Online distributed learning in wind power forecasting

Wind power is one of the most efficient renewable resources without emissions. Nonetheless, it is difficult to exactly forecast wind power generation given historical power and wind speed information, the failure of which may cost the risk of large-scale outages. This article takes a close look at the artificial recurrent neural network framework in the application of wind power forecasting. More intelligent mechanisms using attention to capture spatial-temporal patterns within historical data are emphasized in this work and are shown to be state-of-the-art for short-term wind power forecasting. Our experiments at a wind farm in southeast Australia using only the historical wind power generation and wind speed records from ambient weather stations show that, e.g., 7.4750% in mean absolute error (MAE) and 0.3345 in the coefficient of variation in the root mean squared error (CV-RMSE) for half-hour-ahead prediction. To interpret how the three models under consideration—the long- and short-term time-series network (LSTNet), the temporal pattern attention-based long short-term memory (TPA-LSTM) and the dual-stage attention-based recurrent neural network (DA-RNN)—work, we visualize and analyze the details of the models so that further improvement can be made by combining the advantageous components of the models.

The electrical systems needed for offshore wind farms to collect power from wind turbines-and transmit it to shore- will be a significant cost element of these systems. This paper describes the development of a simplified model of the cost and performance of such systems. The performance prediction accounts for losses as a function of the power produced in the wind farm and the length and size of the cables. The cost prediction is flexibly formulated so wind farm configurations can be evaluated by parameters such as the number of wind turbines, wind turbine size, turbine array configuration and spacing, and distance from shore. The collection system-the medium-voltage electrical grid within the wind farm, and the transmission system-the high-voltage electrical connection to an on-shore transmission line-are treated independently in the model. Data sources for the model and limitations of the data are discussed, and comparison is made to costs reported by others. The choice of transmission system technology is also addressed. This electrical system model is intended for integration into a more comprehensive model of offshore wind farm design, cost, and performance that will be used for parametric studies and optimization of wind farm configurations. Because some concepts for future offshore wind installations in deep water use floating platforms, this paper briefly discusses the application of submarine cable technology to nonfixed termination points, a departure from current practice. Introduction The National Wind Technology Center (NWTC) of the National Renewable Energy Laboratory (NREL) in Golden, Colorado, has undertaken a series of concept studies to evaluate the cost and performance of offshore wind farms. The product of these studies will be a comprehensive model of offshore wind farm design, cost, and performance suitable for parametric studies and optimization of wind farmconfigurations. The overall goal of this effort is to helpidentify technology pathways for offshore wind energy development and deployment in the United States. Offshore wind farms present an attractive option because they allow for larger wind turbines that operate in higher wind resources than land-based [1,2]. Offshore installations are also more expensive, so an understanding of their performance, cost, and optimal configurations is needed. This paper is an overview of one of these concept studies. It focuses on the power losses in wind farm electrical power collection and transmission systems, as well as the costs of the system components and their installation. A hypothetical system was based loosely on the Horns Rev offshore wind farm in Denmark. Inquiries were made with manufacturers about electrical and cost data on the required components, which were then compiled in a spreadsheet model. The performance prediction accounts for losses as a function of power output of the wind farm and length and size of the cables. The cost prediction is flexibly formulated so wind farm configurations can be evaluated by parameters such as the number of wind turbines, wind turbine size, turbine array configuration and spacing, and distance from shore.

The development of wind power generation can promote the transformation of energy structure and the green development of the economy. The land is the spatial carrier of wind power generation projects, which has a basic supporting role for wind power generation. This paper analyzes the situation of land utilization for wind power generation, sorts out relevant national policy documents, and summarizes the problems existing in the implementation of wind power projects, which is of great significance for promoting the development of the wind power industry. The results showed that the installed capacity of wind power and electricity generation increased rapidly in the past decade. The land supplied area for wind power generation reached its peak in 2016 and then fluctuated, with the land supplied area decreasing but the power generation efficiency improving. In the process of wind power land utilization in China, there are some problems, such as the insufficient connection between industry planning and territorial spatial planning, lack of coordination mechanism between government departments for examination and approval, lack of land standards, prominent problems in the use of stock land and the renewal and renovation of old wind farms, and complicated land requisition compensation. Based on this, the paper puts forward corresponding countermeasures and suggestions from the aspects of territorial space planning, land use examination and approval, land use standard, utilization of stock land, popularization and application of land saving technology and land saving mode.

