eCite Digital Repository

Day ahead load forecasting for the modern distribution network - a Tasmanian case study


Jurasovic, M and Franklin, E and Negnevitsky, M and Scott, P, Day ahead load forecasting for the modern distribution network - a Tasmanian case study, Proceedings of The Australasian Universities Power Engineering Conference (AUPEC 2018), 27-30 November 2018, Auckland, New Zeeland, pp. 1-6. (2018) [Refereed Conference Paper]

PDF (Day Ahead Load Forecasting)

Copyright Statement

Copyright 2018 IEEE

Official URL: 10.1109/AUPEC.2018.8758023


Penetration of distributed energy resources in distribution networks is predicted to increase dramatically in the next seven years, bringing with it the opportunity for utilities to have a greater presence at low levels of the network. To achieve this effectively, utilities will require accurate short term load forecasts. This paper presents a novel neural network-based load forecasting system that applies recent advances in neural attention mechanisms. The forecasting system is trained and assessed on ten years of historical half-hourly load, weather, and calendar data to produce a 24-hour horizon half-hourly online forecast. When forecasting during anomalous peak holiday periods on a feeder that has a typical load of less than 1000kVA the forecasting system achieves a MAPE of 7.4% and a mean error of -15kVA. The forecasting system is implemented in a residential battery trial and is able to successfully forecast major peaks with sufficient lead time and accuracy to enable the fleet of batteries to charge ahead of time and provide network support

Item Details

Item Type:Refereed Conference Paper
Keywords:load forecasting, machine learning, DER
Research Division:Engineering
Research Group:Electrical engineering
Research Field:Electrical energy generation (incl. renewables, excl. photovoltaics)
Objective Division:Energy
Objective Group:Renewable energy
Objective Field:Renewable energy not elsewhere classified
UTAS Author:Jurasovic, M (Mr Michael Jurasovic)
UTAS Author:Franklin, E (Associate Professor Evan Franklin)
UTAS Author:Negnevitsky, M (Professor Michael Negnevitsky)
ID Code:130794
Year Published:2018
Deposited By:Engineering
Deposited On:2019-02-12
Last Modified:2019-10-23
Downloads:33 View Download Statistics

Repository Staff Only: item control page