Portfolio theory applied to solar and wind resources forecast

Lima, Marcello Anderson F. B.; Carvalho, Paulo César Marques de; Carneiro, Tatiane C.; Leite, Josileudo R.; Neto, Luiz José de Bessa; Rodrigues, Géssica K.L.; Melo, Francisco Erivan de Abreu

doi:10.1049/iet-rpg.2017.0006

Cited by 25 publications

(14 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If a solar prediction error happens at the end of the day, between 5 and 6 pm in Fortaleza, the impacts of these errors on the PV electricity generation are lower than errors at 12 am, period with greater solar potential. Aiming to adjust the prediction errors taking into account the solar resource availability, a filter called Impact Factor, according to equations (5) and (6) [6], is applied.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

MLP Back Propagation Artificial Neural Network for Solar Resource Forecasting in Equatorial Areas

Lima¹,

Carvalho²,

Braga³

et al. 2018

REPQJ

Self Cite

View full text Add to dashboard Cite

Renewable energy (RE) resources such as solar are increasingly being used worldwide. Solar resource shows high availability, but presents an intermittent characteristic, causing oscillations in the electricity production. Intermittence is one of the main barriers for the use of solar plants in a system that needs to balance demand and electricity production. Aiming to contribute to a larger use of the solar resource in the world energy matrix, we propose a solar irradiance prediction methodology, developed from data collected in Fortaleza-CE (latitude: −03° 43′, longitude: −38° 32′). Predictions were developed using Multilayer Perceptron (MLP) Back propagation Artificial Neural Network (ANN) with the advance of 1 hour. In the best ANN performance, 41.9% of the predictions obtained up to 5% of error, 58.7% obtained errors lower than 10% and 68.6% obtained errors lower than 15%. MAPE (mean absolute percentage error) of 6.11% was found, which can be considered good, since errors found in previous works reached 20%.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Hence, energy storage and/or sources integration are necessary to supply the demand. Consumption and RE based electricity generation forecasting are also employed [6]. In Germany, those responsible for the electricity generators have to report the planned production one day in advance.…”

Section: Introductionmentioning

confidence: 99%

MLP Back Propagation Artificial Neural Network for Solar Resource Forecasting in Equatorial Areas

Lima¹,

Carvalho²,

Braga³

et al. 2018

REPQJ

Self Cite

View full text Add to dashboard Cite

show abstract

“…The second step uses different NN-based forecast methods to predict the solar radiation based on the Fourier model and the historical data. In [14], portfolio theory has been applied to combined wind and solar sources with different shares. In this model, the obtained average forecast error for wind speed is −1.54% and for solar irradiance is 3.16%, whereas the average forecast error obtained for the integration of 30% solar and 70% wind is −0.13%.…”

Section: State Of the Artmentioning

confidence: 99%

Effective prediction model for Hungarian small‐scale solar power output

Abedinia

Raisz

Amjady

2017

IET Renewable Power Generation

View full text Add to dashboard Cite

Owing to critical role of photovoltaic (PV) power in oncoming energy market, an accurate PV power forecasting model is demanded. In this paper, an effective solar power prediction model composed of variational mode decomposition, informationtheoretic feature selection, and forecasting engine with high learning capability is proposed. The feature selection method is based on information-theoretic criteria and an optimisation algorithm. The forecasting engine is multilayer perceptron neural network equipped with modified Levenberg-Marquardt learning algorithm. An evolutionary algorithm is also incorporated into the training mechanism of the forecasting engine to enhance its learning capability. Effectiveness of the proposed PV prediction model is illustrated on a Hungarian solar power plant.

show abstract

“…Martins et al (2017) investigated project portfolio selection in the electricity industry by employing multicriteria decision-making tools to present a web-based decision support system. Lima et al (2017) applied portfolio theory to attend to the forecast of solar and wind resources. Hummel et al (2017) addressed research and development investment projects by introducing a multicriteria resource allocation modeling method.…”

Section: Introductionmentioning

confidence: 99%

Evaluating large, high-technology project portfolios using a novel interval-valued Pythagorean fuzzy set framework: An automated crane project case study

Mohagheghi

Mousavi

Mojtahedi

et al. 2020

Expert Systems with Applications

View full text Add to dashboard Cite

The contemporary organization relies increasingly on developing large, high technology projects in order to gain local and global competitive advantage. Uncertainty and the complexity of project evaluation requires improved and tailored decision making support systems. A new framework for high technology project portfolio evaluation is introduced. Novel development of an interval-valued Pythagorean fuzzy set (IVPFS) approach is shown to accommodate degrees of membership, non-membership and hesitancy in the evaluation process. Developed methods of linear assignment, IVPFS ranking, IVPFS knowledge index, and IVPFS comparison provide a new framework for group evaluation based on a weighting for each decision expert. The framework is developed as a last aggregation which avoids information loss and introduces a new aggregation process. A novel multi-objective model is then introduced to address project portfolio selection while optimizing the value of the portfolio in terms of resilience (the risk of disruption and delays) and skill utilization (assignment of human resources). The applicability of this framework is demonstrated through a case study in high technology portfolio evaluation. The applied case study shows that the presented framework can be applied as the core to a high technology evaluation decision support system.

show abstract

Portfolio theory applied to solar and wind resources forecast

Cited by 25 publications

References 5 publications

MLP Back Propagation Artificial Neural Network for Solar Resource Forecasting in Equatorial Areas

MLP Back Propagation Artificial Neural Network for Solar Resource Forecasting in Equatorial Areas

Effective prediction model for Hungarian small‐scale solar power output

Evaluating large, high-technology project portfolios using a novel interval-valued Pythagorean fuzzy set framework: An automated crane project case study

Contact Info

Product

Resources

About