The demand on energy supply increases continuously as economies develop and world population grows. Most of the energy in the world comes from the fossil fuels and the increase in energy demand accelerates the rate of depleting the fossil fuel resources. As fossil fuel is finite and also due to the environmental considerations, renewable energy (RE) resources have been actively developed as the alternative sources for electricity generation. Renewable sources used for large-scale electricity production can include wind, photovoltaic (PV), waves and so on. Among all the RE resources, wind power generation is witnessing rapid developments in recent years. Unfortunately, wind tends to be unsteady. The fluctuating and uncertain output powers from wind farms can be problematic, especially if there is a high penetration level of the renewable source in a grid system. The fluctuations may lead to excessive voltage variations and unacceptable degree of frequency deviations. Moreover, the unsteady and uncertain input wind power can cause firm power dispatch commitment from wind farms a difficult task. Expensive generation reserves have to be provided for grid system to ensure adequate level of system security and reliability is guaranteed. In fact, power generation from wind farms has often been excluded in the dispatch planning of the grids. Unless other viable techniques can be found, the above issues can constitute major impediment to the successful large-scale integration of wind power generation into grid systems. In this connection, the use of energy storage system (ESS) is one possible solution to mitigate the negative impacts of the unsteady wind power on electricity supply systems and to improve on the dispatchability of the wind power. In this investigation, in order to smoothen the fluctuations in the wind and to realize the dispatch planning of the wind power in a way similar to that of conventional generators, it is proposed that a three-level ESS is incorporated in a large-scale wind power generation scheme. In essence, at cluster-level of wind turbine generators (WTG), the solution involves having the high- and mid-frequency components of the aggregated wind power routed to supercapacitors (SC) and battery banks respectively of a battery-supercapacitor hybrid energy storage system (BSHESS) by a high-pass filter (HPF) and a band-pass filter (BPF). It then results in the smoothening of the wind power harnessed by the cluster. In this thesis, the BSHESS control scheme to reduce the wind power perturbations has been shown. A statistical method is also developed to determine the capacities of the minimum-cost BSHESS to meet the power smoothing objective at pre-specified probability level. Application of the proposed design approach is demonstrated using data obtained from an existing wind farm. As for dispatch planning, attention is to use a low-pass filter (LPF) to extract the low-frequency intrinsic mode and residue functions of wind power. The relatively slow-changing characteristics of the low-frequency wind power components, which contain most of the energy in the wind power, allow accurate forecasts of the power components to be obtained using artificial neural network (ANN). Dispatch planning of the wind power is then realized through buffering the low-frequency power fluctuations by a proposed power flows control strategy applied to a pumped hydroelectric storage (PHS) system. Focusing on low-frequency wind power for dispatch planning is a distinct advantage over the dispatch planning methods proposed by other researchers. Furthermore, a statistical method to determine the power and energy capacities of the PHS is included. The efficacy of the developed approach to dispatch planning is again illustrated based on data obtained from an existing wind farm. In all the above works, suitable cut-off frequencies for the HPF, BPF and LPF are derived based on the developed concept of minimum overlap energy and the outcome of empirical mode decomposition (EMD) analysis. EMD method is used to gain insights into the frequency-time characteristics of wind power. In this manner, the wind power can then be grouped into high-, mid- and low-frequency bands.

