PhD Project on Data analytics algorithms & learning methodologies

All vacancies of AustraliaEngineeringPhD Project on Data analytics algorithms & learning methodologies

The project will focus on data analytics algorithms and learning methodologies relying on synchrophasors measurement data.

Summary about this job

Electrical/Electronic Engineering

Company: Deakin University, School of Engineering

Location: South West Coast VIC

Work type: Contract/Temp

Salary: n\a

Phone: +61-8-6469-1900

Fax: +61-2-3802-2409

E-mail: n\a

Site:

Detail information about job PhD Project on Data analytics algorithms & learning methodologies. Terms and conditions vacancy

PhD Project on "Data analytics algorithms and learning methodologies relying on synchrophasor measurement data”

The project will focus on data analytics algorithms and learning methodologies relying on synchrophasors measurement data. This will include development, trial and application of big data and machine learning algorithms to research trends, relationships and regression models for collected synchrophasor data, conduct data mining and investigate data quality issues of distribution-level phasor measurement units (PMUs), develop dynamic models for load and distributed energy resources based on the synchrophasor data, and utilise developed load/DER models to investigate trends, hosting capacity and characteristics of Energy Queensland and AusNet MV networks.

NOJA Power along with AusNet Services and Energy Queensland is seeking to develop and deploy its next-generation switchgear technology which will integrate a newly developed phasor measurement unit (PMU) (Intelligent Switchgear) into its existing OSM Automatic Circuit Recloser (ACR) (Project).

The Intelligent Switchgear will be deployed on the Energy Queensland and AusNet networks:

(a)        20 (10 each) at the point of connection of a renewable energy generator in the distribution network, and

(b)        80 (40 each) at the medium voltage side of the distribution network in locations with high penetration of variable renewable resources.

The Intelligent Switchgear and trial deployments will generate significantly more granular power system data than is currently available and will help improve the visibility and modelling of the power system. Data collection, analysis and interpretation of synchrophasor data generated in the deployments (Synchrophasor Measurement Data) will facilitate better-informed system planning and real-time operations for both the Australian Energy Market Operator (AEMO) and distribution network service providers (network operators), which is expected to increase the grid’s hosting capacity of renewable energy generation. It is also expected to facilitate understanding of possible advanced fault-finding protection and islanding schemes for the distribution network.

In this project, Synchrophasor Measurement Data collected from large-scale demonstrations in Energy Queensland and AusNet networks will be provided to researchers at Deakin University to increase renewable energy knowledge and develop innovative solutions for future networks with high levels of renewables. In most cases, the contents of the Synchrophasor Measurement Data will lead the analysis process. As part of the process, PhD students will identify the effectiveness of the existing protection and control algorithms, investigate challenges imposed by renewables to the distribution grid and propose modifications in the algorithms in relation to the identified shortcomings. In addition, data collected from synchrophasors will be used to detect hosting capacity and determine vulnerable areas in the utilities networks.

Selection Criteria:

Applicants should have a strong academic record (equivalent to H1 Honours at Deakin University, which is 80% marks or a cgpa of 3.75 out of 4.00) in Electrical Engineering or Computer Science. Candidates with related Master’s degree is highly encouraged.

Successful candidate must be able to work with a team of supervisors and industry partners and thus need to have good oral and written communication skills

Proposed start date: 29.08.2018

Prospective applicants should, in the first instance, email a CV, and an academic transcript to:

[email protected]

Note: Applicants need to submit admission and scholarship applications formally once they are approved by the supervisory panel. The successful candidates will obtain Tuition-fee and living allowances through Noja Power Switchgear and Deakin University Postgraduate Research Scholarship.

Interested candidates can communicate with the principal supervisor Dr. Shama Naz Islam, Lecturer in Electrical Engineering, Deakin University (email: [email protected]) for further details.

Responds for PhD Project on Data analytics algorithms & learning methodologies on FaceBook

Read all comments for PhD Project on Data analytics algorithms & learning methodologies. Leave a respond PhD Project on Data analytics algorithms & learning methodologies in social networks. PhD Project on Data analytics algorithms & learning methodologies on Facebook, LinkedIn and Google+