Residential energy storage is undergoing rapid innovation, driven by the need for efficient solar energy utilization and dynamic grid participation. Texas Instruments' Henrik Magnesson emphasizes that as feed-in tariffs decline and market-driven energy pricing becomes prevalent, homeowners will increasingly turn to battery energy storage systems (ESS) to store excess solar generation for use during peak demand, to charge EVs, or to exploit profitable energy arbitrage opportunities. Click here to listen to Part 1 of this chat.

This first, of a two part series, Inside Electronics podcast, guest-hosted by technology editor Andy Turudic of Electronic Design, features Henrik Mannesson, General Manager of Grid Infrastructure and Power Delivery Industrial Systems at Texas Instruments (TI), discussing the evolving landscape of energy infrastructure with a focus on the pivotal role of semiconductors in the renewable energy transition.

Not every microcontroller can handle artificial intelligence and machine learning (AI/ML) chores. Simplifying the models is one way to squeeze algorithms into a more compact embedded compute engine. Another way is to pair it with an AI accelerator like Femtosense’s Sparse Processing Unit (SPU) SPU-001 and take advantage of sparsity in AI/ML models.

In this episode, Sam Fok, CEO at Femtosense, talks about AI/ML on the edge, the company's dual sparsity design, and how the small, low power SPU-001 can augment a host processor.