Wind power is currently the fastest growing power generation sector in the world-worldwide growth in wind power generation has been at 40% a year for the last 10 years. With this rapid growth of generation, new challenges are being introduced to power markets. Wind power is an intermittent source. For example, at a wind site in Tasmania, Australia, the average change in mean wind speed vectors over a 2.5- minute period is about 44.4% and the average change in maximum wind speeds over the same period is 55.0%. This demonstrates that the wind speed and its direction can change rapidly by a large amount over a very short period of time. Great variability in wind farm generation has both technical and commercial implications for the efficient planning and operation of power systems. Large wind farms tend to use large wind turbines. Large turbines have a significant rotational inertia when considering a short time frame. As a result, wind patterns shorter than 10 seconds usually have a negligible effect on the turbine output, and it is a standard practice in wind generation to neglect short-term gusts. However, trends over several minutes are of vital importance. In order to accommodate the increase in wind power generation, we need to change the way that wind generation is scheduled. Both utilities and electricity market operators will be required to forecast the wind generation to improve system performance. Wind generation will have to be bid into the market like any other generation. In order to handle these requirements, power system operators will need to have better wind forecasting models and tools. Forecasting is a vital part of business planning in today’s competitive environment, regardless of the field in which you work. To be ready for a situation before it occurs gives a distinct advantage over the competition. Wind prediction is complex due to the wind’s high degree of volatility and deviation. This means that standard time length definitions for power engineering do not strictly apply. The phrase shortterm in the case of wind forecasting, normally means periods from minutes out to half an hour while longterm forecasting means periods from several hours out to a few days. This difference between the two forecasting time periods is important when it comes to creating a prediction system. Three main classes of different techniques have been used for wind power forecasting. These are numerical weather prediction (NWP) methods, statistical methods, and methods based on applications of artificial neural networks (ANN) and adaptive neuro-fuzzy inference systems (ANFISs). TheNWP methods are dominant for forecasts over 10 hours ahead. However, statistical and ANN-based methods appear to be more accurate over shorter periods (minutes to a few hours). They are also much simpler than the NWP methods.

A multiscale numerical framework coupled with control strategies for simulating a wind farm in complex terrain

Wind energy is a rapidly expanding source of renewable energy, but is highly intermittent. The performance of a wind farm, composed of a collection of wind turbines, depends not only on the placement of wind turbines in a farm, but also control actions taken by individual turbines. The wind turbine placement (layout) design problem involves adjusting turbine locations within a given area to improve a performance objective (such as maximizing annualized energy production). This layout problem has been addressed previously considering the effect of constraints such land configuration, installed capacity, and wake model choice on the performance of wind farms. All the studies, however, ignore the effects of the control system, which can have significant impact on performance. A well designed wind farm — without an optimal controller — will not achieve the full system level optimal performance, and vice-versa. In this article, we propose a novel layout co-design approach that includes optimal control considerations to exploit this synergy between farm layout and control. Layout case studies involving 8 and 12 turbines are presented. An annual energy production improvement of up to 17% is observed when accounting for coupling between control and layout design, when compared to layout-only optimization.

Electrical systems endowed with variable generating units will dominate the electrical landscape in the near future. These types of generating units will bring new opportunities to utilities, companies and customers, but they will also bring new problems to electrical companies. As wind power generation is one of the most important renewable energy sources, because its production is environmentally clean, it is important to achieve proper locations for new wind farms. So, to evaluate their impact on the electrical network it is necessary to develop an accurate wind farm model for the network analysis program. This paper presents the model of a wind farm exclusively made up of double fed induction machines.

