Wind Power Capacity Research Articles

Deep reinforcement learning-based multi-objective optimization for electricity–gas–heat integrated energy systems

With the increasing global attention on energy efficiency and carbon emissions, the optimization of integrated energy systems (IES) has become the key to improve energy efficiency and reduce pollution emissions. However, most of the existing optimization methods cannot effectively deal with the complexity of high dimensional continuous action space. Therefore, this paper focuses on a novel multi-objective optimization strategy for the electricity–gas–heat integrated energy systems (EGH-IES). Firstly, considering the absorption capacity of wind power and the emission of pollutant gases, a multi-objective optimization model is constructed based on the mechanism model and operation constraints of each device in EGH-IES, in which the integrated operation cost and the environmental factors are taken as optimization objectives. Then, the multi-objective optimization problem is designed as the optimal strategy of interaction learning between agent and environment in reinforcement learning, and the output power of the devices constitutes the action of reinforcement learning. Additionally, the Ornstein–Uhlenbeck process is introduced to enhance the training efficiency and exploration performance of the agent, and the deep deterministic policy gradients (DDPG) algorithm is employed to optimize the action, thus the output power of the appliances could be obtained. Finally, the simulation results show that compared with deep Q network (DQN) method and proximal policy optimization (PPO) method, the reward function value of the proposed method increases by 2.43% and 6.09%, respectively, which represents a reduction in economic cost and pollutant emissions. These verify the effectiveness and superiority of the proposed multi-objective optimization scheme in cost reduction and benefit improvement for the EGH-IES.

Robust wind power capacity planning under fuel price uncertainty using conic duality theory and piecewise McCormick relaxation

Increasing the proportion of renewable energy sources (RESs) in power generation is crucial due to fossil fuel depletion and rising environmental pollution. In this regard, identifying the most lucrative sites and sizes for installing wind farms, as one of the fastest-growing types of RESs, is imperative. This paper presents a robust profit-oriented wind power capacity planning (WPCP) considering long- and short-term uncertainty. The model forms a two-stage min-max-min hierarchical structure. The first stage minimizes the investment cost plus maximum regret, while the second stage maximizes the profit under the worst-case uncertainty realization. Unlike the existing approaches where uncertainty in fossil fuel prices is neglected, we model fuel price uncertainty using both polyhedral and ellipsoidal uncertainty sets. In this respect, the third level is formulated as a bi-level program, with the upper level being the profit maximization and the lower level being the locational marginal price (LMP) calculation. In the case of the ellipsoidal set, the conic duality theory is employed to dualize the lower level. The piecewise McCormick relaxation (PMR) technique linearizes the bilinear terms. The nested column-and-constraint generation (NCCG) technique solves the formulated problem. A clarifying case study is employed to demonstrate the efficacy of the proposed model.

Strategies for sustainable development of offshore wind power in regions with limited resources

Offshore wind power, as a renewable energy source, possesses significant potential in the process of decarbonizing the energy system. Despite the current lack of economic competitiveness compared to other renewable energy sources, offshore wind power development has not received due attention. Nonetheless, it holds significant potential for future growth given the dual pressures of increasing power demand and carbon reduction. Consequently, a bottom-up energy system planning model is developed to consider the simultaneous transition of supply and demand sides, focusing on offshore wind power development and integration in Hebei, China, a region with limited resources. The analysis indicates that by 2060, Hebei could potentially install up to 20 GW of offshore wind power capacity, with the Tangshan area identified as a suitable location for wind power integration. In current policy background, which is considered more aggressive, the annual cost across the entire system is projected to increase by 7 %. Offshore wind power is deemed particularly suitable for hydrogen production to mitigate seasonal fluctuations, contingent upon synchronized energy transition on the demand side and corresponding hydrogen demand. A typical operational strategy involves hydrogen production from offshore wind power during winter and spring, with storage or utilization during summer and autumn.

