Sensitive Parameter Analysis for Solar Irradiance Short-Term Forecasting: Application to LoRa-Based Monitoring Technology

Abstract

Due to the relevant penetration of solar PV power plants, an accurate power generation forecasting of these installations is crucial to provide both reliability and stability of current grids. At the same time, PV monitoring requirements are more and more demanded by different agents to provide reliable information regarding performances, efficiencies, and possible predictive maintenance tasks. Under this framework, this paper proposes a methodology to evaluate different LoRa-based PV monitoring architectures and node layouts in terms of short-term solar power generation forecasting. A random forest model is proposed as forecasting method, simplifying the forecasting problem especially when the time series exhibits heteroscedasticity, nonstationarity, and multiple seasonal cycles. This approach provides a sensitive analysis of LoRa parameters in terms of node layout, loss of data, spreading factor and short time intervals to evaluate their influence on PV forecasting accuracy. A case example located in the southeast of Spain is included in the paper to evaluate the proposed analysis. This methodology is applicable to other locations, as well as different LoRa configurations, parameters, and networks structures; providing detailed analysis regarding PV monitoring performances and short-term PV generation forecasting discrepancies.

Democratization of PV Micro-Generation System Monitoring Based on Narrowband-IoT

“…As a main drawback, this solution only allowed a limited number of transmissions, due to the over-air time of works with high spreading factor value (SF11 and SF12) to ensure an accurate reception of data packets with a restricted duty cycle (1%). In addition, a LoRa sensitive analysis was conducted by the authors in [25] for PV short-time forecasting accuracy estimation.…”

Short-Term Solar Irradiance Prediction Based on Adaptive Extreme Learning Machine and Weather Data

“…The connection of the PV panel to the main grid impacts the voltage stability of the system and leads to disturbances [ 9 ]. Therefore, several solutions have been introduced to mitigate the impact of penetrating the main grid [ 10 ], such as a meter data management system [ 11 ], smart transformers [ 12 ], smart inverters [ 13 ], an outage management system [ 14 ], and solar irradiance prediction [ 15 ]. Both grid-tied and off-grid PV systems can be improved if information about the future values of solar irradiance is accurately predicted [ 16 ].…”