The application of federated learning in Virtual Power Plants (VPPs) addresses the data silo issue between VPPs and enhances their ability to cope with nonlinear and stochastic scheduling characteristics, which enables VPPs better accommodate distributed energy resources and flexible loads while participating in frequency regulation services. However, although existing federated learning methods strive to solve privacy protection issues, the plaintext transmission of gradients still exposes sensitive data to the threat of curious power control centers and external inference attacks. Therefore, a privacy-protected horizontal federated reinforcement learning approach for multi-VPP optimal scheduling is proposed in this paper. Firstly, a cost-based global optimization scheduling model for multiple VPPs is constructed, modeling the internal scheduling process of VPPs as a Markov decision process. Then, an improved secure horizontal federated multi-VPP collaborative training method is presented, and local models are trained using the Deep Transformer Q-Network algorithm, with local differential privacy and CKKS homomorphic encryption implemented to ensure privacy protection. Finally, a case study is conducted using frequency regulation ancillary service market data and the IEEE-39 bus system structure. Simulation results show that the proposed approach outperforms similar algorithms, achieving high levels of privacy protection and economic operation for VPPs.

Geographically distributed data centers (DCs) have emerged as significant energy consumers, which has led to the integration of renewable energy sources (RES) into DC power provisioning systems. However, the intermittent nature of RES and the randomness of user requests can cause significant fluctuations in DC operating power. It can be detrimental to the operation of IT equipment and lead to instability in the power grid. In this paper, aiming for tightly coupled interconnection scenarios with multi-data centers in varying regions, a multi-data center tie-line power smoothing method based on demand response is proposed. By modulating the power load of server clusters with workload scheduling, we establish a control model combined with intra-DC temporal task migration and inter-DC spatial task migration to deal with high-frequency power fluctuations. The uninterruptible power supply (UPS) battery control model is established to tackle low-frequency fluctuations. Furthermore, we design the two-stage heuristic power regulation algorithm to achieve the best practice of smoothing effect by real-time tracking of power targets after two-layer filtering. Finally, this paper performs a detailed performance simulation evaluation based on tracking data from a real DC and wind and photovoltaic (PV) new energy generation data, using four interconnected DC parks of different sizes across different regions as examples. The simulation results demonstrate that the proposed method effectively smoothing the multi-data center's tie-line power. Additionally, inter-DC temporal task migration serves as a viable solution to overcome the limitations of task migration response within a single DC, reducing the frequency of UPS battery bank charges and discharges, which in turn prolongs their service life. This approach facilitates the utilization of RES while maintaining power quality, and it also aids in reducing the escalating operation and maintenance expenses of DCs.

Distributed storage systems, e.g., Hadoop Distributed File System (HDFS), have been widely used in datacenters for handling large amounts of data due to their excellent performance in terms of fault tolerance, reliability and scalability. However, these storage systems usually adopt the same replication and storage strategy to guarantee data availability, i.e., creating the same number of replicas for all data sets and randomly storing them across data nodes. Such strategies do not fully consider the difference requirements of data availability on different data sets. More servers than necessary should thus be used to store replicas of rarely-used data, which will lead to increased energy consumption. To address this issue, we propose an energy-efficient storage strategy for cloud datacenters based on a novel hypergraph coverage model. According to users' requirements of data availability in different applications, our proposed algorithm can selectively determine the corresponding minimum hyperedge coverage, which represents the minimum set of data nodes required in the datacenter. Hence, some other data nodes can be turned off for the purpose of energy saving. We have also implemented our proposed algorithm as a dynamic runtime strategy in a HDFS based prototype datacenter for performance evaluation. Experimental results show that the variable hypergraph coverage based strategy can not only reduce energy consumption, but can also improve the network performance in the datacenter.