An internet of things-based weather system for short-term solar and wind power forecasting using double moving average

Abstract

This article presents the design and implementation of an internet of things (IoT)-based weather forecasting system aimed at optimizing operational planning for renewable energy generation. The system leverages a Raspberry Pi as its central controller, integrating pyranometer and anemometer sensors for real-time data collection and predictive analytics. Utilizing the double moving average method, the system provides accurate short-term forecasts of solar and wind power outputs, which are crucial for addressing the intermittency challenges of renewable energy sources. The integration with the Blynk platform ensures user-friendly data visualization and accessibility. Results from a three-day testing phase reveal the system's high accuracy, with prediction errors of 8.79% for solar power and 16.49% for wind power. These findings underscore the system's potential to enhance energy planning, improve efficiency, and support sustainability goals. By enabling data-driven decision-making, this IoT-based forecasting system offers a scalable solution for advancing renewable energy integration into the power grid.