To increase the output voltage stability and improve the operating efficiency of proton exchange membrane fuel cells (PEMFCs), a data-driven cooperative method for controlling the PEMFC output voltage is proposed in this paper. The proposed method adapts centralized learning and decentralized implementation, which can nonlinearly and adaptively realize optimal coordinated control over the hydrogen valve and the DC/DC converter. Additionally, a champion multiagent double delay deep deterministic policy gradient (CMA-4DPG) algorithm is proposed in this method, the design of which incorporates the policies of the champion selection mechanism, cooperative exploration, imitation learning guidance and curriculum guidance to improve the robustness of the cooperative method. The method cooperates with multiple controller to prevent output voltage fluctuation. The experimental results show that by simultaneously regulating the hydrogen flow through the hydrogen valve and the duty ratio of the DC/DC converter, the proposed method achieves better robustness and can improve the tracking performance of the PEMFC output voltage.

Wind speed fluctuation generally shortens the lifetime of the insulated gate bipolar transistor (IGBT) module in the doubly fed induction generator (DFIG), which leads to frequent component replacement and cost increase of wind power generation. Conventional power control strategies consider solely the wind turbine output power maximization, and existing junction temperature thermal management strategies focus on IGBT lifetime extension, both of which are not effective under turbulent wind speed conditions and ignore the trade-off between the device reliability and output power for the overall DFIG economic benefit. To bridge the gap between the IGBT reliability and the output power under turbulent wind speed conditions, we propose a novel IGBT thermal management strategy for optimal economic benefit. Specifically, we first smooth the output power through a linear power control (LPC) method with conditions on the wind speed and turbine speed to reduce the IGBT low-frequency junction temperature fluctuation, which extends IGBT lifetime. We then propose a grid encirclement and suppression search (GESS) method that maximizes the economic benefit defined by LPC-smoothed output power and IGBT lifetime. Simulation shows that our proposed LPC-GESS strategy outperforms a competing strategy at economic benefit by a large margin, up to 15.3%. Our proposed strategy can potentially be used in wind power stations for fast and reliable economic benefit-oriented IGBT thermal management.

Dense Long Range (LoRa) networks suffer from packet loss when many end devices contend for the same unlicensed channel. Channel activity detection (CAD) can miss weak or cross-spreading-factor (cross-SF) transmissions, while a uniform carrier sense multiple access with collision avoidance (CSMA/CA) backoff rule ignores the different time-on-air (ToA) costs of SF7–SF12 packets. To address these two coupled problems, this paper proposes an interference-limit-aware CSMA protocol (ILA-CSMA). ILA-CSMA first combines CAD with an instantaneous received signal strength indicator (RSSI) test derived from the residual interference tolerance of the selected spreading factor, and then scales the contention window according to normalized ToA. The protocol is implemented in the Framework for LoRa (FLoRa), an OMNeT++-based LoRa network simulator, and is evaluated for networks with 100–2000 nodes. Compared with Pure ALOHA, Slotted ALOHA, standard CSMA/CA, and two ablation variants, ILA-CSMA improves dense-network access by jointly reducing hidden collisions and airtime imbalance. In the 2000-node case, it increases the packet delivery ratio (PDR) by about 20 percentage points relative to standard CSMA/CA, keeps the Jain fairness index (JFI) above the 0.85 reference line, reduces the energy consumed per successful packet to 22% of the standard CSMA/CA value, and reduces conditional average packet delay from 18.5 s to 8.2 s. These results show that interference-aware sensing and ToA-aware backoff can improve large-scale LoRa access under the evaluated simulation conditions.