---
title: "Dake 2.0: deep tech energy"
description: "Dake restarts as a deep tech research project at the intersection of quantum physics, artificial intelligence and energy engineering."
url: "https://www.noze.it/en/insights/dake-2-deep-tech-energy/"
lang: "en"
alternate: "https://www.noze.it/insights/dake-2-deep-tech-energy/"
published: "2024-01-15"
author: "noze S.r.l."
keywords: "AI, R&D, Dake, Deep Tech, Quantum, Energy, Deep Learning, Graph Neural Networks"
---

# Dake 2.0: deep tech energy

Dake restarts as a deep tech research project at the intersection of quantum physics, artificial intelligence and energy engineering.

15 January 2024

## The restart

**Dake** restarts as a **deep tech** research project operating at the intersection of **quantum physics**, **artificial intelligence** and **energy engineering**. This is not a simple update: the project is reconfigured from the ground up with an ambitious mandate and a rigorous scientific foundation.

## Energy network optimization

The central axis of the research is **energy network optimization through AI**. **Deep Learning** algorithms are applied to the modeling and control of energy distribution infrastructures, with the goal of studying the reduction of **transmission losses**. Early laboratory results are encouraging, but the research is ongoing and real-scale validation remains an objective to be achieved.

## Research areas

The project is structured around three exploratory fronts:

- **Quantum systems**: study and simulation of quantum phenomena applicable to combinatorial optimization and distributed computing.
- **Distributed energy infrastructures**: modeling of decentralized networks for energy production, storage and distribution.
- **Gravitational potential energy harvesting**: research on innovative systems for energy recovery from gravitational sources, a field that remains largely unexplored.

## Technology stack

The technologies employed include **Deep Learning**, **Physics Simulation**, **Quantum Computing**, **Reinforcement Learning** and **Graph Neural Networks** — a set of tools that reflects the interdisciplinary nature and computational complexity of the project.