Flexibility Assessment of Ternary Pumped Storage in Day-Ahead Optimization Scheduling of Power Systems

To explore the advantages in the flexibility of ternary pumped storage units (T-PSUs) compared with fixed-speed pumped storage units (FS-PSUs) and variable-speed pumped storage units (VS-PSUs) in the day-ahead optimal scheduling of power systems, this paper firstly establishes the mathematical model of T-PSUs which is suitable for the target application, and establishes a new hybrid pumped storage model combining both FS-PSUs and T-PSUs for the purpose of improving existing FS-PSUs. Secondly, a day-ahead optimal scheduling model used for a wind-thermal-pumped storage bundled transmission system with the goal of obtaining the lowest operating cost is established. Additionally, various indicators are proposed to comprehensively evaluate the flexibility of different pumped storage unit types on day-ahead optimal scheduling. Finally, a sensitivity analysis is conducted from three aspects: covering the wind power capacity, load rate, and pumped storage capacity. The results indicate that T-PSUs are superior to FS-PSUs and VS-PSUs in maintaining the smooth, economic, and robust operation of thermal power units, as well as in promoting wind power consumption. This provides a significant reference for evaluating the technical and economic benefits of the different types of pumped storage units in applications of future power grids.

Hydrogen production from treated wastewater powered by solar–wind energy: Feasibility analysis and optimal planning

Wastewater treatment plants can provide a sustainable solution for hydrogen production by harnessing renewable energy and using treated water as feedstock as hydrogen demands in the future are expected to increase significantly. This study provides a decision-making model that enables the determination of optimal capacities of solar power, wind power, reverse osmosis, electrolyser, storage tank, and optimal hourly grid import. Such a project simultaneously provides electricity for hydrogen production and wastewater treatment, and sells hydrogen and renewable energy certificates. The planning aims to maximise the annual profits and renewable energy ratio. The case study shows that coupling a 120,000 m3/day plant scale with a 5 ton/day hydrogen facility shows a gross profit margin of 35.2%, a payback period of 7.2 years. This outperforms scenarios that exclude land and energy constraints in wastewater treatment plants. The influence of renewable energy ratios, hydrogen demand, and the prospective water usage for future regional scenario are further discussed.

Evaluating clean electricity transition progress across UK political pledges and G7 countries

The transition towards clean electricity is central to global decarbonisation. Countless metrics are used to assess national electricity transition efforts, which hinders understanding and comparison between nations or political party pledges. This study instead proposes three simple metrics: clean generation share, gross, and net carbon emissions intensity. It uses them to provide the first evaluation of the 2024 Clean Energy Mission (CEM) proposed by the UK's newly-elected Labour Government, which has strengthened ambition for wind and solar power capacity. We compare the CEM to previous political pledges, finding it could reduce national electricity generation emissions by 17 MtCO2 in 2030, equivalent to a two percentage point increase in the UK's 2030 Nationally Determined Contribution (NDC). We also use these metrics to compare past efforts and future pledges across the G7 countries, finding that the CEM progresses the UK from having the lowest share of clean electricity in 2010 to the highest by 2030. The UK must increase its pace of clean electricity uptake and decarbonisation by a factor of 1.5–2 to meet its 2030 targets; compared to a factor 4–6 acceleration required by Germany and the US. The paper provides an innovative, simple and replicable framework for assessing the impact of political pledges or national targets for the power sector, and for comparing efforts to decarbonise electricity between countries and over time.

