The project will develop algorithms for a customer-focussed software solution that interprets energy supply and demand at the system level (focussing on residential, but applicable also to small commercial). Interpreting the complex relationship between cost, supply and load along with accurate data and analytics will enable end users to proactively manage demand. The algorithms will take local load, weather and energy generation inputs and automate the analysis of the electricity production and consumption.
You are here
RP1023: Forecasting and home energy analysis in residential energy management solutions
Publications related to this project
This presentation investigates the value of using forecast variables from multiple vertical layers of NWP as machine learning inputs in improving the accuracy of solar irradiance forecasts.
This paper reviews the most recent methods and techniques for using smart meter data such as forecasting, clustering, classification and optimisation.
Australian rooftop solar is now at a crossroads – but it’s all positive. New technologies mean big data can be gathered from systems so that performance can be monitored and alerts raised if problems occur.
This paper analyses the impacts of household electricity load consumption profile and PV size on PV self-consumption.
Inspired by the advancements in larger scale load forecasting, this paper proposes a novel forecast method for individual household electricity loads.
In this paper, models which predominantly use smart meter data alongside with weather variables, or smart meter based models (SMBM), are implemented to forecast individual household loads. Well-known machine learning models such as artificial neural networks (ANN), support vector machines (SVM)...
Student Poster – Participants Annual Forum 2015 – Baran Yildiz
Residential and small commercial electricity load forecasting