Wind Turbine Operation and Maintenance Video Supportive System Based on the Mobile Internet of Things

Effects of Large Scale Wind Power on Total System Variability and Operation: Case Study of Northern Ireland

Wind power forecast plays an important role in wind farm operation and grid scheduling decisions. Prediction of power output from wind vector based on wind farm equivalent power curve is the final step of forecast, which has a lot of interaction with the grid dispatching, and it has a particularly prominent influence on the wind farm power output so as to cut down prediction accuracy. Focusing on the step of "wind-power transformation", a correction method of day-ahead wind power forecast including multiple factors such as wind-abandon coefficient is proposed in this paper. Firstly, it is proved that the wind power prediction error is affected by a variety of factors, such as the amplitude of predicted power, the volatility of forecast as well as the stability of recent wind power output. And a model is built to quantify them respectively. Then the wind-abandon coefficient is introduced to modeling the effect of wind power curtailment activities of grid dispatching to forecast accuracy. Finally, the evaluation model of wind power forecasting error is built by using the multiple linear regression method and corrects the predictive value. Case study basing on the actual operation data of a wind farm in northern China has shown that the proposed method is effective to improve the accuracy level of wind power forecast.

This study investigates the effects of the construction and operation of a large Danish offshore wind farm on harbor and gray seal haul-out behavior within a nearby (4 km) seal sanctuary. Time-lapse photography, visual monitoring, and aerial surveys were used to monitor the number of seals on land in daylight hours. Seals were monitored during two preconstruction periods (19 June–31 August 2001 and April–August 2002), a construction period of the wind farm (August 2002–December 2003), and a period of operation of the wind farm (December 2003–December 2004). Monthly aerial surveys were conducted to estimate the proportion of seals in the sanctuary relative to neighboring haul-out sites. From preconstruction to construction and through the first year of operation the number of harbor seals in the sanctuary increased at the same rate as the number of seals at the neighboring haul-out sites. No long-term effects on haul-out behavior were found due to construction and operation of the wind farm. However, a significant short-term decrease was seen in the number of seals present on land during sheet pile driving in or near the wind farm. Acoustic deterrents were utilized simultaneously to avoid hearing damage.

With the rapid increase of wind power centralized grid-connection scale, the security and stability of power grid are greatly affected. In order to simulate the dynamic characteristics of wind farm accurately, a large-scale wind power online equivalent method based on multi-source data fusion is proposed. The operating state of the state estimation modeling network is identified by the fusion of multi-source real-time data such as SCADA, PMU and security and stability control system. When the error of branch power flow or node voltage at the boundary is large, the active power regulation range of wind power generators is determined by comprehensively considering the actual measurement collected by the wind farm centralized control system and the prediction information of the wind power prediction system. The active power of each wind farm is determined by quadratic programming model. The wind power generators are grouped according to the topology in the wind farm, then each group is subdivided according to static characteristic and operating state in turn. The dynamic models and static parameters of equivalent wind power generators and equivalent transformers are calculated. The proposed method is proved to be fast and effective through the analysis of a practical power grid example.

Investigation of the impact of planetary boundary layer turbulence on the performance of onshore wind farm

Wind power is widely used and creates value worldwide. However, it also poses a threat to the survival of soaring birds. This study focuses on the role of government restrictions in mitigating the adverse effects of wind power on soaring birds. We used an overall research method to identify research questions, selected typical wind farms from different provinces and topographic landscapes in China for descriptive analysis, and supported by data from environmental impact reports, government gazettes, and walk-through surveys, analyzed and concluded that government restrictions can be used as a means of weakening the impacts of wind power generation on soaring birds. And our findings suggest that site control for wind farms that have not yet been established, restrictions on the timing of power generation for wind farms in operation, and ecological restoration of wind farms that have caused environmental damage are effective implementation options for government restrictions. Additionally, the policy strengths of the above government restrictions are guided, recommended, and mandatory, respectively. Government restrictions can serve as an effective means of mitigating the negative impact of wind power on soaring birds, generating economic value while maximizing the protection of soaring birds’ subsistence. Based on our findings, we call on governments to pay attention to the negative impacts of wind farms on soaring birds and put forward three concrete and feasible recommendations, expecting countries to enact governmental constraints to find a balance between economic, social, and ecological benefits.