Forecasting techniques for renewable energy sources: Performance analysis and economic impact on grid operation
The recent movement of Victoria on subsidising photovoltaic (PV) power installations on the household level is about to introduce highly intermittent and uncertain generation in the distribution system. The unpredictable nature of the high penetration of PV power may rapidly deteriorate both the reliability and economic performance of power systems. This project focuses on developing statistical learning methods appropriate for forecasting PV generation. Existing PV power data with spatial and temporal correlation will be utilised to understand the underlying statistical properties of PV generation. Using these properties, short-term time-series forecasting tools will be developed in order to provide useful forecasts and uncertainty measures. The resulted high-performance forecasting methods along with the knowledge of basic household load profiles will allow for a more accurate quantification of active power reserve requirements necessitated by the future PV-rich distribution systems. This will be achieved by analysing the impact of the uncertainty on reserve requirements given the technical constraints and control capabilities of a distribution network. This forecasting approach is a key step towards the development of a data-driven decision-making framework for power system operation.
- Dr. Maria Vrakopoulou, Lecturer, Electrical and Electronic Engineering
- Prof. Howard Bondell, Arc Future Fellow, Mathematics and Statistics
How to apply
Applicants must apply to MEI via email with the subject 'Application for the MEI Internship Program'. Prospective interns must submit a cover letter that:
- identifies at most 3 of the listed projects, ranked from highest to lowest preference;
- explains why these projects are of interest; and
- explains why potential PhD study after the internship is of interest.
This letter must be accompanied by a CV and copies of all Bachelors and/or Masters transcripts, supplied as one .pdf document.
Applications open on Friday 31 July and close on Friday 25 September.