A novel offshore wind power prediction model based on TCN-DANet-sparse transformer and considering spatio-temporal coupling in multiple wind farms

Offshore wind power capacity is growing, leading to larger clustered farms. Accurately predicting offshore wind power capacity is crucial for power system stability; however, current studies often overlook neighbouring installations. To address this, this study presents the Temporal Convolutional Network-Dual Attention Network-Sparse Transformer (TCN-DANet-Sparse Transformer) model, which considers the spatiotemporal coupling of multiple wind farms. Before detailing our model, we review the existing prediction methods, noting their limitations in capturing interconnected adjacent wind farms. Our model integrates spatial information from nearby farms to enhance prediction reliability. Through Pearson Correlation Coefficient analysis, we explore the temporal and spatial coupling features. Using overlapping sliding windows, we partition farms into subsequences, processed with TCN-DANet for efficient spatio-temporal feature extraction. These features are then input into the Sparse Transformer to improve the computational efficiency. Validated using a dataset from Kächele et al., our model outperforms the baseline on the London Wind Farm. In spring, for Case 1, the mean square error (MSE) of the main model decreased by 43.19 % compared to that of the TCN-DANet-transformer model. Similarly, for Case 2, the MSE of the main model is reduced by 41.69 %.

Investigating the Structural and Power Performance of a 15 MW Class Wind Energy Generation System under Experimental Wind and Marine Loading

The global transition to renewables in response to climate change has largely been supported by the expansion of wind power capacity and improvements in turbine technology. This is being made possible mainly due to improvements in the design of highly efficient turbines exceeding a 10 MW rated power. Apart from power efficiency, wind turbines must withstand the mechanical stress caused by wind–hydro conditions. Such comprehensive structural analysis has rarely been performed previously, especially for large-scale wind turbines under real environmental conditions. The present work analyzes the energy production and structural performance of an NREL-IEA 15 MW wind turbine using measured wind and hydro data. First of all, an optimum operating range is determined in terms of the wind speed and blade pitch angle to maximize the power coefficient. Then, at this optimum range, a detailed breakdown of the forces and moments acting on different components of the wind turbine is presented. It was found that wind speeds of 9 to 12 m/s are best suited for this wind turbine, as the power coefficient is at its maximum and the mechanical loads on all components are at a minimum. The loads are at a minimum due to the optimized blade pitch angle. The bending force on a monopile foundation (fixed on the seabed) is found to be at a maximum and corresponds to nearly 2000 kN. The maximum blade force is nearly 700 kN, whereas on the tower it is almost 250 kN. The maximum force on the tower occurs at a point which is found to be undersea, whereas above-sea, the maximum force on the tower is nearly 20% less than the undersea maximum force. Finally, seasonal and annual energy production is also estimated using locally measured wind conditions.

Pyrolysis process and products characteristics of glass fiber reinforced epoxy resin from waste wind turbine blades

The installed wind power capacity has reached up to 906 GW globally meaning the usage of wind turbine blades (WTBs) with around 9.06 Mt. The waste WTBs with a rapid growth was estimated to be 72.0 kt in 2022 based on the projected lifetime of 20 years. The recycling of fibers reinforced thermoset polymer from waste WTBs has become a knotty environmental issue. This work aimed at studying the pyrolysis behaviors of a glass fibers reinforced epoxy resin materials from a waste WTBs, and revealing the impacts of pyrolysis atmosphere and temperature on the pyrolysis products. It was found that the black glass fibers with deposited carbon and the clean glass fibers were obtained by pyrolysis in N2 and air, respectively. Both pyrolysis in N2 and air produced the pyrolysis oil and gas with similar compositions. The preferable strength of fibers and yield of oil could be obtained at applicable pyrolysis temperature of 450 °C. The oil yields were 13.17 wt.-% and 11.93 wt.-% by pyrolyzing at 450 °C in N2 and air, respectively. The analysis of pyrolysis pathway suggested that the oxygen promoted the decomposition of epoxy resin into small molecules of gases by pyrolysis in air. The utilization of recycled products gas was also discussed. The findings of this work could provide some suggestions to explore a route with low cost to recycling the waste WTBs by pyrolysis.

