Machine Learning for Energy Distribution

9 use cases for energy distribution companies

Distributed production, the rise of renewables, the move to a smarter grid and competitive marketing is changing the energy distribution market and putting pressure on the profit margins of utilities. 

There is an increased need to make smarter decisions on a scale. And these decisions need to be made fast to remain competitive. Machine learning is becoming the most important tool to help you make better decisions around pricing and create better relationships with your customers. With machine learning, you can: 

  • Predict prices and demand,
  • Optimize retail prices,
  • Make better offers, win more customers, reduce churn and predict customer lifetime value,
  • Predict the merit order and optimize consumption

Accurately Predict Energy Prices

As personal power generation (using solar or wind power) gets easier and cheaper, consumers and businesses are increasingly producing their own power. 

Personal power generation allows people to make, consume, and store their own energy. Depending on where they live, they may even be able to sell surplus power back to the local power utility. 

Machine learning can help find the best time to produce, store, or sell this energy. Ideally, energy should be consumed or stored when prices are low and sold back to the grid when prices are high.

When we use machine learning models to look at historical data, usage trends, and weather forecasts, we can make much more accurate predictions on an hourly basis. This helps people with personal and business energy generation systems make strategic decisions about what to do with their energy. 

For example, Adaptive Neural Fuzzy Inference System (ANFIS) has been used to predict short-term wind patterns for power generation. This allows producers to maximize energy production, and sell it back to the grid when prices are at their peak.

Accurately Predict Energy Demand 

Accurately predicting customers’ energy needs is critical for any utility provider. To date, there is no adequate solution for bulk energy storage, which means energy needs to be transmitted and consumed almost as soon as it’s produced. 

We're using machine learning to increase the accuracy of these predictions. Historical energy use data, weather forecasts, and the types of businesses or buildings operating on a given day all play a role in determining how much energy is used. 

For example, a hot summer day mid-week means more energy usage because office buildings run air conditioning at a high capacity. Weather forecasts and historical data can help identify those patterns in time to prevent rolling blackouts caused by air conditioners in the summer. 

Machine learning finds complicated patterns in the various influencing factors (such as day of the week, time, predicted wind and solar radiation, major sports events, past demand, mean demand, air temperature, moisture and pressure, and wind direction) to explain developments in demand. Because machine learning finds more intricate patterns than humans can, its predictions are more accurate. This means you can increase efficiency and decrease costs when you buy energy – without having to make expensive adjustments.

Optimize Prices Through Better Trading

Providing the best prices for a commodity like electricity is key to surviving in an open energy market. When consumers can choose who provides their electricity, price comparison is inevitable. 

To stay competitive, utility providers use machine learning to determine the best times to buy energy, based on when the price is lowest.

When it comes to commodity tracing, there are thousands of factors that affect energy prices  – everything from the time of day to the weather. We can use machine learning to analyze tiny changes in these factors, which helps utility providers make more informed decisions about when to buy and sell energy. 

But we can go further, for one of our clients we combined gradient boosting, general additive and deep learning models to more accurately predict day-ahead prices. We also used machine learning to help a B2B energy distributor pick trading strategies to buy futures cheaper.

In some markets, this kind of analysis has led to multiple price reductions for consumers in a single year.

Reduce Customer Churn

In open energy markets, where customers have a choice of utility providers, understanding which customers are going to churn out can be critical. In the energy sector, churn rates – the percentage of customers who stop using a service in a given year – can be as high as 25%. Accurately predicting and preventing churn is essential to survival. 

We can use machine learning to help utility owners anticipate when a customer is getting ready to churn out. 

By using techniques such as Cross-Industry Standard Process for Data Mining (CRISP-DM), AdaBoost, and Support Vector Machines, as well as historical usage data, utility providers can identify key indicators that predict whether a customer is going to churn. 

These include things like customer satisfaction, employment status, energy consumption, home ownership, or rental status. A change in any of these factors can point to a customer who’s getting ready to terminate their service. 

When we identify these indicators far enough in advance, you can prevent churn by working with customers to solve any problems they’re experiencing.

Predict Customer Lifetime Value

In an open utilities market, utility owners and providers have to pay more attention to metrics like customer lifetime value (CLV). This helps them understand how much any given customer is going to spend over the term of their contract.

