Distributed Energy Trading and Scheduling Among Microgrids via Multiagent Reinforcement Learning.

Renewable energy technologies empower microgrids to generate electricity to supply themselves and trade with others. Under this paradigm, microgrids have become autonomous entities that must intelligently determine their policies for energy trading and scheduling. Many factors influence a microgrid's decision-making, such as the complex microgrid infrastructure, the uncertain energy yield and demand, and the competition among the energy market players. These factors are usually hard to precisely model, and deriving the optimal policy for a microgrid is challenging. We propose a multiagent reinforcement learning (MARL) approach with an attention mechanism to learn the optimal policies for the microgrids without complex system modeling. We model each microgrid as an autonomous agent, which learns how to schedule energy resources and trade with others by collaborating with other agents. We adopt attention mechanism to enable intelligently selecting contextual information for the training of each agent. After training, an agent can make control decisions using only its local information, which can well preserve the microgrids' privacy and reduce the communication overhead among microgrids to facilitate distributed control. We implement a simulation environment and evaluate the performances of our proposed method using real-world datasets. The experimental results show that our method can significantly reduce the cost of the microgrids compared with the baseline methods.

In-situ self-assembly of robust Fe (III)-carboxyl functionalized polyacrylonitrile polymeric bead catalyst for efficient photo-Fenton oxidation of p-nitrophenol.

From the view of channel confinement and functional site capture, we develop an in-situ self-assembly strategy to fabricate the carboxyl functionalized Fe-HPAN bead catalyst with highly stable and uniformly dispersed metallic sites for efficient photo-Fenton oxidation of p-nitrophenol (p-NP). BET and FTIR analysis reveal that numerous carboxyl groups and mesopores exist in Fe-HPAN beads, which acts to capture and immobilize iron ions. Catalytic results show that the degradation rate and TOC removal for p-NP were up to 99.78 and 91.68% under the optimal condition. Even at near neutral pH, the degradation rate almost keep the same and the TOC removal can still reach 73.05%. Due to the autocatalytic cycle of FeIII/FeII, the apparent rate constant of Fe-HPAN (0.2247 min-1) was 5.4 times as high as unmodified Fe-PAN (0.0415 min-1) in the presence of H2O2 and visible light irradiation, which was 2-3 orders of magnitude larger than that of other reaction systems. More importantly, Fe-HPAN bead catalyst exhibited little loss of activity even after 20 cycles of re-utilization. The possible degradation pathway of p-NP was also proposed based on GC/MS analysis. The present work may provide a new perspective for the use of synthetic polymer to prepare low-cost, efficient and robust photo-Fenton oxidation catalysts.

[Investigation of heart rate turbulence after atrial premature beats before onset of paroxysmal atrial fibrillation].

OBJECTIVE: To discuss the clinical significance of heart rate turbulence (HRT) after atrial premature beats in accessing the temporal changes of vagus nerve before the onset of paroxysmal atrial fibrillation. METHODS: The HRT parameters: turbulence onset (TOA) and turbulence slope (TSA) after atrial premature impulses occurring 0 to 60 min before and after the onset of AF 56 patients with atrial fibrillation (AF). The heart rate variability (HRV) time domain parameter SDNN and the frequency-domain parameters, low frequency (LF), high frequency (HF), and LF/HF ratio were also analyzed. TOA and TSA were calculated for 3 periods reflecting morning hours (6-10 am), afternoon hours (1-5 pm), and night hours (0-4 am). RESULTS: (1) The TOA and TSA were significantly higher 1 h preceding AF than 1 h after AF(0.47+/-0.32 vs 0.24+/-0.18 and 16+/-6 vs 13+/-4, both P<0.05). The HRV time domain parameters and frequency-domain parameters did not change remarkably after the onset of PAF. (2) The TOA and TSA were significantly higher in night hours than in morning hours (1.2+/-0.6 vs 0.8+/-0.4 and 17+/-6 vs 14+/-4 respectively, both P<0.05), the two parameters of HRT maintained significant circadian variations. CONCLUSION: Vagal inhibition in response to premature atrial excitation is absent and transient enhancement of vagal outflow would occur before AF. HRT before atrial premature beats is of significance in accessing the changes of autonomic nervous system before onset of AF.