Forecasting volatility of wind power production

Shen, Zhenjiang; Ritter, Matthias

doi:10.1016/j.apenergy.2016.05.071

Cited by 60 publications

(33 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, from the perspective of control variables, capital held by major shareholders (Orecta) is negatively correlated with the over-investment and underinvestment of the company. This means that when the majority shareholder has more funds, the compensation contract based on its own interests lacks sufficient compensation effect and incentive effect for the management and give of the management layer, which easily leads to the opportunistic behavior of the operator, leading to unreasonable investment in enterprises, especially the management's excessive investment; in model (2) and 3, the estimated coefficient of Ownership Concentration (Qwc) is negative, which is significant at 10% level. When the degree of equity concentration increases, the interests of major shareholders and the maximization of the enterprise value gradually converge, which is beneficial to improve the investment efficiency of the enterprise to some extent; the estimation coefficient of the listed years (Age) of the enterprise is relatively small.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Exploration of Volatility and Market Risk of Stock Return Rate in Listed Financial Enterprises Based on Fair Value Measurement

Xue¹

2019

Proceedings of the 2nd International Conference on Economy, Management and Entrepreneurship (ICOEME 2019)

View full text Add to dashboard Cite

The measurement attribute of fair value has been proved to improve the transparency of financial statement information. However, there are few guidelines on fair value measurement in accounting standards, so it is difficult to meet the need of fair value measurement in practical application. Taking the listed companies from 2009 to 2015 as samples, Richardson model is adopted as the tool to calculate the investment efficiency, from the perspective of fair value hierarchy, whether the stratified measurement of fair value can improve the investment level in the Chinese market environment is investigated theoretically and tested empirically. The study shows that the net asset information measured at the first level of fair value is reliable, which is beneficial to improve the quality of accounting information, reduce the information asymmetry and agency cost between contracting parties, and improve the investment efficiency of the company; the net asset information measured at the second level of fair value has a promoting effect on the investment efficiency, indicating that even though the net asset information content measured at this level is lower than that measured at the first level, many reliable and relevant information is still disclosed; due to the lack of accurate and fixed valuation technology, net asset information measured at the third layer of fair value is susceptible to manipulation and triggers opportunistic behavior. However, the number of items measured at this level is small, resulting in less information disclosed, and the overall effect on investment behavior is small.

show abstract

Section: Discussionmentioning

confidence: 99%

“…However, the improvement of "reputation premium" doesn't mean the improvement of audit quality. The higher the profit and loss of changes in the fair value per share of listed companies, the lower the audit quality [2].…”

Section: Literature Reviewmentioning

confidence: 99%

Exploration of Volatility and Market Risk of Stock Return Rate in Listed Financial Enterprises Based on Fair Value Measurement

Xue¹

2019

Proceedings of the 2nd International Conference on Economy, Management and Entrepreneurship (ICOEME 2019)

View full text Add to dashboard Cite

show abstract

“…Recently, Cadenas et al [24] compared the predictive capacity of a univariate ARIMA model for wind speed against a nonlinear autoregressive exogenous model (NARX) model using as input the wind direction, temperature, pressure, solar radiation, relative humidity and speed of the wind. The main assumption of the statistical methods is that these assume a family of underlying stochastic processes that are generally stationary, linear and homoscedastic, but most of the time series analyzed do not comply with these restrictions, since they have characteristics of heteroscedasticity and present long-term dependencies [7,8].…”

Section: Methodsmentioning

confidence: 99%

Wind Power Forecasting Based on Echo State Networks and Long Short-Term Memory

et al. 2018

View full text Add to dashboard Cite

Wind power generation has presented an important development around the world. However, its integration into electrical systems presents numerous challenges due to the variable nature of the wind. Therefore, to maintain an economical and reliable electricity supply, it is necessary to accurately predict wind generation. The Wind Power Prediction Tool (WPPT) has been proposed to solve this task using the power curve associated with a wind farm. Recurrent Neural Networks (RNNs) model complex non-linear relationships without requiring explicit mathematical expressions that relate the variables involved. In particular, two types of RNN, Long Short-Term Memory (LSTM) and Echo State Network (ESN), have shown good results in time series forecasting. In this work, we present an LSTM+ESN architecture that combines the characteristics of both networks. An architecture similar to an ESN is proposed, but using LSTM blocks as units in the hidden layer. The training process of this network has two key stages: (i) the hidden layer is trained with a descending gradient method online using one epoch; (ii) the output layer is adjusted with a regularized regression. In particular, the case is proposed where Step (i) is used as a target for the input signal, in order to extract characteristics automatically as the autoencoder approach; and in the second stage (ii), a quantile regression is used in order to obtain a robust estimate of the expected target. The experimental results show that LSTM+ESN using the autoencoder and quantile regression outperforms the WPPT model in all global metrics used.

show abstract

“…Apart from the numerous benefits of renewable energy sources (RES), there are some disadvantages of utilizing those technologies. Relatively high capital investment costs (Ellabban et al 2014), low predictability (Rahbar et al 2015, Shen & Ritter 2016 and power generation intermittency (Turkenburg et al 2000) are commonly raised issues. Wind is volatile in its nature and its almost zero marginal costs must be offset by the fact that the intermittent generators produce power whenever they can, additionally increasing high variability of this type of power (Fogelberg & Lazarczyk 2017).…”

Section: Introductionmentioning

confidence: 99%

Study of wind power utilization in district heating systems in the Westfjords, Iceland

Mathews

Sowiżdżał

2019

geol

View full text Add to dashboard Cite

Some Renewable Energy Sources (RES), such as wind power, are often regarded as intermittent. That means they are not available on demand, but rather depend on external conditions e.g. such as the weather. In order to manage these resources, it is advised to combine them with energy storage or other energy sectors, what is known as "sector coupling". This approach is set to mitigate the negative impact of unstable renewable energy sources and manage the generated surpluses. In this study, a system combining wind turbines, district heating network and short-term thermal energy storage was proposed and examined for the instance of the Westfjords, Iceland. Ísafjörður, Patreksfjörður, Bolungarvík and Flateyri are the exemplary communities with existing district heating networks, chosen to investigate the implementation of the system. A short review of the current state of the energy sector in Iceland was provided to present the local conditions. Wind potential in the described area was estimated as high in comparison with average wind turbine generation in the European Union and a few instances of wind turbines placement were analyzed in this study. For locations close to the district heating network, a long-term correlation between power generation and usage was proven. However, locating wind turbines in places with better wind conditions, provides stable output and a similar amount of energy produced by fewer generators.

show abstract

Forecasting volatility of wind power production

Cited by 60 publications

References 60 publications

Exploration of Volatility and Market Risk of Stock Return Rate in Listed Financial Enterprises Based on Fair Value Measurement

Exploration of Volatility and Market Risk of Stock Return Rate in Listed Financial Enterprises Based on Fair Value Measurement

Wind Power Forecasting Based on Echo State Networks and Long Short-Term Memory

Study of wind power utilization in district heating systems in the Westfjords, Iceland

Contact Info

Product

Resources

About