ABSTRACT
The need for accurate solar power forecasting is critical for grid stability as solar energy becomes more prevalent. This paper presents a new framework called Cloud-based Analysis and Integration for Data Efficiency (CAIDE) for real-time monitoring and forecasting of solar irradiance in sensor farms. CAIDE can handle multiple sensor farms, enhance predictive models in real-time, and is built on Model Based Systems Engineering (MBSE) and Internet of Things (IoT) technologies. It can correct its forecasts, ensuring they stay current, and operates on various architectures, ensuring scalability. Tested on multiple sensor farms, CAIDE proved to be scalable and improved the initial accuracy of solar power production forecasts in real-time. This framework is significant for solar plant deployment and the advancement of renewable energy.
Disclosure statement
No potential conflict of interest was reported by the authors.
Abbreviation
ANN | = | Artificial Neural Network. |
API | = | Application Programming Interface. |
CAIDE | = | Cloud-based Analysis and Integration for Data Efficiency. |
Conv-LSTM | = | Convolutional LSTM. |
DEVS | = | Discrete Event System Specification. |
DL | = | Deep Learning. |
DNN | = | Deep Neural Network. |
EU | = | European Union. |
GCP | = | Google Cloud Platform. |
GHI | = | Global Horizontal Irradiance. |
GPU | = | Graphics Processing Unit. |
GUI | = | Graphical User Interface. |
IoT | = | Internet of Things. |
IP | = | Internet Protocol. |
LSTM | = | Long Short-Term Memory. |
M&S | = | Modeling and Simulation. |
MAE | = | Mean Absolute Error. |
MAPE | = | Mean Absolute Percentage Error. |
MBSE | = | Model Based Systems Engineering. |
MIDC | = | Measurement and Instrumentation Data Center. |
ML | = | Machine Learning. |
MSE | = | Mean Squared Error. |
NFF | = | Non-Functional Feature. |
NWP | = | Numerical Weather Prediction. |
PV | = | Photovoltaic. |
PVGIS | = | PhotoVoltaic Geographical Information System. |