What’s making your customer’s energy bill balloon? Is it their new washing machine? The teenager’s long showers? An air conditioner working overtime?
Thanks to machine learning (ML), deep neural networks (DNNs) and our talented data science team, we’ve now got the power to find out. With Tally Load Disaggregation, we can empower your customers to take control of their energy use and break it down to appliance level.
In the last 15 years, smart meters have revolutionised mass market energy use. Around 75% of US households have smart meters and by 2024, more than 1.2 billion devices are expected to be installed worldwide.
Widespread uptake of in-home meters, coupled with advances in smart meter technology that allow us to collect household consumption data at five-minute intervals, has revolutionised energy insights. Now, with the advent of big data and artificial intelligence (AI) at our fingertips, smart meters are again proving their value to individual customers and energy companies alike.
With increased focus on decarbonisation and smarter energy use, coupled with the current global energy crisis and rising cost of living, load disaggregation is becoming an increasingly vital part of efficiently managing power consumption.
At Tally Group, we’re leveraging our deep understanding of customer needs and our knowledge of innovative methods and technologies to disaggregate residential smart meter data in a way that works for our clients, and their customers.
Tally Group’s data science team has developed cutting-edge AI, machine learning and neural networks to detect appliance consumption. Real-world monitoring, testing and customer feedback have helped us refine the model further.
We’ve used a wide range of deep neural networks (a class of machine-learning methods inspired by the brain’s biological structure) to obtain load disaggregation for residential buildings by training three major components.
The first component is a deep neural network to disaggregate the energy consumption into low-medium consumption appliances such as fridges and washing machines, air-conditioning and entertainment. The second and third components use long-short term memory (LSTM) and convolutional neural networks (CNNs) with residual blocks to obtain loads for electric hot-water systems and timed-loads such as pools or spas, respectively. We’ve used a combination of classifiers and regressors to detect and quantify the related appliances consumptions.
One of the challenges of high through-put deep learning methods is deploying these models commercially in a scalable way. The advent of cloud-based infrastructure like Amazon Web Services (AWS) enables high-performance computing as a service out of the box. This means we’re able to train large-scale deep neural networks, then test and deploy our models in a way that provides scalable implementation. We use AWS to deploy our models in a scalable way that uses multi-batch processing technology to obtain load disaggregation results based on smart meter readings.
Tally Load Disaggregation supplies deep and actionable insights into energy usage. Our easy-to-understand graphs enable your customers to pinpoint the underlying factor for their bills blowing out (right down to appliance or category level) and act on it accordingly. Load disaggregation will allow you to see whether that latest energy-saving appliance buy is living up to its claims. Regular email updates mean they can also compare their recent usage pattern with previous months.
Using Tally Load Disaggregation, your customers can potentially detect faulty or inefficient appliances at their property, then use these insights to decide whether they need to upgrade or repair them. They can even use it to help keep up with the Jones’, since load disaggregation can supply insights that show customers how their appliances’ energy use compares to other households in their area.
If there’s ready access to meter usage data in your energy market, Tally Load Disaggregation can be up and running within weeks. It integrates with our Tally Trust product to supply granular usage data by the hour, day and week. Independent research proves our usage insights feature can reduce churn by a third*. In a world that can feel out of control, it’s good to know there’s something you’ve got the power to change.
