New 3-year postdoctoral research position on AI-powered control and optimisation for smart distribution systems with hybrid transformers at @oxengsci in collaboration with @energy_matthew & @IONATE_Energy
Link: https://t.co/SHrjUd3N90
Apply by 10th of January
Interested in how multi-agent reinforcement learning (MARL) can support the decentralization and decarbonization of energy networks and mitigate the associated challenges? Have a look at our survey, written with Chaimaa Essayeh, @UoE_Agents, and @TMorstyn https://t.co/F2tU90oSdv
REPORT RELEASE @EnergyREV_UK - Putting wind and solar in their place: Internalising congestion and other system-wide costs with enhanced contracts for difference in Great Britain. @UKRI_News@innovateuk @jjeh102 @camjhep@TMorstyn
https://t.co/3iWYojTuqL
The paper looks at algorithm development and qubit scaling for problems where we want to:
- Plan distribution network upgrades
- Site/size renewables
- Schedule loads with on/off flexibility (e.g. EVs, smart appliances)
Can quantum computing help with power system optimisation? The answer is not if but when. New paper in IEEE Trans. on Smart Grid using @dwavesys 5,760 qubit quantum annealer
https://t.co/TukVjhxOxq
New partnership with @nationalgriduk to help decarbonise power transmission. Great work from the whole team on getting this partnership going. More information on: https://t.co/59oefKtqlG (my photography hobby also paid off with this featured picture 📷)
@SchoolOfEng_UoE
"Putting Wind and Solar in Their Place" - new paper with Iacopo Savelli, @jjeh102 and @camjhep.
We look at how we can improve the UK's renewable CfD auctions by accounting for cost & CO2 impacts of network congestion, redispatch and reserve requirements.
https://t.co/WzOzUYg5Lp
Key takeaways:
1. Carbon abatement from renewables depends on network congestion due to redispatch.
2. Deploying renewables in the south of GB can decrease congestion cost by £4.04/MWh.
3. Predictable renewable generation can decrease reserve costs by £2.44/MWh.
New paper out🚨It's hard to navigate the space of distributed energy resources coordination! The literature is growing exponentially, with many words like 'P2P' and 'transactive energy' thrown around. How do all coordination strategies relate to each other?https://t.co/LhBMw8Byrr
@MattDeakin6@DavidHowey@edinburgh@OtherProfGreen@CentreDice Great, let’s follow up on potential links. For our project data- and model-driven methods will be complementary, since we have a high-fidelity GB system model plus access to granular long-term market data.
Recruting a Postdoctoral Research Associate to look at energy market integration of grid-scale storage for maximum emissions reduction @Edinburgh. Collaboration with Professor @DavidHowey, @OtherProfGreen. Link: https://t.co/ezzUtUVCLw
Apply by 07/06/2022
First PhD paper published! 🎉
We propose novel scalable multi-agent reinforcement learning algorithms for the distributed control of residential flexibility, including EVs and smart heating. @MD_MCCULLOCH@TMorstyn https://t.co/WItMxcxhmy #energytwitter#reinforcementlearning
We present a "smart energy neighbourhood" architecture for pursuing shared objectives within local energy system, such as reducing energy poverty and supporting community investment in clean energy technologies.
Local energy isn't just about competition - new paper "Better together: Harnessing social relationships in smart energy communities" with Iacopo Savelli in Energy Research & Social Science for @EnergyREV_UK, @TheSmithSchool & @UoE_IES https://t.co/cQDW3ibXeV