Machine learning can do more than just giving you a more accurate CLV prediction. By inputting data like customer information, consumption habits, location, purchase history, and payment behavior, we can use machine learning models like deep neural networks to predict the overall value of an individual customer. 

With machine learning, we can even take this one step further by suggesting ways to increase customer value. This could mean making highly-targeted offers to similar customers, or leveraging natural language processing (NLP) to help improve service for frustrated customers who might be ready to churn.

Predict the Probability of Winning a Customer

For utility providers in open markets, having a complete picture of potential customers is critical to staying ahead of the competition. 

But machine learning can do more than offer you this complete picture. It can also provide the information you need to make data-driven marketing decisions.. This means that when a person lands on your website, you’ll be able to figure out whether that person will become a customer. 

We can use machine learning to gather the information that person brings with them – things like where they live, what kind of computer they’re using, their browsing history, search history, and how many times they’ve been to your website – and come up with an accurate picture of that person as a consumer. 

From there, not only can machine learning determine the likelihood of that person becoming a customer (this is known as scoring), it can also determine the best strategy for turning them into a customer. This involves using highly targeted advertising and delivering a very personalized experience – for example, using a picture of a family of four on the homepage when someone from a family of four visits the site.

Make Highly Targeted Offers to Customers

In open energy markets, consumers have a choice of utility providers. Personalized offers are essential to enticing new customers and keeping existing ones, especially since brand loyalty isn’t as strong as it used to be. 

We can use machine learning to help you gain the insight you need to make irresistible offers that speak directly to a specific customer’s needs. 

By analyzing spending habits and customer data, machine learning can help you determine the best kind of offer to make to a certain customer at any given time. 

For example, if the data indicates that a customer is getting ready to move, you could send out an offer waiving the connection fee at their new location. This kind of personalized offer puts you ahead of the competition and makes the customer less likely to churn.

Optimize Energy Consumption 

People have long been conscious of energy consumption, both at home and at work. But without doing a lot of manual calculations, we've only ever been able to get an overall sense of energy use, without knowing which appliances or devices use the most. 

Smart meters and the rise of Internet of Things devices have changed all that. Non-intrusive appliance load monitoring (NIALM), also known as disaggregation, is an algorithm that uses machine learning to analyze energy consumption at the device-specific level. 

We can help you figure out which appliances cost the most to operate. This will help both home and business customers fine-tune their consumption habits to save money and reduce energy use. They can either use high-cost appliances less often or replace them with more energy-efficient models. 

Predict Merit Order of Energy Prices

Utility providers have a lot of options when it comes to sourcing where they get their energy – everything from renewables like wind and solar to fossil fuel and nuclear. When it comes time to sell power, these different sources are organized into a merit order based on price. This determines the order in which power from these various sources is sold. 

Because we have access to data from a wide variety of sources, we can use machine learning to analyze both real-time data and historical data. Machine learning algorithms are also better at taking into account all the different factors that influence the price –things like weather, demand, how much energy is available from the various sources, historical usage, etc.– to predict an optimized merit order.

This helps you make more informed decisions about where you’re getting your power. This is especially helpful in markets where there is a lot of renewable energy, such as wind, because it's hard to guarantee energy availability from these sources.

Energy Transmission

Anticipating and Preventing Power Grid Failure

Massive power outages cause chaos for the general public, and they cost utility providers roughly $49 billion a year.

This wouldn’t be much of a problem if massive power outages were rare, but outages affecting more than 50,000 people have increased dramatically in recent years. This means utility companies need to find new ways of anticipating and managing these outages.

These days, smart grids are producing massive amounts of data, which means predicting and managing outages is easier than ever. Unlike traditional power grids, which are one-directional (meaning they only transmit power in one direction), smart grids are two-directional. They can capture data from every possible source in the grid at the same time as they’re providing electricity. They collect and monitor data from sources like smart meters, IoT devices, and power generation stations, providing a clear, real-time look at power usage.

Machine learning can use this data to anticipate and prevent massive power outages in the grid. Machine learning helps identify non-obvious patterns in the data that can be a precursor to grid failure, which helps maintenance teams preempt failure.

Balancing the Grid

Balancing the grid — making sure energy supply matches energy demand — is one of the most important jobs a transmission operator has. But renewable energy sources depend heavily on the weather, making them harder to predict.

