model for the sea surface state has been developed on the basis of a generalization of Charnock's roughness model and the geostrophic drag law. This model predicts the surface friction velocity and the surface roughness as functions of the geostrophic wind speed and the length of the water fetch. Copyright © 2004 John Wiley & Sons, Ltd.     

Optimising residential electric vehicle charging under renewable energy: Multi‐agent learning in software simulation and hardware‐in‐the‐loop evaluation

The integration of intermittent renewable energy sources coupled with the increasing demand of electric vehicles (EVs) poses new challenges to the electrical grid. To address this, many solutions based on demand response have been presented. These solutions are typically tested only in software‐based simulations. In this paper, we present the application in hardware‐in‐the‐loop (HIL) of a recently proposed algorithm for decentralised EV charging, prediction‐based multi‐agent reinforcement learning (P‐MARL), to the problem of optimal EV residential charging under intermittent wind power and variable household baseload demands. P‐MARL is an approach that can address EV charging objectives in a demand response aware manner, to avoid peak power usage while maximising the exploitation of renewable energy sources. We first train and test our algorithm in a residential neighbourhood scenario using GridLAB‐D, a software power network simulator. Once agents learn optimal behaviour for EV charging while avoiding peak power demand in the software simulator, we port our solution to HIL while emulating the same scenario, in order to decrease the effects of agent learning on power networks. Experimental results carried out in a laboratory microgrid show that our approach makes full use of the available wind power, and smooths grid demand while charging EVs for their next day's trip, achieving a peak‐to‐average ration of 1.67, down from 2.24 in the baseline case. We also provide an analysis of the additional demand response effects observed in HIL, such as voltage drops and transients, which can impact the grid and are not observable in the GridLAB‐D software simulation.     

Post‐installation adaptation of offshore wind turbine controls

The cost of offshore wind energy can be reduced by incorporating control strategies to reduce the support structures' load effects into the structural design process. While effective in reducing the cost of support structures, load‐reducing controls produce potentially costly side effects in other wind turbine components and subsystems. This paper proposes a methodology to mitigate these side effects at the wind farm level. The interaction between the foundation and the surrounding soil is a major source of uncertainty in estimating the safety margins of support structures. The safety margins are generally closely correlated with the modal properties (natural frequencies, damping ratios). This admits the possibility of using modal identification techniques to reassess the structural safety after installing and commissioning the wind farm. Since design standards require conservative design margins, the post‐installation safety assessment is likely to reveal better than expected structural safety performance. Thus, if load‐reducing controls have been adopted in the structural design process, it is likely permissible to reduce the use of these during actual operation. Here, the probabilistic outcome of such a two‐stage controls adaptation is analyzed. The analysis considers the structural design of a 10 MW monopile offshore wind turbine under uncertainty in the site‐specific soil conditions. Two control strategies are considered in separate analyses: (a) tower feedback control to increase the support structure's fatigue life and (b) peak shaving to increase the support structure's serviceability capacity. The results show that a post‐installation adaptation can reduce the farm‐level side‐effects of load‐reducing controls by up to an order of magnitude.     

Minimization of the energy storage requirements of a stand‐alone wind power installation by means of photovoltaic panels

Autonomous wind power systems are among the most interesting and environmentally friendly technological solutions for the electrification of remote consumers. In many cases, however, the battery contribution to the initial or the total operational cost is found to be dominant, discouraging further penetration of the available wind resource. This is basically the case for areas possessing a medium–low wind potential. On the other hand, several isolated consumers are located in regions having the regular benefit of an abundant and reliable solar energy supply. In this context the present study investigates the possibility of reducing the battery size of a stand‐alone wind power installation by incorporating a small photovoltaic generator. For this purpose an integrated energy production installation based exclusively on renewable energy resources is hereby proposed. Subsequently a new numerical algorithm is developed that is able to estimate the appropriate dimensions of a similar system. According to the results obtained by long‐term experimental measurements, the introduction of the photovoltaic panels considerably improves the operational and financial behaviour of the complete installation owing to the imposed significant battery capacity diminution. Copyright © 2006 John Wiley & Sons, Ltd.     