Capacity Optimization of Pumped–Hydro–Wind–Photovoltaic Hybrid System Based on Normal Boundary Intersection Method

Introducing pumped storage to retrofit existing cascade hydropower plants into hybrid pumped storage hydropower plants (HPSPs) could increase the regulating capacity of hydropower. From this perspective, a capacity configuration optimization method for a multi-energy complementary power generation system comprising hydro, wind, and photovoltaic power is developed. Firstly, to address the uncertainty of wind and photovoltaic power outputs, the K-means clustering algorithm is applied to deal with historical data on load and photovoltaic, wind, and water inflow within a specific region over the past year. This process helps reduce the number of scenarios, resulting in 12 representative scenarios and their corresponding probabilities. Secondly, with the aim of enhancing outbound transmission channel utilization and decreasing the peak–valley difference for the receiving-end power grid’s load curve, a multi-objective optimization model based on the normal boundary intersection (NBI) algorithm is developed for the capacity optimization of the multi-energy complementary power generation system. The result shows that retrofitting cascade hydropower plants with pumped storage units to construct HPSPs enhances their ability to accommodate wind and photovoltaic power. The optimal capacity of wind and photovoltaic power is increased, the utilization rate of the system’s transmission channel is improved, and the peak-to-valley difference for the residual load of the receiving-end power grid is reduced.

Stock Selection Analysis of Innovative Multifactor Model in New Energy Sector

As of 2024, China’s new energy sector has made significant progress, ranking first in the world in terms of installed photovoltaic (PV) and wind power capacity. The proportion of new energy in the energy mix has increased significantly, driving China’s energy transition and sustainable development. Meanwhile, with the rapid development of Internet technology, quantitative investment strategies based on artificial intelligence technology are expected to show great growth potential in the future financial sector. In this context, this paper will construct a multi-factor model with the help of machine learning, combine value analysis and technical analysis, select candidate factors, develop exclusive factors for the characteristics of the new energy industry, test the validity of the factors, construct a multi-factor stock picking strategy and carry out backtesting analysis. The results demonstrate that the strategy can effectively manage risks and achieve excess returns, which is theoretically and practically instructive for the construction of investment portfolios. The results provide an effective investment strategy reference for financial institutions such as banks, brokerage firms and fund companies.

Creating a renewable energy-powered energy system: Extreme scenarios and novel solutions for large-scale renewable power integration

The large-scale integration of renewable power sources, such as wind and solar, is pivotal in achieving climate change mitigation goals and reducing dependency on fossil fuels within energy systems. This manuscript explores the integration of substantial wind and solar power capacities into Luxembourg's energy framework, addressing challenges like variability, intermittency, and curtailment. It delves into scenarios that include power-to-heat (P2H) and vertical farming (VF) technologies to improve system flexibility and promote the incorporation of renewable energy. Utilising a mixed-integer linear programming (MILP) algorithm, an energy balance model with hourly resolution optimises the system. This algorithm guides the operation of individual plants, ensuring optimal performance based on a variety of criteria. Notable findings underscore the significant influence of an appropriate mix of renewable power resources, indicating a potential increase in renewable power consumption by up to 50% within the system. Furthermore, curtailment management solutions are shown to enhance renewable power integration by as much as 30%, highlighting the importance of strategic, system-wide approaches. Additionally, vertical farming emerges as a promising avenue for significantly augmenting the utilisation of surplus solar power, potentially by up to 100%. While the integration of large-scale renewable power is demonstrably viable, it necessitates a meticulously crafted strategy that considers technological innovations and strategic planning.

Comparative Analysis of Global Onshore and Offshore Wind Energy Characteristics and Potentials

Wind energy, which generates zero emissions, is an environmentally friendly alternative to conventional electricity generation. For this reason, wind energy is a very popular topic, and there are many studies on this subject. Previous studies have often focused on onshore or offshore installations, lacking comprehensive comparisons and often not accounting for technological advancements and their impact on cost and efficiency. This study addresses these gaps by comparing onshore and offshore wind turbines worldwide in terms of installed capacity, levelized cost of electricity (LCOE), total installed cost (TIC), capacity factor (CF), turbine capacity, hub height, and rotor diameter. Results show that onshore wind power capacity constituted 98.49% in 2010, 97.23% in 2015, and 92.9% in 2022 of the world’s total cumulative installed wind power capacity. Offshore wind capacity has increased yearly due to advantages like stronger, more stable winds and easier installation of large turbine components. LCOE for onshore wind farms decreased from 0.1021 USD/kWh in 2010 to 0.0331 USD/kWh in 2021, while offshore LCOE decreased from 0.1879 USD/kWh in 2010 to 0.0752 USD/kWh in 2021. By 2050, wind energy will contribute to 35% of the global electricity production. This study overcomes previous limitations by providing a comprehensive and updated comparison that incorporates recent technological advancements and market trends to better inform future energy policies and investments.

