Major changes are in store for the electricity grid. On the one hand, there is the fast-growing variable production of renewable energy, including solar and wind, to be reckoned with. On the other hand, more and more technical applications (e.g. electric vehicles, heat pumps, …) require a considerable amount of energy and have very specific demand patterns. The consequences of these evolutions are mostly felt in three segments of the electricity market: electricity supply, balance maintenance and network congestion. As the need for flexible means to match supply and demand continues to increase, all eyes are now on innovative initiatives such as the Flux50 ICON project.
On January 24, the Flux50 ICON project kicked off with a meeting themed ‘privacy-friendly power flexibility trading’. What the participants refer to as ‘flexibility’ comes down to the electricity grid being able to maintain a balance between electricity demand and supply, within the limits of the current distribution and transmission systems and by means of controllable and flexible resources in the short term. However, worries over privacy are impeding this approach, especially when it comes to household electricity consumption. The PrivateFlex project is determined to solve this issue for good.
By aggregating the flex of hundreds of consumer appliances, different demand-side management (DSM) strategies – such as demand response and energy trading or ancillary services – can be carried out. However, for this to work, users must share their available local flex with the aggregator. Unfortunately, even though participants are fairly rewarded for their commitment, not everyone is willing to expose their energy data. As a result, privacy proves a major obstacle to broadening the use of household flex in demand control.
Nevertheless, flex will simply not be possible without personal data. A user’s demand is highly linked to their behavior, which introduces many uncertainties in the available flex. Moreover, local flex can also be achieved by means of heterogeneous sources, adding to the complexity of the problem. While data must indeed remain private, we must at least be able to capture uncertainties in the process.
First and foremost, The PrivateFlex project aims to tackle the abovementioned issues by making use of cryptographic algorithms, such as computation over encrypted data (COED), to keep flex data local and private while still allowing the flex to be traded at an aggregated level. Their second objective is to better characterize flex by means of machine learning (ML) techniques, both at local and aggregate level.
AE, in a consortium with KU Leuven, Smappee, Centrica Business Solutions (formerly known as REstore) and NXP, will be working on this project to create cost-effective solutions that address privacy issues and deal with uncertainty, ensuring that demand response can be implemented in residential buildings. Participating in our dream team will be kuori, d-Sides and Seth&Dunn, supported by the knowledge and expertise of our consultants specializing in the utilities sector. Specifically, AE will study the scalability of Kuori in combination with encryption on streaming data. In addition, empowered by the d-Sides analytics team and Seth&Dunn’s lean innovation teams, AE will investigate potential incentives for customers to make their flexibility available for analysis. To tackle that final challenge, we will look into self-learning algorithms and the use of gamification. Stay tuned!