Long‐term loads for a monopile‐supported offshore wind turbine

Accurate prediction of long‐term ‘characteristic’ loads associated with an ultimate limit state for design of a 5‐MW bottom‐supported offshore wind turbine is the focus of this study. Specifically, we focus on predicting the long‐term fore–aft tower bending moment at the mudline and the out‐of‐plane bending moment at the blade root of a monopile‐supported shallow‐water offshore wind turbine. We employ alternative probabilistic predictions of long‐term loads using inverse reliability procedures in establishing the characteristic loads for design. Because load variability depends on the environmental conditions (defining the wind speed and wave height), we show that long‐term predictions that explicitly account for such load variability are more accurate, especially for environmental states associated with above‐rated wind speeds and associated wave heights. Copyright © 2012 John Wiley & Sons, Ltd.     

Optimal asset allocation of wind energy units in conjunction with demand response for a large‐scale electric grid

Demand response is considered to be a realistic and comparatively inexpensive solution aimed at increasing the penetration of renewable generations into the bulk electricity systems. The work in this paper highlights the demand response in conjunction with the optimal capacity of installed wind energy resources allocation. Authors proposed a total annual system cost model to minimize the cost of allocating wind power generating assets. This model contains capacity expansion, production, uncertainty, wind variability, emissions, and elasticity in demand to find out cost per hour to deliver electricity. A large‐scale electric grid (25 GW) is used to apply this model. Authors discovered that demand response based on interhourly system is not as much helpful as demand response grounded on intrahourly system. According to results, 32% wind generation share will provide the least cost. It is also worth noting that optimal amount of wind generation is much sensitive to installation cost as well as carbon tax.     

Downwind pre‐aligned rotors for extreme‐scale wind turbines

Downwind force angles are small for current turbines systems (1–5 MW) such that they may be readily accommodated by conventional upwind configurations. However, analysis indicates that extreme‐scale systems (10–20 MW) will have larger angles that may benefit from downwind‐aligned configurations. To examine potential rotor mass reduction, the pre‐alignment concept was investigated a two‐bladed configuration by keeping the structural and aerodynamic characteristics of each blade fixed (to avoids a complete blade re‐design). Simulations for a 13.2 MW rated rotor at steady‐state conditions show that this concept‐level two‐bladed design may yield 25% rotor mass savings while also reducing average blade stress over all wind speeds. These results employed a pre‐alignment on the basis of a wind speed of 1.25 times the rated wind speed. The downwind pre‐aligned concept may also reduce damage equivalent loads on the blades by 60% for steady rated wind conditions. Even higher mass and damage equivalent load savings (relative to conventional upwind designs) may be possible for larger systems (15–20 MW) for which load‐alignment angles become even larger. However, much more work is needed to determine whether this concept can be translated into a practical design that must meet a wide myriad of other criteria. Copyright © 2017 John Wiley & Sons, Ltd.     

Multi‐agent‐based sharing power economy for a smart community

In this paper, a multi‐agent‐based locally administrated power distribution hub (PDH) for social welfare is proposed that optimizes energy consumption, allocation, and management of battery energy storage systems (ESSs) for a smart community. Initially, formulation regarding optimum selection of a power storage system for a home (in terms of storage capacity) is presented. Afterwards, the concept of sharing economy is inducted in the community by demonstrating PDH. PDH is composed of multiple small‐scale battery ESSs (each owned by community users), which are connected together to form a unified‐ESS. Proposed PDH offers a localized switching mechanism that takes decision of whether to buy electricity from utility or use unified‐ESS. This decision is based on the price of electricity at ‘time of use’ and ‘state of charge’ of unified‐ESS. In response to power use or share, electricity bills are created for individual smart homes by incrementing or decrementing respective submeters. There is no buying or selling of power from PDH; there is power sharing with the concept of ‘no profit, no loss’. The objective of the proposed PDH is to limit the purchase of electricity on ‘high priced’ hours from the utility. This not only benefits the utility at crucial hours but also provides effective use of power at the demand side. The proposed multi‐agent system depicts the concept of sharing power economy within a community. Finally, the proposed model is analyzed analytically, considering on‐peak, off‐peak, and mid‐level (mid‐peak) prices of a real‐time price signal during 24 h of a day. Results clearly show vital financial benefits of ‘sharing power economy’ for end users and efficient use of power within the smart community. Copyright © 2017 John Wiley & Sons, Ltd.     

