Summary For enhancing the awareness and competitiveness of distributed energy resources (DER) in energy markets, an optimal and implementation and operation of these resources. To address this issue, in this paper, objective, DERs that can collaborate with other DER installed as closer or far topologies, forming coalitions for gaining competitiveness between each other in the energy market, have been selected for study. The profit allocation due to coalition between DERs is being identified as an important issue for ensuring renewable sources installation in smart grids. A methodology with, bi‐level, structures is proposed to maximize the profit in a competitive market and allocate profit resulting from a coalition formation between multiple energy districts encompassing DERs. In the primary level analysis, a mechanism based on noncooperative game theory is presented with the aim of creating a competitive market, as well as, to study the supply energy strategies based on pricing mechanisms of multiple energy suppliers. In the second level, various distribution methods, namely, Shapley, Nucleolus, and Merge and Split, are compared with each other for profit allocation analysis. Our study highlights that the disconnection of DERs resulting from pricing decisions allows them to collaborate together with aggregated facilities to achieve higher profits due to excess production and avoid penalties due to shortages in production, which in essence, demonstrates a significant operational increase in their profits, a concept that favors the likelihood for all energy suppliers and producers to form a coalition for economic optimizations.

Summary This paper proposes the gated recurrent unit (GRU)‐recurrent neural network (RNN), a deep learning approach to predict the remaining useful life (RUL) of lithium‐ion batteries (LIBs), accurately. The GRU‐RNN structure can self‐learn the network parameters utilizing adaptive gradient descent algorithms, leading to a reduced computational cost. Unlike the long short‐term memory (LSTM) model, GRU‐RNN allows time‐series dependencies to be tracked between degraded capacities without using any memory cell. This enables the method to predict non‐linear capacity degradations and build an explicitly capacity‐oriented RUL predictor. Additionally, feature selection based on the random forest technique was used to enhance the prediction precision. The analyses were conducted based on four separate cycling life testing datasets of a lithium‐ion battery. The experimental results indicate that the average percentage of root mean square error for the proposed method is about 2% which respectively is 1.34 times and 8.32 times superior to the LSTM and support vector machine methods. The outcome of this work can be used for managing the Li‐ion battery's improvement and optimization.

No abstract

No abstract

No abstract