How ThingsCloud Is Using Machine Learning & IoT To Solve Power Crisis In India

Anusheel Nahar (left) and Amruth Puttappa, Co-Founders, ThingsCloud **Image is for representation purpose only**

Currently, India lacks nearly 80,000 million units of electricity per year. Availability of energy is one of the important factors that propel the prosperity and growth of the nation. A lot of houses are compelled to buy inverters because of this power consumption issue. To solve this issue, and to make the inverters smart, Indian startup ThingsCloud is leveraging IoT, machine learning and cloud computing to develop next-gen intelligent energy systems. 

The Journey

Based out of Bangalore, ThingsCloud was started in 2015 by Amruth Puttappa and Anusheel Nahar. Born and brought up in a small town in Karnataka, Puttappa did his under graduation in Electronics from NIT Surat, after which he went to the US to do his Masters at the University of Texas at Austin. During that time he worked in Analog Devices, which works in the area of signal processing, followed by a startup called Energy Xtreme which made a large scale battery management for the grid for the wind turbine. From his experiences here, he learnt how startups grow. After he returned to India he worked with another startup called NevSemi Inc which were into making solar charge controllers and ADC controllers. 


Sign up for your weekly dose of what's up in emerging technology.

Nahar has done his BTech in Computer Science from IIT Kanpur and went to the University of Wisconsin-Madison to do his Masters. Both the founders hit it off. When they questioned the customers about the problems that they faced in terms of power cutoff, they realised that major power cutoff problems are not even addressed in India. This is when they started getting base ideas for ThingsCloud. 

Tech Used At ThingsCloud

In the Indian tech inverter market, there are two types of power conversations for the solar: 

  1. Grid-Tie inverters: These are the inverters in which whatever power one generates, he has to fill it to the grid. This is what large power producers do.
  2. Off-grid inverters: In this type, one gets to know whenever there is a power cut. This is also dominated by the UPS inverter and used when there is a power cut of short duration like 1 or 2 hours.

The problem with these two types is that in category one if there is a power cut, the potential energy generation will be lost because there is no power safety. The second one, if one does not use enough power that is generated, he cannot feed it back to the grid. It is a very significant problem and most customers do not feel that they are losing power. Moreover, they don’t even know that they are not able to generate it because they think that it is the max that they can generate. This is something that the startup wanted to tackle. When they were interacting with the customers they understood that it has to be something else. That is when they started coming up to say hybrid smart inverter. 

The startups also leverage AI and ML. Give all the data to the could and over time it starts understanding you. 

The startup deploys these technologies to make the systems work: 

  • Power consumption
  • IoT
  • AI and ML

They already have one patent awarded. They are expecting to start getting more patents in the upcoming years. 

Use of AI and ML:

  1. The inverter understands that the power production has dropped, sends the notification to the user using sensors
  2. Preventive maintenance where there is an analysis done to see what is the likelihood of the system and it initiates the service centres to send out the unit so that you don’t have to worry about getting stranded 
  3. It forecasts the energy generation it ensured that you have enough backup when there is a power cut

Skill-set required for each technology: 

1.Power consumption – Embedded C

2.IoT – partly hardware and partly software. Hardware: Embedded C, Cloud: nodejs

3.AIML – Python and R

Views On India’s IoT Progress

According to Puttappa, when they started ThingsCloud, the connectivity was very poor across India. He said, “Since Jio entered the market, the connectivity has been fantastic.” Some of the solutions that we were talking in 2015 it would have been almost impossible but today it is possible because there is enough connectivity, he added. One of the reasons why IoT and cloud management did not take off earlier is because the connectivity was not good. The other challenge is related to hardware.

More Great AIM Stories

Disha Misal
Found a way to Data Science and AI though her fascination for Technology. Likes to read, watch football and has an enourmous amount affection for Astrophysics.

Our Upcoming Events

Masterclass, Virtual
How to achieve real-time AI inference on your CPU
7th Jul

Conference, in-person (Bangalore)
Cypher 2022
21-23rd Sep

Conference, Virtual
Deep Learning DevCon 2022
29th Oct

3 Ways to Join our Community

Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

Telegram Channel

Discover special offers, top stories, upcoming events, and more.

Subscribe to our newsletter

Get the latest updates from AIM