The effect assessment of wind turbine capacity on offshore wind power generation potential in guangdong

Abstract The installed capacity of offshore wind power directly impacts the number of turbines and the total electricity generation. This study uses wind speed and offshore wind power planning data, and Guangdong Province is a case study. Three scenarios are set (7.5 MW, 9.5 MW, and 15 MW) to explore the influence of turbine installed capacity on electricity generation. The results indicate that when the turbine capacity is 9.5 MW, it generates the highest electricity, which accounts for approximately 162718.9 GWh per year.

Wind Turbine Modeling, Maximum Power Point Tracking (MPPT), and Experimental Validation

The research presented is driven by the global increase in wind power capacity and the commitment of the scientific community to facilitate its integration into electrical grids. The focus of this study is the modeling of a wind turbine system, beginning with its mechanical components. To ensure the production of power at optimal levels, a control strategy for Maximum Power Point Tracking (MPPT) based on Optimal Torque (OT) has been adopted. The model and control method, developed in Matlab/Simulink, have demonstrated their precision and efficacy through experimental verification using SCADA data acquired from an operational wind turbine.

Multi-device wind turbine power generation forecasting based on hidden feature embedding

In recent years, the global installed capacity of wind power has grown rapidly. Wind power forecasting, as a key technology in wind turbine systems, has received widespread attention and extensive research. However, existing studies typically focus on the power prediction of individual devices. In the context of multi-turbine scenarios, employing individual models for each device may introduce challenges, encompassing data dilution and a substantial number of model parameters in power generation forecasting tasks. In this paper, a single-model method suitable for multi-device wind power forecasting is proposed. Firstly, this method allocates multi-dimensional random vectors to each device. Then, it utilizes space embedding techniques to iteratively evolve the random vectors into representative vectors corresponding to each device. Finally, the temporal features are concatenated with the corresponding representative vectors and inputted into the model, enabling the single model to accomplish multi-device wind power forecasting task based on device discrimination. Experimental results demonstrate that our method not only solves the data dilution issue and significantly reduces the number of model parameters but also maintains better predictive performance. Future research could focus on using more interpretable space embedding techniques to observe representation vectors of wind turbine equipment and further explore their semantic features.

Hierarchical distributed optimal scheduling decision-making method for district integrated energy system based on analysis target cascade

The district integrated energy system has the characteristics of multi-layer and multi-subjects. Aiming at the problems of data privacy, conflict of interest, and mismatch of interaction power among these multi-subjects, a hierarchical distributed optimal scheduling decision-making method for district integrated energy system based on analysis target cascade is proposed. Firstly, the operational communication architecture of the district integrated energy system based on the cloud-pipe-edge-end is constructed to solve the problems of data transmission, data computation, and data privacy. Secondly, a two-layer distributed scheduling model of district integrated energy system considering waste heat recovery is established based on a laddered carbon trading mechanism. At the upper level, an optimal scheduling model targeting low-carbon and economic performance is developed by considering the participation of district integrated energy system in demand response and the purchase and sale of electricity. At the lower level, an optimal scheduling model considering waste heat recovery for subsystem energy-coupled equipment is developed. Then, the analytical target cascade is used to realize the decoupling of the two-layer model, and the efficient solution is achieved in the process of multiple iterations. Finally, by analyzing the arithmetic examples, it is verified that the proposed method can improve the economy of system operation by 4.38% and the absorption capacity of wind power by 9.89%, while protecting the privacy and interest claims of multiple parties.

