Data-driven Missing Data Imputation for Wind Farms Using Context Encoder

Liao, Wenlong; Bak‐Jensen, Birgitte; Pillai, Jayakrishnan Radhakrishna; Yang, Dechang; Wang, Yusen

doi:10.35833/mpce.2020.000894

Cited by 20 publications

(12 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, the distributions of values refer to the complete and imputed datasets. These have been used by several researchers to evaluate databases (Da Silva et al, 2022; Palharini et al, 2020; Rodrigues, 2019; Rodrigues et al, 2020), including wind speed databases (Afrifa‐Yamoah et al, 2020; Liao et al, 2022; Yozgatligil et al, 2013).…”

Section: Methodsmentioning

confidence: 99%

Evolution of wind speed observed in Brazil between 1961 and 2020

Lima,

Rodrigues,

Santos E Silva

et al. 2024

Intl Journal of Climatology

View full text Add to dashboard Cite

The study's main objective was to analyse daily wind speed data in Brazil collected on‐site from 1961 to 2020 and assess changes in two 30‐year climatological normals, denoted as P1 and P2. Data were sourced from 54 INMET‐managed meteorological stations, with missing data filled using the bootstrap expectation maximization algorithm. Imputation performance was evaluated, and results suggested that the 10% imputed level was most reliable, showing low RMSE values (below 0.5), SD values near 1, and r values exceeding 0.93. This method proved suitable for reconstructing historical wind speed data in Brazil. The analysis included the application of the Mann–Kendall test to detect linear trends and Sen's slope test to quantify trend intensity, both at a 5% significance level. Positive trends during P2 were observed in the Amazon basin and Brazil's semiarid region, while negative trends increased along the coast and in the Southeast region. Average wind speeds during P1 were higher than in P2. Comparing the two climatological normals revealed significant positive trends in some regions during P2, with an increase in average monthly variation of up to 0.85 m·s−1. The average slopes of significant trends were −1 and 1 m·s−1·decade−1 for all periods. The results indicated high wind magnitudes, with maximum power density of 778.08 W·m−2 for the NEB region, 170.90 W·m−2 for the SEB region and 401.67 W·m−2 for the SUB, making these regions promising for future wind power projects. These findings have the potential to enhance the optimization of renewable wind energy generation in Brazil.

show abstract

Section: Methodsmentioning

confidence: 99%

Evolution of wind speed observed in Brazil between 1961 and 2020

Lima,

Rodrigues,

Santos E Silva

et al. 2024

Intl Journal of Climatology

View full text Add to dashboard Cite

show abstract

“…In addition, unforeseen factors such as communication failures, accidental data loss, and regular memory cleaning can render normal operational data unavailable. These factors can result in insufficient or unreliable training data, which will ultimately affect the performance of the estimation model [14]. Addressing these issues is essential in ensuring the accuracy and effectiveness of WT anomaly detection.…”

Section: Nomenclature β γ D I E Mae E N E Rmse F Lossmentioning

confidence: 99%

Data-driven Anomaly Detection Method Based on Similarities of Multiple Wind Turbines

Zeng,

Yang,

Feng

et al. 2024

Journal of Modern Power Systems and Clean Energy

View full text Add to dashboard Cite

The operating conditions of wind turbines (WTs) in the same wind farm (WF) may share similarities due to their shared manufacturing process, control strategy, and operating environment. However, the similarities of WTs are seldom considered in WT anomaly detection, resulting in the disregard of useful information. This paper proposes a method to improve the reliability and accuracy of WT anomaly detection using the supervisory control and data acquisition (SCADA) data of multiple WTs in the same WF. First, a similarity assessment method based on a comparison of different observation time series is proposed, which objectively quantifies the similarities of WT operating conditions. Then, the SCADA data of the target WT and selected WTs that are similar are used to establish several estimation models through a long short-term memory (LSTM) algorithm. LSTM models that exhibit good estimation performance are used to construct a combined estimation model that estimates the variations in the monitored variables of the target WT. Finally, an anomaly detection method that jointly compares the effective value and information entropy of the residuals is proposed to identify anomalies. The effectiveness and accuracy of the proposed method are verified using the data of two actual WFs.

show abstract

“…A Bayesian Gaussian imputation approach was discussed for IoT sensor data (Ahmed et al, 2022). A two-stage deep autoencoder and context encoder techniques were proposed to handle missing values in wind farm data (Liu and Zhang, 2021; Liao et al, 2022). A fine-tuned imputation based on generative adversarial networks was implemented for soft sensor applications (Yao and Zhao, 2022).…”

Section: Introductionmentioning

confidence: 99%

Artificial neural network-based data imputation for handling anomalous energy consumption readings in smart homes

Purna Prakash,

Kumar,

Ravindranath

et al. 2024

Energy Exploration & Exploitation

View full text Add to dashboard Cite

Smart homes are at the forefront of sustainable living, utilizing advanced monitoring systems to optimize energy consumption. However, these systems frequently encounter issues with anomalous data such as missing data, redundant data, and outliers data which can undermine their effectiveness. In this paper, an artificial neural network (ANN)-based approach for data imputation is specifically designed to deal with the anomalies in smart home energy consumption datasets. Our research harnesses the power of ANNs to model intricate patterns within energy consumption data, enabling the accurate imputation of missing values while detecting and rectifying anomalous data. This approach not only enhances the completeness of the data but also augments its overall quality, ensuring more reliable results. To evaluate the effectiveness of our ANN-based imputation method, comprehensive experiments were conducted using real-world smart home energy consumption datasets. Our findings demonstrate that this approach outperforms traditional imputation techniques like mean imputation and median imputation in terms of accuracy. Furthermore, it showcases adaptability to diverse smart home scenarios and datasets, making it a versatile solution for improving data quality. In conclusion, this study introduces an advanced data imputation technique based on ANNs, tailor-made for addressing anomalies in smart home energy consumption data. Beyond merely filling data gaps, this approach elevates the dataset's reliability and completeness, thereby facilitating a more precise analysis of energy consumption and supporting informed decision-making in the context of smart homes and sustainable energy management. Ultimately, the proposed method has the potential to contribute considerably to the ongoing evolution of smart home technologies and energy conservation efforts.

show abstract

Data-driven Missing Data Imputation for Wind Farms Using Context Encoder

Cited by 20 publications

References 30 publications

Evolution of wind speed observed in Brazil between 1961 and 2020

Evolution of wind speed observed in Brazil between 1961 and 2020

Data-driven Anomaly Detection Method Based on Similarities of Multiple Wind Turbines

Artificial neural network-based data imputation for handling anomalous energy consumption readings in smart homes

Contact Info

Product

Resources

About