Meet the team | Furqan Tahir

Welcome to another edition of our 'Meet the Team' interview series! This time, we're thrilled to introduce you to a key player in the Voltaware family. While our cutting-edge technology often grabs the headlines, it's the dedicated and talented individuals behind the scenes who are the real heroes of our success. In this edition, we shine a spotlight on Furqan Tahir, our Head of Smart Meter Insights, who is at the forefront of transforming energy data into meaningful insights.

Meet Furqan Tahir, the mastermind behind Voltaware’s innovative Smart Meter Insights. As our Head of Smart Meter Insights, Furqan blends the precision of data science with the art of AI/ML, creating a symphony of energy disaggregation that turns your home’s energy data into actionable insights. When he’s not fine-tuning AI models or synchronizing with his team across time zones, Furqan can be found hiking up a trail, perfecting his tennis serve, or cycling through scenic routes. Get ready to dive into the fascinating world of smart meters, AI, and a dash of lasagna love, as we uncover what makes Furqan tick both inside and outside the office.

Could you describe your role as the Head of Smart Meter Insights at Voltaware? What does your typical day look like?

As the Head of Smart Meter Insights, I lead a team of Data Scientists, Analysts and Backend Engineers to develop AI/ML based solutions for energy disaggregation and personalised actionable insights using only the home’s smart meter consumption data.

My typical day starts with a review of the product’s Jira board. This involves creating and updating various epics/cards for the team to work on and ensure that the product’s development activities remain aligned with the company’s business priorities. I would then have the daily standup meeting with the Data Science Team, where each member provides a quick overview of what they are currently working on, whether they face any blockers or require help with any particular task.

I usually dedicate some morning time to have in-depth technical discussions with relevant Team members on implementing new product features as well as enhancing/maintaining the library. In addition to this, I also make it a point to set aside at least a couple of hours each day for core library development work. This typically involves tasks related to training and testing AI/ML disaggregation models for new appliances as well as refining some of the existing appliance models etc.

In the afternoon, I have a catchup with the Backend engineers, who are mostly based in Brazil, to align on the technical requirements for any new product features, deployment activities as well as exposing new insights on the API for our customers.

To cap off the day, there are often calls with new/existing customers to update them on the project activities, discuss disaggregation results and insights as well as provide updates on the product roadmap features.

You’ve been with Voltaware for over three years. What has been your most rewarding project involving energy data insights, and what impact did it have on the company’s goals?

I started working on the Smart Meter disaggregation project a couple of years ago. This involved developing a library that leverages the power of AI/ML to accurately detect appliance signatures within the smart meter energy data. Whilst this project has been challenging due to the low resolution of the smart meter data, however, we now have a product that can accurately estimate the consumption of most major appliances found within homes. Furthermore, we have developed an AI/ML based module to infer each home’s appliance list (thereby eliminating the need to have this information availablefrom the customer). This means that we only require the home’s smart meter data to generate an accurate bill breakdown each week and provide personalised actionable insights to the customers. This has enabled Voltaware to offer energy disaggregation and personalised insights to a wide spectrum of clients.

How do you balance the need for detailed energy usage insights with privacy concerns for end-users? What measures does Voltaware implement to ensure data security and privacy?

We have purposefully designed the Smart Meter Product in a way that it only requires the home’s load curve and not much else. For example, we often find that customer home’s metadata (appliance list), whilst very useful, is often hard to obtain. Therefore, as mentioned above, we rely only on the smart meter energy data to infer the homes appliance list and provide energy disaggregation and personalised insights. Any data that we receive from our clients is anonymised and we fully comply with the GDPR regulations to protect the privacy and personal data of individuals

Artificial Intelligence (AI) is becoming increasingly important in data analytics. How do you see AI transforming the energy sector, and what role does it play in Voltaware’s work with energy data?

AI technology looks set to revolutionise the energy sector: smart homes are becoming smarter; consumers are increasingly using AI to make intelligent energy choices; and we are even seeing the use of deep learning based real-time models for demand side management. Voltaware is at the cutting edge of this AI revolution within the energy sector. As mentioned above, we leverage the power of AI/ML to accurately detect appliance signatures, and provide personalised insights which help customers reduce their energy costs as well as their carbon footprint.

How do you stay updated with the latest advancements in data science?

Data Science is rapidly advancing and it is important to stay up-to-date with the latest developments. To this end, I attend webinars/talks from leading experts in the field as well as enroll in relevant online courses (where possible).

Outside of work, what are some of your hobbies or interests?

I enjoy playing tennis, hiking and cycling.

Last one is a “lightning round”

1. Favourite color
• Blue
2. Favourite food
• Lasagna
3. Favourite season
• Spring
4. Tea or coffee?
• Tea
5. Python or Java?
• Python
6. Introvert or extrovert?
• Extrovert
7. Gym or sofa?
• Gym
8. The Big Bang Theory or Friends?
• The Big Bang Theory