Transmission operators spend millions each year fixing planning mistakes that lead to producing too much or too little power. In hybrid systems — which rely on both renewable energy sources and fossil fuels to generate electricity — these mistakes have to be corrected at the last minute by buying more energy or compensating power plants for the excess.

Machine learning is the most accurate method available to forecast the output of renewable energy. Advanced methods, like Long Short-Term Neural Networks (LSTMs), can weigh the many factors involved — wind, temperature, sunlight, and humidity forecasts — and make the best predictions. This saves money for operators and preserves resources for power plants.

Preventing Blackouts and Brownouts With Real-time Monitoring and AI Prediction

Power grids have a lot of obstacles to overcome in providing continuous energy to customers. Weather patterns, usage, internal failure, even wildcard incidents like lightning strikes and interference from wild animals can all affect power delivery.

Machine learning is increasingly being used to help predict potential brownout and blackout conditions. By feeding historical data into the AI and running Monte Carlo simulations to predict potential outcomes, grid operators can use machine learning to identify conditions that could lead to grid failure. And they can act accordingly.

Sensors like phase measurement units (PMU) and smart meters can provide usage information in real-time. When combined with both historical and simulation data, AI can help mitigate potential grid failure, using techniques like grid balancing and demand response optimization. Incidents that would otherwise have affected millions of people can be contained to a smaller area and fixed faster for less money.

Differentiate Power System Disturbances from Cyber Attacks

Cyber attacks are increasingly used to target important infrastructure, like shutting down hospitals with Ransomware attacks (when attackers break into the system and lock legitimate users out until a ransom is paid). With utility grids, a cyber attack can have widespread consequences and affect millions of users.

Detecting these attacks is critical.

Developers are using machine learning to differentiate between a fault (a short-circuit, for example) or a disturbance (such as line maintenance) in the grid and an intelligent cyber attack (like a data injection).

Since deception is a huge component of these attacks, the model needs to be trained to look for suspicious activity – things like malicious code or bots – that get left behind after the deception has occurred.

One such method uses feature extraction with Symbolic Dynamic Filtering (an information theory-based pattern recognition tool) to discover causal interactions between the subsystems, without overburdening computer systems. In testing, it accurately detected 99% of cyber attacks, with a true-positive rate of 98% and a false-positive rate of less than 2%. This low false-positive rate is significant because false alarms are one of the biggest concerns in detecting cyber attacks.

Balance Supply and Demand

Utility providers are looking for ways to better predict power usage while maintaining maintaining energy supply at all times. This becomes critical when renewable power sources (like solar or wind) are introduced into the grid.

Because these renewable power sources rely on elements beyond human control (like the weather), utility providers know they can’t always rely on renewables for continuous production. Knowing precisely when demand levels will peak allows utility providers to connect to secondary power sources (like conventionally generated electricity) to bolster the available resources and ensure constant service provision.

More and more utility providers are turning to machine learning for help. We can feed historical data into machine learning algorithms -- like Support Vector Machines (SVM) -- to accurately forecast energy usage and ensure sufficient levels and constant supply.

Detect Power Grid Faults

Current methods for detecting faults in the grid consume a lot of unnecessary time and resources. This creates a situation where power transmission is interrupted and customers are without electricity while faults are first located, then fixed.  

Machine learning can find faults quickly and more accurately helping you minimize service interruption for your customers.. Support Vector Machines (SVM) are combined with Discrete Wavelet Transformation (DWT) to locate faults in the lines using a traveling wave-based location method.

When we apply  DWT (a form of numerical and functional analysis that captures both frequency and location information) to the transient voltage recorded on the transmission line, we can determine the location of the fault by calculating aerial and ground mode voltage wavelets. So far, this method has detected fault inception angles, fault locations, loading levels, and non-linear high-impedance faults for both aerial and underground transmission lines.

Detect Non-Technical Power Grid Losses

In the energy world, “non-technical losses” means energy theft or fraud from the system.

There are two common types of non-technical losses. The first is when a customer uses more energy than the meter reports. The second involves rogue connections stealing energy from paying customers. To pull off this theft or fraud, bad actors can bypass smart meters completely or insert chips into the system that change how meters track energy use. Meter readers can also be bribed to report lower numbers (though thanks to smart meters, this is increasingly hard to do).

Because these non-technical losses cost $96 billion annually, utility providers are turning to machine learning to combat the problem.

