The course (available in Classroom) teaches how to develop a profit-maximizing arbitrage strategy for energy storage using mathematical optimization (Linear and Mixed-Integer programming) in Python. Full Python code available to download and fully explained in the video (1 hour and 15 minutes). No prerequisites (beginner-friendly). Energy storage can make money through various ways, one of which is energy storage trading (arbitrage). See the attached figure summarising the energy storage arbitrage strategy. The algorithms and strategies taught in this course are the industry standard for the following roles: - Quantitative Analysts (Quants) in energy firms - Energy Traders - Data Scientists (Energy) - Asset Managers Where is this code used? This specific type of optimization (Arbitrage & Dispatch) is used in firms across the energy and financial sectors: - Hedge Funds & Prop Trading - Investment Banks - Commodity Trading Houses - Energy Majors & Tech Energy Storage : - Utilities (e.g., Duke Energy, NextEra, Enel) own batteries (energy storage) to help stabilise the electricity grid. - Independent Power Producers (IPPs) (e.g., Vistra, AES, Neoen) are companies that build and own power plants (solar, wind, batteries) specifically to sell electricity for profit. They are very active users of arbitrage strategies. - Investment Funds (e.g., Gresham House, Gore Street Capital) are specialized funds that buy batteries as financial assets, similar to how a real estate fund buys apartment buildings to collect rent. - Hedge funds (like Citadel, D.E. Shaw, or Millennium) thrive on volatility. In energy markets, prices can jump from $20 to $2,000 in minutes.

A new online course is ready, with its full Python code available to download and explained. It is in the Classroom --> 1.37. It is called "1.37. Download Electricity Market Data Via API". You will learn to build, in Python, a tool that asks the user for a date range and specific electricity generation units , and downloads the data instantly, and saves it in a multi-sheet Excel workbook. All the code is in Python and fully available for you to download. You can integrate it in your project easily. For example if you have a Machine Learning (or optimisation) model, you can integrate this code in this model. So with this code you will pull real-time data, and then pass them as inputs to your model. Or this can be used as part of an Algorithmic Trading model. By automating the retrieval of real-time signals like System Prices and grid actions, you provide the raw fuel your AI needs to train, backtest strategies, and predict market movements. This is the Client- Server software architecture. Our Python code is the "client" who asks for data. And the 'Server' is the computer (remote) where we connect and request electricity data to download. We connect to the server of the company "Elexon", which is in Great Britain. Think of the electricity grid in Great Britain as a marketplace. Elexon is the independent referee. Elexon doesn't generate electricity, and they don't sell it to your house. Their job is to make sure the "books balance" at the end of the day. If a power plant promised to generate 100MW but only generated 90MW, Elexon is the one who calculates the penalty. The "Server" we connect to is their public library of everything that happened on the grid: who generated what, when, and how much it cost. You can find more about Elexon on their website at : https://www.elexon.co.uk You can view electricity data on their portal which is called "Insights Solution" and it is at https://bmrs.elexon.co.uk .

I’ve just published a new online course about Memory-Efficient Processing of Big Data. This course teaches real-world skills as they are used in practice. Smart meters measure the electricity-consumption data every hour, and store the information in CSV files. These files eventually become very large (big data). The new online course is called "Smart Meter Big Data Efficient Processing" and it is in the Classroom in 1.36. This online course teaches a Python methodology that is used by energy companies in practice to read extremely large datasets (Big Data). Without this technique such files cannot be read because they cause a memory (RAM) error. Companies that sell electricity to consumers are known as 'Retailers' or 'Suppliers'. Such companies have CSV files with hundreds of millions of rows, where each row is the hourly kWh electricity consumption. If they try to load these CSV files, their computers will run out of RAM and crash. So these companies process these files using Python iterators, which enable a memory-efficient and fast processing method. In this course, I show you the industry-standard solution: using Python Iterators to process Big Data in "chunks". See the attached image; this is analysed in detail in the course.

Course practice 1.35 This course, with its Python exercise, allows you to visualise 10 years of global trends and developments in clean energy production by major region (Africa, China, Europe, etc.). 1/ World 2/ Africa The improvements are clear to see!

Since linear and logistic regression are supervised models and are frequently used for exploratory analysis in data mining, would it be accurate to say that the distinction between data mining and machine learning is primarily methodological (discovery vs prediction) rather than algorithmic? Please feel free to share any experiences choosing to use data mining for Energy or any other industry.