Multi‐hazard reliability assessment of offshore wind turbines

A probabilistic framework is developed to assess the structural performance of offshore wind turbines under multiple hazards. A multi‐hazard fragility surface of a given wind turbine support structure and the seismic and wind hazards at a specific site location are incorporated into the probabilistic framework to assess the structural damage due to multiple hazards. A database of virtual experiments is generated using detailed three‐dimensional finite element analyses of a set of typical wind turbine systems subject to extreme wind speeds and earthquake ground motions. The generated data are used to develop probabilistic models to predict the shear and moment demands on support structures. A Bayesian approach is used to assess the model parameters incorporating the information from virtual experiment data. The developed demand models are then used to estimate the fragility of the support structure of a given wind turbine. As an example of the proposed framework, the annual probabilities of the occurrence of different structural damage levels are calculated for two identical wind turbines, one located in the Gulf of Mexico of the Texas Coast (prone to hurricanes) and one off the California Coast (a high seismic region). Copyright © 2014 John Wiley & Sons, Ltd.     

Estimation of offshore extreme wind from wind‐wave coupled modeling

A coupledwind‐wave modeling system is used to simulate 23 years of storms and estimate offshore extreme wind statistics. In this system, the atmospheric Weather Research and Forecasting (WRF) model and Spectral Wave model for Near shore (SWAN) are coupled, through a wave boundary layer model (WBLM) that is implemented in SWAN. The WBLM calculates momentum and turbulence kinetic energy budgets, using them to transfer wave‐induced stress to the atmospheric modeling. While such coupling has a trivial impact on the wind modeling for 10‐m wind speeds less than 20 ms^?1, the effect becomes appreciable for stronger winds—both compared with uncoupled WRF modeling and with standard parameterization schemes for roughness length. The coupled modeling output is shown to be satisfactory compared with measurements, in terms of the distribution of surface‐drag coefficient with wind speed. The coupling is also shown to be important for estimation of extreme winds offshore, where the WBLM‐coupled results match observations better than results from noncoupled modeling, as supported by measurements from a number of stations.     

Integrated offshore wind farm design: Optimizing micro‐siting and cable layout simultaneously

Electrical layout and turbine placement are key design decisions in offshore wind farm projects. Increased turbine spacing minimizes the energy losses caused by wake interactions between turbines but requires costlier cables with higher rates of failure. Simultaneous micro‐siting and electrical layout optimization are required to realize all possible savings. The problem is complex, because electrical layout optimization is a combinatorial problem and the computational fluid‐dynamics calculations to approximate wake effects are impossible to integrate into classical optimization. This means that state‐of‐the‐art methods do not generally consider simultaneous optimization and resort to approximations instead. We extend an existing model that successfully optimizes cable design to simultaneously consider micro‐siting. We use Jensen's equations to approximate the wake effect in an efficient manner, calibrating it with years of mast data. The wake effects are precalculated and introduced into the optimization problem. We solve simultaneously for turbine spacing and cable layout, exploiting the tradeoffs between these wind farm features. We use the Barrow Offshore Wind Farm as a case study to demonstrate realizable savings up to 6 MEUR over the lifetime of the plant, although it is possible that unforeseen design constraints have implications for whether the savings seen in our model are fully realizable in the real world. In addition, the model provides insights on the effects of turbine spacing that can be used to simplify the design process or to support negotiations for surface concession at the earlier stages of a project.     

