Multi‐stack fuel cell (MFC) systems provide higher performances and reliability than single‐stack fuel cell systems through higher flexibility. The aim of this study is to investigate the degraded mode operation of MFC systems upon the loss of one of its stack. The different power allocation strategies impact the behaviour of the MFC system. Fuel consumption results obtained through simulation using a driving cycle acquired on a test vehicle are used to compare the chosen allocation strategies. The simulations have been conducted in a Matlab–Simulink environment. The results show that with a simple reconfiguration of the system the multi‐stack system can still complete the driving cycle. The fuel consumption results during normal and degraded mode operation are compared and show acceptable efficiency loss during degraded mode operation.

Multi stack fuel cell systems provide higher performances and reliability than single stack fuel cell systems. The aim of this paper is to investigate the degraded mode operation of multi- stack fuel cell systems upon the loss of one of its stack. The different power allocation strategies impact the behavior of the multi-stack fuel cell system. Fuel consumption results on a driving cycle acquired on the Hydrogen Research Institute's (HRI) test vehicle also depends on the chosen allocation strategy. The simulations have been conducted in MATLAB - Simulink. The results show that with a simple reconfiguration of the system the multistack system can still complete the driving cycle. The fuel consumption results during normal and degraded mode operation are compared and show acceptable efficiency loss during degraded mode operation.

An efficient participation of prosumers in power system management depends on the quality of information they can obtain. Prosumers actions can be performed by automated agents that are operating in time-changing environments. Therefore, it is essential for them to deal with data stream problems in order to make reliable decisions based on the most accurate information. This paper provides an in-depth investigation of data and concept drift issues in accordance with residential prosumer agents. Additionally, the adaptation techniques, forgetting mechanisms, and learning strategies employed to handle these issues are explored. Accordingly, an approach is proposed to adapt the prosumer agent models to overcome the gradual and sudden concept drift concurrently. The suggested method is based on triggered adaptation techniques and performance-based forgetting mechanism. The results obtained in this study demonstrate that the proposed approach is capable of constructing efficient prosumer agents models with regard to the concept drift problem.

Flexibility from demand-side resources is increasingly required in modern power systems to maintain the dynamic balance between demand and supply. This flexibility comes from elastic users managing controllable loads. In this context, controlling Electric Space Heaters (ESHs) is of particular interest because it can leverage building inner thermal storage capacity to shift consumption while maintaining comfort conditions. Some economic Demand Response (DR) programs have considered exploiting EHSs flexibility potentials in recent years. However, these programs still struggle to engage customers due to the complexity of processing price signals for inexpert users. Therefore, it is necessary to develop automated tools for helping users to operate their loads. Accordingly, this paper presents a recommender system based on Gaussian processes to discover users' valuations of thermal comfort and perform the predictive control of their ESHs. The proposed method enables customers to participate in DR programs and impose their preferences through straightforward queries instead of directly changing control parameters. Validation results demonstrate that users maximize their utility by supplying noiseless and consistent data to the recommender system. Additionally, the suggested approach achieves a higher acceptance rate than other methods from the literature, such as persistency and support vector machines.