We can help utility providers mine historical customer data to discover irregularities that indicate theft or fraud. These can be things like unusual spikes in usage, differences between reported and actual usage, and even evidence of equipment tampering.

Energy Distribution

Better Predict Energy Demand

Accurately predicting customers’ energy needs is critical for any utility provider. To date, we haven’t found an adequate solution for bulk energy storage, which means energy needs to be transmitted and consumed almost as soon as it’s produced.

We're using machine learning to increase the accuracy of these predictions. Historical energy use data, weather forecasts, and the types of businesses or buildings operating on a given day all play a role in determining how much energy is used.

For example, a hot summer day mid-week means more energy usage because office buildings run air conditioning at a high capacity. Weather forecasts and historical data can help identify those patterns in time to prevent rolling blackouts caused by air conditioners in the summer.

Machine Learning finds complicated patterns in the various influencing factors (such as day, time, predicted wind and solar radiation, major sports events, past demand, mean demand, air temperature, moisture and pressure, wind direction, day of the week, etc.) to explain the development of demand. Because machine learning finds more intricate patterns, its predictions are more accurate. This means energy distributors can increase efficiency and decrease costs when they buy energy – without having to make expensive adjustments.

Energy Generation

Predict Turbine Malfunction

Wind is a great renewable energy source, but wind turbine maintenance is notoriously expensive. It accounts for up to 25% of the cost per kWh. And fixing problems after they occur can be even more expensive.

Machine learning can help you get ahead of this problem. The goal is to reduce maintenance costs by catching problems before the turbine malfunctions. This is particularly important when wind farms are located in hard-to-access places, such as the middle of the ocean, which makes repair costs even higher.

Real-time data gathered with Supervisory Control and Data Acquisition (SCADA) can help identify possible malfunctions in the system far enough in advance to prevent failure.

For example, data from sensors found within the turbines – such as oil, grease, and vibration sensors – have been used to train machine learning models to identify precursors to failure, such as low levels of lubricant.

This method can train machine learning models to predict failures up to 60 days in advance.

Consumption / Retail

Accurately Predict Energy Prices

As personal power generation (using solar or wind power) gets easier and cheaper, consumers and businesses are increasingly producing their own power.

Personal power generation allows people to make, consume, and store their own energy. Depending on where they live, they may even be able to sell surplus power back to the local power utility.

Machine learning can help find the best time to produce, store, or sell this energy. Ideally, energy should be consumed or stored when prices are low and sold back to the grid when prices are high.

By looking at historical data, usage trends, and weather forecasts, machine learning models have made accurate predictions on an hourly basis. People with personal and business energy generation systems can use these predictions to make strategic decisions about whether to use, store, or sell their energy.

For example, Adaptive Neural Fuzzy Inference System (ANFIS) has been used to predict short-term wind patterns for wind power generation. This allows producers to maximize energy production and sell it when energy prices are at their peak.

Reduce Customer Churn

In open energy markets, where customers have a choice of utility providers, understanding which customers are going to churn out can be critical. Churn rates, which is the percentage of customers who stop using your service in a year, can be as high as 25%. Being able to predict churn and stay ahead of it is essential to survival.

Machine learning is helping utility owners predict when a customer is getting ready to churn out. By using techniques such as Cross-industry Standard Process for Data Mining (CRISP-DM), AdaBoost, and Support Vector Machines, as well as historical usage data, utility providers can identify key indicators of whether or not a customer is going to churn. These indicators include things like customer satisfaction, employment status, energy consumption, home ownership or rental status. A change in any of these can indicate a customer is getting ready to terminate their service.

When these indicators are identified far enough in advance, it’s possible to avoid churn by working with customers to solve any problems they’re experiencing.

Energy Trading

Predict Energy Prices

Just like natural gas and oil, wholesale energy is a market commodity. So naturally it's important for traders to be aware of market fluctuations and pricing when it comes to buying and selling energy.

To help make sense of the massive amounts of data used to make trading decisions, traders are increasingly turning to machine learning.

A mix of statistical analysis and machine learning can help commodity traders make better predictions. Classical statistical analysis techniques like time series analysis, Seasonal Autoregressive Integrated Moving Average (SARIMA), and regression models are used to deal with the data. And machine learning makes connections between the various data points.

What’s more, machine learning trains itself to make increasingly accurate predictions using the constant flow of real-time data.

Get Notified of New Articles

Leave your email to get our weekly newsletter.

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.