Version | 1.1 |

Unit Name | Big Data Analytics in Electricity Grids |

Unit Code | BEE309 |

Unit Duration | 1 Semester |

Award |
Bachelor of Science (Engineering) Duration 3 years |

Year Level | Three |

Unit Creator / Reviewer | Dr Hadi Harb |

Core/Sub-discipline | Sub-discipline |

Pre/Co-requisites | None |

Credit Points |
3 Total Course Credit Points 81 (27 x 3) |

Mode of Delivery | Online or on-campus. |

Unit Workload | (Total student workload including “contact hours” = 10 hours per week) Pre-recordings / Lecture – 1.5 hours Tutorial – 1.5 hours Guided labs / Group work / Assessments – 2 hours Personal Study recommended – 5 hours |

## Unit Description and General Aims

The objective of this unit is to impart to students a detailed knowledge of the use of machine learning and data analytics in different applications related to the electricity grid. The unit provides a mathematical background and a description of the steps required to build and evaluate a machine learning system. Information presented in this unit also includes: an introduction to different algorithms used in machine learning, a description of typical applications, an overview of software tools commonly used in machine learning and different case studies. Students will complete a project covering the design of a machine learning system to solve a realistic problem related to the electricity grid.

## Learning Outcomes

On successful completion of this Unit, students are expected to be able to:

- Explain the need/importance of machine learning and its applications to data analytics in electricity grid.

Bloom's Level 2 - Apply the basic mathematical concepts used in machine learning.

Bloom's Level 3 - Evaluate and compare different machine learning systems according to an application.

Bloom's Level 5 - Apply machine learning algorithms to solve supervised and unsupervised learning problems using a variety of tools.

Bloom's Level 3 - Design machine learning solutions to efficiently manage various electricity grid data.

Bloom's Level 6

## Student Assessment

Assessment Type | When assessed | Weighting (% of total unit marks) | Learning Outcomes Assessed |

Type: Weekly quizzes Topics: Topics 2 to 11 |
Weekly | 10% | All |

Type: Multi-choice test / Extended answer / Short answer questions Students may be required to complete a test with about 10 questions of numerical problems and short answer questions to demonstrate an understanding of the applications of machine learning in electricity grid, building and evaluating a machine learning system, and the algorithms used in machine learning. |
Due after Topic 4 | 20% | 1, 2, 3, 4 |

Type: Short answer questions / Practical Students will complete a test requiring the implementation of solutions to solve specific data analytics problems. |
Due After Topic 8 | 30% | 2, 3, 4, 5 |

Type: Project Students may be required to complete a project where they have to analyze data and design a machine learning solution to a problem in electricity grid. |
Final Week | 35% | All |

Example: Presentation, discussion, group work, exercises, self-assessment/reflection, case study analysis, application. |
Continuous | 5% | - |

**Overall Requirement:** An overall final unit score of 50% or above must be achieved to pass the unit once all assessment has been completed.

## Prescribed and Recommended Readings

#### Required textbook(s)

- Rodolfo Bonnin. (2017). Machine Learning for Developers. Packt Publishing. ISBN: 978-1786469878

Available on Knovel - J. P. Han, H. Jian Tong, Data Mining Concepts and Techniques, 4th Edition. Elsevier, 2023

#### Reference Materials

- References from authentic websites on the Internet:
- Weka Wiki Documentation
- R Introduction Manual
- IEEE Transaction on Smart Grids journals

## Unit Content

#### Topic 1

*Introduction to Data Analytics and Data in Electricity Grids*

- Basics of data analytics
- Machine Learning vs Artificial Intelligence
- Supervised, Unsupervised, Reinforcement Learning
- Types of data in electricity grids: electrical and non-electrical data
- Introduction of data analytics in electricity grids: event analytics, state analytics, customer analytics and operational analytics

#### Topic 2

*Python in Data Analytics*

- Essential libraries of Python for big data analytics: Pandas, Numpy, Matplotlib, Scikit-learn, Statsmodel, Tensorflow
- Examples of using the essential libraries to analyse electricity grids data

#### Topic 3

*Data Flow and Feature Engineering*

- Data sources in electricity grids
- Data preprocessing
- Data visualization
- Features and feature vectors
- Dimensionality reduction
- Data mining
- Application of feature engineering to big datasets in electricity grids

#### Topic 4

*Commonly Used Supervised Learning Algorithms*

- K-Nearest Neighbors
- Decision trees
- Linear regression
- Naïve Bayes
- Implementation of classification algorithms in electricity grids
- Implementation of regression algorithms in electricity grids

#### Topic 5

*Unsupervised Machine Learning and Reinforcement Learning Algorithms*

- Clustering: K-means, DBSCAN, Hierarchal clustering
- Association: Apriori and other algorithms
- Learning models of reinforcement: Markov decision process and Q learning
- Implementation of clustering algorithms using electricity grids data
- Implementation of association rules using electricity grids data
- Example of reinforcement learning in smart grids, e.g., energy trading

#### Topic 6

*Other Algorithms (III)*

- Genetic algorithms and other optimization algorithms
- Artificial Neural Networks:
- Feedforward Neural Networks
- Convolutional Neural Networks
- Recurrent Neural Networks

- Artificial neural networks in electricity demand forecasting

#### Topic 7

*Introduction of other Tools in Data Analytics*

- R
- MATLAB
- WEKA
- Cloud-based Solutions
- Examples of using R and other tools in analyzing electricity grids data

#### Topic 8

*Event Analytics in Smart Grid
s*

- Fault and failure diagnosis
- Fraud detection
- Predictive outage management
- Statistical Process Control for event/anomaly detection

#### Topic 9

*State Analytics in Smart Grids*

- Equipment health and condition monitoring
- System and state identification
- Predictive control
- Stability enhancement
- Asset management

#### Topic 10

*Customer Analytics in Smart Grids*

- Demand response
- Consumer modelling and segmentation
- Customer behavior
- Peer-to-peer energy trading

#### Topic 11

*Operational Analytics in Smart Grids*

- Generation and load forecasting
- Real-time energy management
- Price forecasting
- Economic load dispatch
- Network constraint forecasting & dynamic network operating envelopes
- Risk analysis

#### Topic 12

Unit Review

In the final week, students will have an opportunity to review the contents covered so far. Opportunity will be provided for a review of student work and to clarify any outstanding issues. Instructors/facilitators may choose to cover a specialized topic if applicable to that cohort.

## Software/Hardware Used

#### Software

- WEKA
- R
- MATLAB
- Python

#### Hardware

- N/A