No abstract

No abstract

In the energy sector, prosumers are becoming relevant entities for energy management systems since they can share energy with their citizen energy community (CEC). Thus, this paper proposes a novel methodology based on demand response (DR) participation in a CEC context, where unsupervised learning algorithms such as convolutional neural networks and k-means are used. This novel methodology can analyze future events on the grid and balance the consumption and generation using end-user flexibility. The end-users’ invitations to the DR event were according to their ranking obtained through three metrics. These metrics were energy flexibility, participation ratio, and flexibility history of the end-users. During the DR event, a continuous balancing assessment is performed to allow the invitation of additional end-users. Real data from a CEC with 50 buildings were used, where the results demonstrated that the end-users’ participation in two DR events allows reduction of energy costs by EUR 1.31, balancing the CEC energy resources.

The use of energy sharing models in smart grids has been widely addressed in the literature. However, feasible technical solutions that can deploy these models into reality, as well as the correct use of energy forecasts are not properly addressed. This paper proposes a simple, yet viable and feasible, solution to deploy energy management systems on the end-user-side in order to enable not only energy forecasting but also a distributed discriminatory-price auction peer-to-peer energy transaction market. This work also analyses the impact of four energy forecasting models on energy transactions: a mathematical model, a support-vector machine model, an eXtreme Gradient Boosting model, and a TabNet model. To test the proposed solution and models, the system was deployed in five small offices and three residential households, achieving a maximum of energy costs reduction of 10.89% within the community, ranging from 0.24% to 57.43% for each individual agent. The results demonstrated the potential of peer-to-peer energy transactions to promote energy cost reductions and enable the validation of auction-based energy transactions and the use of energy forecasting models in today’s buildings and end-users.

No abstract