Live Class Details

Professional Certificate of Competency in Big Data and Analytics in Electricity Grids

Date and Time :  Apr 8, 2021   01:00AM
Time Zone : Azores Standard Time
Duration : 30 minutes
Datacenter Region : Europe (London, United Kingdom)

Energy and utilities are taking advantage of the technology boom! They are turning knowledge into power by using big data & analytics in informing their decision-making and customer journey. This course explores the use of big data & data analytics in electricity grids using applied industry-focused case studies.

Course Details

The 12-week part-time course, led by an industry expert will provide you with a practical, in-depth view of the use of data analytics and machine learning to solve problems in electricity production and distribution.

55% of companies have already adopted Big Data analytics to reduce overall cost and increase profit. With this in mind, this program has been tailored to equip you with the skills and knowledge to stand out from the crowd and harness the power of big data, working at the forefront of a fast-growing, dynamic, and future-proof field.

The course will cover the foundations of data analytics including data acquisition, pre-processing, and visualization. You will learn how to make use of powerful machine learning models such as Artificial Neural Networks and decision trees.

By the end of the program, you will be able to identify problems that could be solved using data analysis and machine learning, and you will be able to develop solutions to such problems.

Course Structure

Module 1: Data analytics and machine learning basics

1. Data analytics
2. Machine Learning and Artificial Intelligence
3. Supervised, Unsupervised, Reinforcement Learning
4. Building and deployment
5. Evaluation of a system

Module 2: Data flow and feature engineering

1. Data sources: sensors, behaviors, social networks, text, images, videos, sounds
2. Data preprocessing
3. Features and feature vectors
4. Data visualization
5. Data mining
6. Big data

Module 3: Mathematical background

1. Statistics and probabilities
2. Derivatives
3. Optimization
4. Similarity estimation
5. Game theory

Module 4: Algorithms (I)

1. K-means algorithm
2. A-priori algorithm
3. Genetic algorithms

Module 5: Algorithms (II)

1. K-Nearest Neighbors
2. Naïve Bayes
3. Decision trees
4. Linear regression

Module 6: Algorithms (III)

1. Feedforward Neural Networks
2. Convolutional Neural Networks
3. Recurrent Neural Networks

Module 7: Applications (I)

1. Dimensionality reduction
2. Finding correlations/correlation analysis
3. Clustering
4. Classification
5. Time series analysis/forecasting
6. Predictions
7. Model Predictive Control

Module 8: Applications (II)

1. Natural language processing
2. Knowledge representation: databases, ontologies, rules, natural language and chatbots

Module 9: Tools (I)

1. Python
2. Pandas, Numpy, Matplotlib
3. Scikit-learn
4. Statsmodel
5. Tensorflow

Module 10: Tools (II)

2. R
5. Cloud-based solutions

Module 11: Case studies (I)

1. SCADA data analytics for Intelligent Alarm processing
2. SCADA data analytics for Predictive maintenance
3. Electricity demand forecasting (short- and long-term)
4. Short-term wind and solar power forecasting
5. Sentiment analysis on social media
6. Data visualization using clustering
7. Statistical Process Control for event/anomaly detection

Module 12: Case studies (II)

1. Fraud detection
2. Online and offline smart metering data analytics
3. Predictive outage management
4. Consumer modeling and segmentation
5. Sensor data for failure/fault predictions
6. Condition monitoring (generators, transformers, converters, breakers)
7. Energy management systems
8. Recommender systems

9. Resilient operation of power grid