An M‐Rice wind speed frequency distribution

Several known statistical distributions can describe wind speed data, the most commonly used being the Weibull family. In this paper, a new law, called ‘M‐Rice’, is proposed for modeling wind speed frequency distributions. Inspired by recent empirical findings that suggest the existence of some cascading process in the mesoscale range, we consider that wind speed can be described by a seasonal AutoRegressive Moving Average (ARMA) model where the noise term is ‘multifractal’, i.e. associated with a random cascade. This leads to the distribution of wind speeds according to the M‐Rice probability distribution function, i.e. a Rice distribution multiplicatively convolved with a normal law. A comparison based on the estimation of the mean wind speed and power density values as well as on the different goodness‐of‐fit tests (the Kolmogorov–Smirnov test, the Kuiper test and the quantile–quantile plot) was made between this new distribution and the Weibull distribution for 35 data sets of wind speed from the Netherlands and Corsica (France) sites. Accordingly, the M‐Rice and Weibull distributions provided comparable performances; however, the quantile–quantile plots suggest that the M‐Rice distribution provides a better fit of extreme wind speed data. Beyond these good results, our approach allows one to interpret the observed values of Weibull parameters. Copyright © 2011 John Wiley & Sons, Ltd.     

Redefinition power curve for more accurate performance assessment of wind farms

The lack of accurate methods for assessment of the productive capacity of wind power plants is becoming a bottleneck in an increasingly commercialized wind power industry. In this article the inherent components of performance assessment are identified and analysed and ways of minimizing uncertainties on the components are investigated. The main components are identified as ‘site calibration’, ‘wind turbine sensitivity to flow variables’, ‘plant blockage effects’ and ‘uncertainty analysis’. Site calibration is the action of estimating the flow variables at the wind turbine position from measurements of these quantities at another (reference) position. The purpose of sensitivity analysis is to clarify which and how flow variables influence power output. Plant blockage effects refer to the power plant's influence on the reference measurements of flow variables. Finally, the component uncertainties and in turn the integrated uncertainty on the average productive capacity of the wind power plant are investigated. It is found that uncertainties can be reduced (1) by including several more flow variables in addition to hub‐height wind speed, (2) by carrying out site calibration with utmost care and by inclusion of more variables, (3) by taking plant blockage into consideration, (4) by aiming at ‘plant‐average’ power instead of looking only at individual machines and, possibly, (5) by introduction of remote‐sensing anemometer techniques. Copyright © 2000 John Wiley & Sons, Ltd.     

An Integrated Feasibility Analysis of a Stand‐alone Wind Power System,including No‐energy Fulfillment Cost

Autonomous wind power systems are among the most interesting and environmentally friendly technological solutions for the electrification of remote consumers. However, the expected system operational cost is quite high, especially if the no‐load rejection restriction is applied. This article describes an integrated feasibility analysis of a stand‐alone wind power system, considering, beyond the total long‐term operational cost of the system, the no‐energy fulfilment (or the alternative energy coverage) cost of the installation. Therefore the impact of desired system reliability on the stand‐alone system configuration is included. Accordingly, a detailed parametric investigation is carried out concerning the influence of the hourly no‐energy fulfilment cost on the system dimensions and operational cost. Thus, by using the proposed method, one has the capability–in all practical cases–to determine the optimum wind power system configuration that minimizes the long‐term total cost of the installation, considering also the influence of the local economy basic parameters. Copyright © 2003 John Wiley & Sons, Ltd.     

Impact of battery storage on economics of hybrid wind‐diesel power systems in commercial applications in hot regions

Integration of wind machines and battery storage with the diesel plants is pursued widely to reduce dependence on fossil fuels. The aim of this study is to assess the impact of battery storage on the economics of hybrid wind‐diesel power systems in commercial applications by analyzing wind‐speed data of Dhahran, East‐Coast, Kingdom of Saudi Arabia (K.S.A.). The annual load of a typical commercial building is 620,000 kWh. The monthly average wind speeds range from 3.3 to 5.6 m/s. The hybrid systems simulated consist of different combinations of 100‐kW commercial wind machines (CWMs) supplemented with battery storage and diesel generators. National Renewable Energy Laboratory's (NREL's) (HOMER Energy's) Hybrid Optimization Model for Electric Renewables (HOMER) software has been employed to perform the economic analysis. The simulation results indicate that for a hybrid system comprising of 100‐kW wind capacity together with 175‐kW diesel system and a battery storage of 4 h of autonomy (i.e. 4 h of average load), the wind penetration (at 37‐m hub height, with 0% annual capacity shortage) is 25%. The cost of generating energy (COE, $/kWh) from this hybrid wind–battery–diesel system has been found to be 0.139 $/kWh (assuming diesel fuel price of 0.1$/L). The investigation examines the effect of wind/battery penetration on: COE, operational hours of diesel gensets. Emphasis has also been placed on un‐met load, excess electricity, fuel savings and reduction in carbon emissions (for wind–diesel without battery storage, wind–diesel with storage, as compared to diesel‐only situation), cost of wind–battery–diesel systems, COE of different hybrid systems, etc. The study addresses benefits of incorporation of short‐term battery storage (in wind–diesel systems) in terms of fuel savings, diesel operation time, carbon emissions, and excess energy. The percentage fuel savings by using above hybrid system is 27% as compared to diesel‐only situation Copyright © 2012 John Wiley & Sons, Ltd.     

