Next-Gen Photovoltaic Forecasting: Leveraging Machine Learning for Energy Optimization

Introduction:

Solar energy, being both sustainable and abundant, plays a crucial role in the global transition towards renewable energy sources. However, its variable nature poses significant challenges for its integration into energy systems. Accurate solar forecasting is essential to enhance the reliability and efficiency of solar power, thus facilitating better energy management and grid stability.

Project Overview:

This PhD project aims to develop next-generation solar forecasting techniques by harnessing the capabilities of artificial intelligence (AI), machine learning (ML), and Internet of Things (IoT) technologies. The project will focus on creating innovative predictive models that not only forecast solar output more accurately but also provide real-time adaptability to changing weather conditions and solar irradiance.

Objectives:

Develop Enhanced Predictive Models: Utilize ML algorithms to improve the accuracy of solar irradiance and power output forecasts. This involves training models on historical data, real-time data from IoT sensors, and satellite imagery.

Integration of IoT in Solar Forecasting: Deploy IoT sensors across solar farms to collect high-resolution, real-time data on environmental conditions and panel performance. This data will be used to refine forecasting models continuously.

Probabilistic Forecasting Approaches: Move beyond deterministic forecasts to probabilistic models that provide a range of possible outcomes, enhancing decision-making processes for grid operators and energy managers.

Impact Analysis on Grid Management: Evaluate how improved forecasting affects energy storage, load management, and overall grid stability. Develop strategies to optimize these areas using predictive data.

Research Impact:

The anticipated advancements from this project will significantly impact solar energy management, facilitating smoother integration of renewable sources into the energy grid. This research will provide valuable insights into the scalability of renewable energy, promote sustainable practices, and support policy development for future energy infrastructure.

This project will be based at the UoY.

Entry Requirements:

The potential candidate must hold a previous degree and have experience in Electrical, Electronics, or Communications Engineering, Computer Science, or a related field. Candidates with practical experience in AI or machine learning are particularly encouraged to apply.

How to Apply:

Applicants should apply via the University’s online application system at https://www.york.ac.uk/study/postgraduate-research/apply/. Please read the application guidance first so that you understand the various steps in the application process.

This project is open-ended making it suitable for MSc by Research and PhD level.