Demand forecast of PV integrated bioclimatic buildings using ensemble framework

Raza, Muhammad Qamar; Mithulananthan, Nadarajah; Ekanayake, Chandima

doi:10.1016/j.apenergy.2017.08.192

Cited by 40 publications

(19 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such a combination of networks is popularly referred to as fusion or aggregation. The NNE depicts improved prediction results in load demand forecast application in our earlier study [16].…”

Section: Introductionmentioning

confidence: 64%

An Ensemble Framework for Day-Ahead Forecast of PV Output Power in Smart Grids

Raza

Mithulananthan

et al. 2019

IEEE Trans. Ind. Inf.

Self Cite

View full text Add to dashboard Cite

The uncertainty associated with solar photo-voltaic (PV) power output is a big challenge to design, manage and implement effective demand response and management strategies. Therefore, an accurate PV power output forecast is an utmost importance to allow seamless integration and a higher level of penetration. In this research, a neural network ensemble (NNE) scheme is proposed, which is based on particle swarm optimization (PSO) trained feedforward neural network (FNN). Five different FFN structures with varying network complexities are used to achieve the diverse and accurate forecast results. These results are combined using trim aggregation after removing the upper and lower forecast error extremes. Correlated variables namely wavelet transformed historical power output of PV, solar irradiance, wind speed, temperature and humidity are applied as inputs to the multivariate NNE. Clearness index is used to classify days into clear, cloudy and partial cloudy days. Test case studies are designed to predict the solar output for these days selected from all seasons. The performance of the proposed framework is analyzed by applying training data set of different resolution, length and quality from seven solar PV sites of the University of Queensland, Australia. The forecast results demonstrate that the proposed framework improves the forecast accuracy significantly in comparison with individual and benchmark models. Index Terms-PV power output forecasting, solar irradiance, neural network ensemble (NNE), ensemble network (EN), particle swarm optimization, clearness index, cloudy day (CLD), partially cloudy day (PCD) and clear day (CD).

show abstract

Section: Introductionmentioning

confidence: 64%

An Ensemble Framework for Day-Ahead Forecast of PV Output Power in Smart Grids

Raza

Mithulananthan

et al. 2019

IEEE Trans. Ind. Inf.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The data reported from the IEA showed that the total installed production capacity of photovoltaic systems (PV) has grown with an average rate of 49% per year during the last ten years [19], and, similarly, an increment of 12% per year has been registered for solar thermal (ST) plants [20]. Furthermore, the growing interest toward bioclimatic and solar houses is demonstrated by numerous studies on the exploitation of solar irradiation for passive strategies [21][22][23][24][25][26]. The concept of a zero-emission solar house (ZESH) was proposed by Oliveira et al, 2017 [27], who developed the Ekó House ZEB concept, starting from the aforementioned classification proposed by Torcellini et al [8].…”

Section: Towards Ghgs Reduction: Zero-emission Buildingsmentioning

confidence: 99%

Parametric Design to Maximize Solar Irradiation and Minimize the Embodied GHG Emissions for a ZEB in Nordic and Mediterranean Climate Zones

et al. 2020

View full text Add to dashboard Cite

This work presents a validated workflow based on an algorithm developed in Grasshopper to parametrically control the building’s shape, by maximizing the solar irradiation incident on the building envelope and minimizing the embodied emissions. The algorithm is applied to a zero-emission building concept in Nordic and Mediterranean climate zones. The algorithm enables conducting both energy and environmental assessments through Ladybug tools. The emissions embodied in materials and the solar irradiation incident on the building envelope were estimated in the early design stage. A three-steps optimization process through evolutionary solvers, such as Galapagos (one-objective) and Octopus (multi-objective), has been conducted to shape the most environmentally responsive ZEB model in both climates. The results demonstrated the replicability of the algorithm to optimize the solar irradiation by producing an increment of solar incident irradiation equal to 35% in the Mediterranean area, and to 20% in the Nordic climate. This could contribute to compensate the additional 15% of emissions due to the higher quantities of employed materials in the optimized design. The developed approach, which is based on the parametric design principles for ZEBs, represents a support instrument for designers to develop highly efficient energy solutions in the early design stages.

show abstract

“…(1) Statistical methods mainly include time series methods [4], wavelet analysis [5,6], classification regression [7,8], and spectral analysis [9]. These methods use statistical principles to establish a functional relationship between historical power series and future photovoltaic power.…”

Section: Introductionmentioning

confidence: 99%

Short-Term Photovoltaic Power Output Prediction Based on k-Fold Cross-Validation and an Ensemble Model

2019

View full text Add to dashboard Cite

Short-term photovoltaic power forecasting is of great significance for improving the operation of power systems and increasing the penetration of photovoltaic power. To improve the accuracy of short-term photovoltaic power forecasting, an ensemble-model-based short-term photovoltaic power prediction method is proposed. Firstly, the quartile method is used to process raw data, and the Pearson coefficient method is utilized to assess multiple features affecting the short-term photovoltaic power output. Secondly, the structure of the ensemble model is constructed, and a k-fold cross-validation method is used to train the submodels. The prediction results of each submodel are merged. Finally, the validity of the proposed approach is verified using an actual data set from State Power Investment Corporation Limited. The simulation results show that the quartile method can find outliers which contributes to processing the raw data and improving the accuracy of the model. The k-fold cross-validation method can effectively improve the generalization ability of the model, and the ensemble model can achieve higher prediction accuracy than a single model.

show abstract

Demand forecast of PV integrated bioclimatic buildings using ensemble framework

Cited by 40 publications

References 43 publications

An Ensemble Framework for Day-Ahead Forecast of PV Output Power in Smart Grids

An Ensemble Framework for Day-Ahead Forecast of PV Output Power in Smart Grids

Parametric Design to Maximize Solar Irradiation and Minimize the Embodied GHG Emissions for a ZEB in Nordic and Mediterranean Climate Zones

Short-Term Photovoltaic Power Output Prediction Based on k-Fold Cross-Validation and an Ensemble Model

Contact Info

Product

Resources

About