Optimisation of behind the meter DER generation assets within network constraints: A roadmap to successful DR program

Optimisation of behind the meter DER generation assets within network constraints: A roadmap to successful DR program

Demand response programs can bring many benefits to various stakeholders in the power industry. Among various participants in demand response programs, the commercial and industrial (C&I) customers can make a profound impact on power networks compared with the residential consumers.

This project aims to solve some of the demand response challenges associated with C&I customers. More specifically, the challenges associated with demand response baseline calculations and back-up generator connections to the distribution grid are investigated in this project.

This project will employ machine learning approaches to investigate and demonstrate its potential to improve demand response baselines, and will also investigate the potential and/or barriers of using back-up generators of the C&I customers in demand response programs. Lastly, the project will explore the role of network tariffs in demand response programs which can incentivise the uptake of batteries.

The expected project outcomes to C&I customers, distribution network service providers (DNSPs) and policymakers include;

• Demonstrate the potential of machine learning approaches for demand response programs;

• Unlocking the value of backup generators of their participation in demand response;

• Identification of technical pathways to enable exporting capabilities from backup generators;

• Demonstrate the potential of participation-based tariff to encourage C&I customers in demand response;

• Feasibility analysis of participating in demand response program through battery installation.

Outcome

The project has uncovered strong correlations between the weather parameters (e.g. temperature) and historical energy demand profiles of some of the C&I customer groups (e.g. shopping centres).  These correlations have assisted to develop enhanced demand response baselines using machine learning techniques, and ultimately they can deliver the best outcomes to both the C&I customers (improved revenue) and network operators (reliability and security). The team has also completed a comprehensive review on backup generator connection requirements stipulated in various, local, national, and international distribution network codes and regulations. This has helped to understand the feasibility and potential costs that would need to be considered by C&I Customers who want to participate in demand response programs by feeding energy back into the network.

Project Partners: RMIT University, AGL, AusNet Services, Monash University, C4NET,