Wind turbine end-of-life options based on the UN Sustainable Development Goals (SDGs)

The installed wind power capacity is rapidly growing worldwide, and large volumes of waste materials would need to be treated due to the decommissioning of wind turbine systems in the next years. The purpose of the present work is to evaluate the sustainability performance of decommissioning options for wind turbines and suggest policies to improve the sustainability of the wind turbine end-of-life phase by jointly applying Life Cycle Assessment (LCA) and Data Envelopment Analysis (DEA) methodologies. Unlike most of the relevant literature, which focuses mainly on technical aspects of wind turbine decommissioning, the proposed approach considers all three dimensions of sustainability using Sustainable Development Goals (SDGs) as a guide to identify economic, environmental, and social indicators. The methodology is applied to a representative case study of a wind turbine operating in the Greek territory using real data. Repurposing was found to be the most sustainable end-of-life alternative for composite waste. In contrast, the waste treatment option of the foundation concrete contributes substantially to the sustainability performance of the examined scenario. The sustainability performance of these technologies could be enhanced by the operation of dedicated concrete and composite materials recycling facilities close to wind parks, following cross-sectoral approaches. The results also indicate that the social aspects of the sustainability framework are equally important and should be considered when strategies towards more sustainable waste management of wind turbine systems are designed.

Optimal wind power capacity decision consider commitment contracts under uncertain power supply and electricity demand in China

China has been introducing reforms in the electricity market. Since 2016, electricity retailers are allowed to operate in the market once monopolized by traditional power companies. This regulatory environment demands new types of purchase contracts to remunerate the energy agents and deliver better prices for consumers fairly and sustainably. This paper proposes two new electricity purchase contracts with risk sharing mechanism and studies on wind power supplier's optimal capacity investment problem under supply and demand uncertainty. Firstly, a basic model for fixed demand contract is developed, and the optimal capacity is obtained. Secondly, the fixed commitment order contract and the forecast order contract with risk sharing mechanism are proposed to manage the fluctuation of wind power supply randomness. With backward induction, the optimal investment capacity of wind power supplier is solved, and then the fixed order quantity or forecast demand quantity of the electricity retailer can be obtained. Our results show that the fixed order quantity may have a positive influence on the wind power supplier's capacity investment decision. While, the forecast order quantity may have a negative influence on the wind power supplier's capacity investment decision. In addition, wind density has a strong influence on wind power capacity investment, and it has a positive impact on wind power supplier's profit, but it does not always have a positive impact on electricity retailer's profit. At last, based on numerical analysis, we examine how the wind density distribution coefficient change affect members' profit in the electricity supply chain. We also find that even with wind curtailment punishment, the forecast order contract can make a Pareto improvement on the whole electricity supply chain.

Bias correction of wind power forecasts with SCADA data and continuous learning

Wind energy plays a critical role in the transition towards renewable energy sources. However, the uncertainty and variability of wind can impede its full potential and the necessary growth of wind power capacity. To mitigate these challenges, wind power forecasting methods are employed for applications in power management, electricity trading, or maintenance scheduling. In this work, we present, evaluate, and compare four machine learning-based wind power forecasting models. Our models correct and improve 48-hour forecasts extracted from a numerical weather prediction (NWP) model. The models are evaluated on datasets from a wind park comprising 65 wind turbines. The best improvement in forecasting error and mean bias was achieved by a convolutional neural network, reducing the average NRMSE down to 22%, coupled with a significant reduction in mean bias, compared to a NRMSE of 35% from the strongly biased baseline model using uncorrected NWP forecasts. Our findings further indicate that changes to neural network architectures play a minor role in affecting the forecasting performance, and that future research should rather investigate changes in the model pipeline. Moreover, we introduce a continuous learning strategy, which is shown to achieve the highest forecasting performance improvements when new data is made available.