Photovoltaic Energy All-Day and Intra-Day Forecasting Using Node by Node Developed Polynomial Networks Forming PDE Models Based on the L-Transformation

نویسندگان

چکیده

Forecasting Photovoltaic (PV) energy production, based on the last weather and power data only, can obtain acceptable prediction accuracy in short-time horizons. Numerical Weather Prediction (NWP) systems usually produce free forecasts of local cloud amount each 6 h. These are considerably delayed by several hours do not provide sufficient quality. A Differential Polynomial Neural Network (D-PNN) is a recent unconventional soft-computing technique that model complex patterns. D-PNN expands n-variable kth order Partial Equation (PDE) into selected two-variable node PDEs first or second order. Their derivatives easy to convert Laplace transforms substitute using Operator Calculus (OC). proves two-input nodes insert their PDE components its gradually expanded sum model. Its representation allows for variability uncertainty specific patterns surface layer. The proposed all-day single-model intra-day several-step PV schemes compared interpreted with differential stochastic machine learning. statistical models evolved time delay predict output complete day sequences hours. Spatial from larger territory initially recognized daily periods enable compute accurate predictions compensate unexpected pattern variations different initial conditions. optimal samples, determined particular shifts between inputs output, trained Clear Sky Index defined horizon.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Optimal energy management of microgrid in day-ahead and intra-day markets using a copula-based uncertainty modeling method

Recently, economic and environmental problems have created a strong attitude toward utilizing renewable energy sources (RESs). Nevertheless, uncertainty of wind and solar power leads to a more complicated energy management (EM) of RESs in microgrids. This paper models and solves the EM problem of microgrid from the generation point of view. To do this, mathematical formulation of a grid- connec...

متن کامل

Volatility forecasting using threshold heteroskedastic models of the intra-day range

This paper provides an effective approach for forecasting return volatility via threshold heteroskedastic models of the daily asset price range, defined as the difference between the highest and lowest log asset price recorded throughout the day. We propose a general model specification, allowing the intra-day high-low price range to depend nonlinearly on past information, or an exogenous varia...

متن کامل

Forecasting next-day price of electricity in the Spanish energy market using artificial neural networks

In this paper, next-day hourly forecasts are calculated for the energy price in the electricity production market of Spain. The methodology used to achieve these forecasts is based on artificial neural networks, which have been used successfully in recent years in many forecasting applications. The days to be forecast include working days as well as weekends and holidays, due to the fact that e...

متن کامل

Participating of Micro-grids in energy and spinning reserve markets – Intra-day market

Due to uncertain nature of wind and photovoltaic power units, the participation of this units in electricity markets is subjected to significant deviation penalties. This issue leads to despondency or even admission of these units in the competitive environment. With regard to this fact that the low deviations are available when predictions are performed in a short-term horizon and also distrib...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Energies

سال: 2021

ISSN: ['1996-1073']

DOI: https://doi.org/10.3390/en14227581