Meeting modern grid codes with large direct‐drive permanent magnet generator‐based wind turbines—low‐voltage ride‐through

Ambitious offshore wind energy targets continue to drive technological innovation, with the latest direct‐drive permanent magnet generator‐based wind turbines promising higher efficiency and availability. However, these machines have fixed rotor flux, provided by the magnets, which means that their voltage rises with speed. Further, high machine stator reactance leads to significant magnetic energy storage in the stator windings. Both these aspects provide new challenges for the power converter when designing to meet modern low‐voltage ride‐through requirements. This paper therefore proposes a novel control strategy, using a minimally rated chopper and dynamic brake resistor (DBR) integrated with the wind turbine's power converter, to help these systems to meet the demands of modern grid codes. This control method may allow the chopper and DBR to be rated at only 40% of a fully rated version. Despite only partially rating the DBR system, the control method minimizes the torsional oscillations in the drive train, thereby protecting the mechanical system. Copyright © 2011 John Wiley & Sons, Ltd.     

Wind turbines and seismic hazard: a state‐of‐the‐art review

Wind energy is a rapidly growing field of renewable energy, and as such, intensive scientific and societal interest has been already attracted. Research on wind turbine structures has been mostly focused on the structural analysis, design and/or assessment of wind turbines mainly against normal (environmental) exposures while, so far, only marginal attention has been spent on considering extreme natural hazards that threat the reliability of the lifetime‐oriented wind turbine's performance. Especially, recent installations of numerous wind turbines in earthquake prone areas worldwide (e.g., China, USA, India, Southern Europe and East Asia) highlight the necessity for thorough consideration of the seismic implications on these energy harnessing systems. Along these lines, this state‐of‐the‐art paper presents a comparative survey of the published research relevant to the seismic analysis, design and assessment of wind turbines. Based on numerical simulation, either deterministic or probabilistic approaches are reviewed, because they have been adopted to investigate the sensitivity of wind turbines' structural capacity and reliability in earthquake‐induced loading. The relevance of seismic hazard for wind turbines is further enlightened by available experimental studies, being also comprehensively reported through this paper. The main contribution of the study presented herein is to identify the key factors for wind turbines' seismic performance, while important milestones for ongoing and future advancement are emphasized. Copyright © 2016 John Wiley & Sons, Ltd.     

Effect of increased wind penetration on system prices in Korea's electricity markets

In this paper, we examine the effect of increased wind penetration on system marginal prices (SMPs) in South Korea's electricity market. Korea's renewable portfolio standard (RPS) went into effect in 2012, with a goal of increasing the share of renewable generation to 10% of the total load by 2022. We examine the output of wind installations across the Korean peninsula and simulate an increase in wind penetration consistent with Korea's RPS targets. Under a variety of assumptions on demand elasticity, we find that higher shares of wind generation in total supply reduce both the average SMP and its variation. In particular, we find that wind energy output on the Korean peninsula is more correlated with peak electricity demand than has been reported for other regions. The per‐unit value of wind energy to owners of wind assets is thus higher for South Korea than would be the case for European or North American locations with a similar mix of fuels other than wind. Copyright © 2013 John Wiley & Sons, Ltd.