Predicting rare events of solar power production with the analog ensemble

The Charanka Solar Park, one of the world’s largest multi-developer and multi-beneficiary solar parks, is the hub of solar power production in India. It contributes about 6 per cent to the total solar power production in the country. Although solar power is more expensive than the traditional power in the country, its sheen is still not high to make it a potential source to eliminate energy crisis not just in India but all across the world. Researchers are continuously pushing their envelope to explore as to why solar energy should be adopted over traditional energy sources irrespective of the fact that it is more expensive. The war between its financial and strategic viability is going on. Efforts are being made in the direction of reducing its costs and making it as a financially viable and strategically active option. This case is an attempt in the same direction. We are using Charanka Solar Park as a base to explore if there is any future for such projects in the country. There are projects which are no doubt operational but their long-term viability is truly questionable.

Download Full-text

Balancing future variable wind and solar power production in Central-West Europe with Norwegian hydropower

Energy ◽

10.1016/j.energy.2018.11.068 ◽

2019 ◽

Vol 168 ◽

pp. 870-882 ◽

Cited By ~ 9

Author(s):

I. Graabak ◽

M. Korpås ◽

S. Jaehnert ◽

M. Belsnes

Keyword(s):

Solar Power ◽

Power Production ◽

Variable Wind

Download Full-text

Intra-hour forecasts of solar power production using measurements from a network of irradiance sensors

Solar Energy ◽

10.1016/j.solener.2013.08.002 ◽

2013 ◽

Vol 97 ◽

pp. 58-66 ◽

Cited By ~ 93

Author(s):

Vincent P.A. Lonij ◽

Adria E. Brooks ◽

Alexander D. Cronin ◽

Michael Leuthold ◽

Kevin Koch

Keyword(s):

Solar Power ◽

Power Production

Download Full-text

Controlling Volatility of Wind-Solar Power In Germany

10.21203/rs.3.rs-1142831/v1 ◽

2021 ◽

Author(s):

Hans Lustfeld

Keyword(s):

Electric Power ◽

Wind Turbines ◽

Solar Power ◽

Electric Energy ◽

Power Production ◽

Solar Panels ◽

Smart Meters ◽

Electric Energy Consumption ◽

Process Heating ◽

One Year

Abstract The main advantage of wind-solar power is the electric power production free of CO2. Its main disadvantage is the huge volatility of the system [national electric energy consumption powered by wind-solar power]. In fact, if this power production, averaged over one year, corresponds to the averaged electric consumption and is intended to replace all other electric power generating devices, then controlling the volatility of this system by using storage alone requires huge capacities of about 30TWh, capacities not available in Germany. However, based on German power data over the last six years (2015 till 2020) we show that the required storage capacity is decisively reduced, provided i) a surplus of wind-solar power is supplied, ii) smart meters are installed, iii) a different kind of wind turbines and solar panels is partially used, iv) a novel function describing this volatile system, is introduced. The new function, in turn, depends on three characteristic numbers, which means, that the volatility of this system is characterized by those numbers. When applying our schemes the results suggest that all the present electric energy in Germany can be obtained from controlled wind-solar power. And our results indicate that controlled wind-solar power can produce the energy for transportation, warm water, space heating and in part for process heating, requirering an increase of the electric energy production by a factor of 5. Then, however, a huge number of wind turbines and solar panels is required changing the appearance of German landscapes fundamentally.

Download Full-text

Short-Term Forecasting of Photovoltaic Solar Power Production Using Variational Auto-Encoder Driven Deep Learning Approach

Applied Sciences ◽

10.3390/app10238400 ◽

2020 ◽

Vol 10 (23) ◽

pp. 8400 ◽

Cited By ~ 1

Author(s):

Abdelkader Dairi ◽

Fouzi Harrou ◽

Ying Sun ◽

Sofiane Khadraoui

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Solar Power ◽

Power Production ◽

Superior Performance ◽

Support Vector ◽

Learning Models ◽

Short Term ◽

Learning Methods ◽

Short Term Forecasting

The accurate modeling and forecasting of the power output of photovoltaic (PV) systems are critical to efficiently managing their integration in smart grids, delivery, and storage. This paper intends to provide efficient short-term forecasting of solar power production using Variational AutoEncoder (VAE) model. Adopting the VAE-driven deep learning model is expected to improve forecasting accuracy because of its suitable performance in time-series modeling and flexible nonlinear approximation. Both single- and multi-step-ahead forecasts are investigated in this work. Data from two grid-connected plants (a 243 kW parking lot canopy array in the US and a 9 MW PV system in Algeria) are employed to show the investigated deep learning models’ performance. Specifically, the forecasting outputs of the proposed VAE-based forecasting method have been compared with seven deep learning methods, namely recurrent neural network, Long short-term memory (LSTM), Bidirectional LSTM, Convolutional LSTM network, Gated recurrent units, stacked autoencoder, and restricted Boltzmann machine, and two commonly used machine learning methods, namely logistic regression and support vector regression. The results of this investigation demonstrate the satisfying performance of deep learning techniques to forecast solar power and point out that the VAE consistently performed better than the other methods. Also, results confirmed the superior performance of deep learning models compared to the two considered baseline machine learning models.

Download Full-text

TIME SERIES MODEL APPLIED TO PREDICT THE SOLAR POWER PRODUCTION

18th International Multidisciplinary Scientific GeoConference SGEM2018, Energy and Clean Technologies ◽

10.5593/sgem2018/4.1/s17.098 ◽

2018 ◽

Author(s):

Irina Meghea

Keyword(s):

Time Series ◽

Solar Power ◽

Power Production ◽

Time Series Model

Download Full-text

Economic Implications of Agricultural Land Conversion to Solar Power Production

Energies ◽

10.3390/en14196063 ◽

2021 ◽

Vol 14 (19) ◽

pp. 6063

Author(s):

Yanay Farja ◽

Mariusz Maciejczak

Keyword(s):

Social Welfare ◽

Agricultural Land ◽

Solar Power ◽

Power Production ◽

Production Costs ◽

Maximization Problem ◽

Land Uses ◽

Economic Implications ◽

The Social ◽

Ghg Reduction

Meeting greenhouse gas (GHG) reduction targets will require a significant increase in electricity production from sustainable and renewable sources such as solar energy. Farmers have recognized this need as a chance to increase the profitability of their farms by allocating farmland to solar power production. However, the shift from agriculture to power production has many tradeoffs, arising primarily from alternative land uses and other means of production. This paper models the farmers’ decision as a constrained profit maximization problem, subject to the amount of land owned by the farmers, who have to allocate it between agriculture and solar power fields, while considering factors affecting production costs. The farmers’ problem is nested in the social welfare maximization problem, which includes additional factors such as ecological and aesthetical values of the competing land uses. Empirical analysis using data from a solar field operating in Israel shows that landowners will choose to have solar power production on their land unless agricultural production generates an unusually high net income. Adding the values of non-market services provided by agricultural land does not change this result. The consideration of the reduction in GHG emissions further increases the social welfare from solar fields.

Download Full-text