A deep neural network approach for behind-the-meter residential PV size, tilt and azimuth estimation

Mason, Karl; Reno, Matthew J.; Blakely, Logan; Vejdan, Sadegh; Grijalva, Santiago

doi:10.1016/j.solener.2019.11.100

Cited by 48 publications

(28 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An additional limitation of these methods is that the rough location of the distributed generator is assumed to be known. However, [13], [14], [28] could be used in tandem with this method to first estimate the location of an un- known distributed generator, and then the algorithms proposed in this paper could be applied to a constrained set of candidate injection locations to estimate the power factor of the DER. Another potential solution to this problem would be statistical methods such as best subset selection [17] or other regularization methods such as the LASSO method presented in this paper.…”

Section: Discussionmentioning

confidence: 99%

Power Factor Estimation of Distributed Energy Resources Using Voltage Magnitude Measurements

Talkington

Grijalva

Reno

2021

Journal of Modern Power Systems and Clean Energy

Self Cite

View full text Add to dashboard Cite

This paper presents a new method for the estimation of the injection state and power factor of distributed energy resources (DERs) using voltage magnitude measurements only. A physics-based linear model is used to develop estimation heuristics for net injections of real and reactive power at a set of buses under study, allowing a distribution engineer to form a robust estimate for the operating state and the power factor of the DER at those buses. The method demonstrates and exploits a mathematical distinction between the voltage sensitivity signatures of real and reactive power injections for a fixed power system model. Case studies on various test feeders for a model of the distribution circuit and statistical analyses are presented to demonstrate the validity of the estimation method. The results of this paper can be used to improve the limited information about inverter parameters and operating state during renewable planning, which helps mitigate the uncertainty inherent in their integration.

show abstract

Section: Discussionmentioning

confidence: 99%

Power Factor Estimation of Distributed Energy Resources Using Voltage Magnitude Measurements

Talkington

Grijalva

Reno

2021

Journal of Modern Power Systems and Clean Energy

Self Cite

View full text Add to dashboard Cite

show abstract

“…The hidden dense layers can be stacked to effectively learn features embedded within the data. The DNN architecture has been widely used in speech recognition [25], energy [26], and medical imaging [27].…”

Section: Prediction Of Capacitor's Accelerated Ageing Based On Advancmentioning

confidence: 99%

Prediction of Capacitor’s Accelerated Aging Based on Advanced Measurements and Deep Neural Network Techniques

Liu

Claeys

Pissoort

et al. 2020

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Capacitors are widely used in electronic systems and have a key function in EMC (electromagnetic compatibility) compliance. However, the ageing of capacitors results in an alteration of their parameters, which could pose a threat on the normal operation of systems as well as their EMC compliance. Normally, accelerated ageing is employed to shorten the experiment time. After the ageing, the capacitance and equivalent series resistance (ESR) are measured to evaluate the ageing process. In this paper, a new continuous characterization measurement setup is implemented in which the accelerated ageing of the capacitors under test (CUTs) is continuously monitored during the overall accelerated ageing process. It significantly improves the continuity of the measurement and eliminates the errors attributed to the interrupting of the ageing process. This method is validated by comparing measurement results from the new measurement method with results of the conventional method. This was done by subjecting two types of film capacitors to thermal and electrical stress in order to evaluate the accelerated ageing effects. Furthermore, a conditional deep neural network with dropout technique is proposed to predict the accelerated ageing conditions of the capacitors. Instead of only forecasting the failure threshold, the proposed network is able to dynamically predict the accelerated ageing conditions at different elevated temperatures and voltages. This leads to a serious reduction of the total measurement time: from 1000h to 200h.

show abstract

“…Additionally, Mason et al [19] propose a deep neural network (DNN) approach to estimate the PV size, tilt, and azimuth angles. The method is compared with linear regression optimization.…”

Section: Machine Learning and Optimization In The Pv Modelling Domainmentioning

confidence: 99%

“…Although slightly overestimated, both subplots show a good agreement between the results of the three data set lengths and the reported value, with a higher deviation in the months with fewer clear-sky-like periods, particularly when all-sky conditions are considered. Benchmark publications [17][18][19] have reported a deviation of between 4 • and 5 • for the azimuth angle parametrization. In this work, we show a mean deviation of less than 3 • with a training data set of 90 days with only clear-sky-like periods.…”

Section: Pv System Parametrizationmentioning

confidence: 99%

A Genetic Algorithm Approach as a Self-Learning and Optimization Tool for PV Power Simulation and Digital Twinning

et al. 2020

View full text Add to dashboard Cite

A key aspect for achieving a high-accuracy Photovoltaic (PV) power simulation, and reliable digital twins, is a detailed description of the PV system itself. However, such information is not always accurate, complete, or even available. This work presents a novel approach to learn features of unknown PV systems or subsystems using genetic algorithm optimization. Based on measured PV power, this approach learns and optimizes seven PV system parameters: nominal power, tilt and azimuth angles, albedo, irradiance and temperature dependency, and the ratio of nominal module to nominal inverter power (DC/AC ratio). By optimizing these parameters, we create a digital twin that accurately reflects the actual properties and behaviors of the unknown PV systems or subsystems. To develop this approach, on-site measured power, ambient temperature, and satellite-derived irradiance of a PV system located in south-west Germany are used. The approach proposed here achieves a mean bias error of about 10% for nominal power, 3° for azimuth and tilt angles, between 0.01%/C and 0.09%/C for temperature coefficient, and now-casts with an accuracy of around 6%. In summary, we present a new solution to parametrize and simulate PV systems accurately with limited or no previous knowledge of their properties and features.

show abstract

A deep neural network approach for behind-the-meter residential PV size, tilt and azimuth estimation

Cited by 48 publications

References 25 publications

Power Factor Estimation of Distributed Energy Resources Using Voltage Magnitude Measurements

Power Factor Estimation of Distributed Energy Resources Using Voltage Magnitude Measurements

Prediction of Capacitor’s Accelerated Aging Based on Advanced Measurements and Deep Neural Network Techniques

A Genetic Algorithm Approach as a Self-Learning and Optimization Tool for PV Power Simulation and Digital Twinning

Contact Info

Product

Resources

About