Energy, Learning, and Optimization
This tutorial walks through an example of how to implement ADMM on a blockchain, and complements my Devcon3 talk. Github repository is here
Goal: Use a smart contract to coordinate decentralized optimization¶
This can model federated machine learning or federated optimization problems
We will use the Alternating Direction Method of Multipliers, » Read More
As blockchains extend beyond financial transactions there has been a strong interest in the energy space- my research specialty, and the focus of my most recent paper on blockchains for securing decentralized energy markets.
Having watched other changes in the energy sector, » Read More
Since winning the Correlation One / Citadel datathon in February, I’ve been fascinated by data science jobs in the Finance sector, and the idea of applying my strategic bidding research to equity markets where trading volumes are greater, physical constraints are looser, » Read More
Great news- our proposal for a decentralized blockchain-based energy scheduling system won 2nd place in the Wanxiang Global Blockchain Challenge, the first step to getting our research out of the ivory tower and into industry!
Our proposal outlines an approach to creating the energy network which will power Wanxiang’s 90,000-person smart city (a 5-year, » Read More
I just got back from the First IEEE Conference on Control Technology and Applications, which replaces the previous Multi-conference on Systems and Control.
First, having a conference in Hawaii is fantastic: morning snorkeling missions before the conference started, » Read More
Our blockchain/microgrid research might become a reality: working with the Blockchain@Berkeley team, we’ve submitted a proposal to the Wanxiang Global Blockchain Challenge, an international competition for blockchain infrastructure ideas. If all goes well, this research might turn into the actual metering and scheduling system for a city that is being planned in China. » Read More
Ethereum makes it easy to run simple computations on blockchains while keeping the value of decentralized networks– but real applications will need access to off-blockchain resources, whether for heavy computations or pulling data from the internet. This tutorial walks through how to deploy a smart contract on a private test blockchain and use Python to read data from the blockchain or send data to the blockchain. » Read More
Support vector machines are the canonical example of the close ties between convex optimization and machine learning. Trained on a set of labeled data (i.e. this is a supervised learning algorithm) they are algorithmically simple and can scale well to large numbers of features or data samples, » Read More
Slick algorithms and whiz-bang math are nice to have, but sometimes nothing speaks as well as a hardware demo. And for energy nerds, this means flashing lights. Rather than wrangling an Arduino and working with LEDs, another option is to get a quick start using ‘smart’ » Read More
As the clapping faded, Viktor’s voice rang out over the audience. “…As you navigate the traps and landmines ahead I want you to remember one thing: hustle beats smarts, when the smarts don’t hustle.”
Congratulations. You are now I-Corps alumni. » Read More