Elec2103 Assignment

ELEC2103/ELEC9103 Assignment 2018

Data analytics: Statistics, machine learning and predictive analysis

Modelling, predicting, and verifying the accuracy of models are vital skills in engineering and other fields. This assignment will assess your ability to develop and validate statistical and machine learning models using MATLAB, and in particular, your use of the Statistics and

Machine Learning Toolbox.

Key information

 Due Monday 24 September 2018.

 Worth 15% of your final grade.

 Submission comprises one or more m-files, and must build on the elec2103a.m file provided.

 Submission via Canvas.

 Feedback available until Thursday 20 September 2018 (via the Canvas discussion board).

Background

This assignment asks you to explore and analyse distribution zone substation data collected and published by the power distribution network company Ausgrid, which services the Sydney and Hunter regions of NSW.

Ausgrid operates a network with over 180 zone substations. These substations form the boundary between the sub-transmission network and the distribution (11kV) network. Typically, these are the small substation buildings you might see scattered throughout the suburbs (i.e. not large the high-voltage transmission substations, and also not the green “kiosk” low-voltage distribution transformers seen on streets and in basements of apartment buildings). A zone substation connects between several hundred to a few thousand low-voltage customers, such as homes, small businesses and retail. As such, the data that you will analyse in this assignment is the aggregated loads of many electricity customers.

Ausgrid are required to provide network capacity that serves customer loads with a very high reliability, at minimum cost. As such, they are very interested in predictive analytics, which allow them to forecast growth rates for zone feeder loads and to investigate network augmentation or reconfiguration works to meet future load, or inform their operational strategies for managing peak loads or scheduling maintenance.

1

The assignment task

You are to explore and analyse some or all of the Ausgrid distribution zone substation data files. You are to complete your analysis using MATLAB, and present your analysis as a report contained in a script and other files that can be published to a report in html using MATLAB’s Publish features. You are encouraged to share ideas, but your submitted assignment must be uniquely your own.

The data

The data you will