Multi-Time-Scale Optimal Scheduling Strategy for Marine Renewable Energy Based on Deep Reinforcement Learning Algorithm.

Surrounded by the Shandong Peninsula, the Bohai Sea and Yellow Sea possess vast marine energy resources. An analysis of actual meteorological data from these regions indicates significant seasonality and intra-day uncertainty in wind and photovoltaic power generation. The challenge of scheduling to leverage the complementary characteristics of various renewable energy sources for maintaining grid stability is substantial. In response, we have integrated wave energy with offshore photovoltaic and wind power generation and propose a day-ahead and intra-day multi-time-scale rolling optimization scheduling strategy for the complementary dispatch of these three energy sources. Using real meteorological data from this maritime area, we employed a CNN-LSTM neural network to predict the power generation and load demand of the area on both day-ahead 24 h and intra-day 1 h time scales, with the DDPG algorithm applied for refined electricity management through rolling optimization scheduling of the forecast data. Simulation results demonstrate that the proposed strategy effectively meets load demands through complementary scheduling of wave power, wind power, and photovoltaic power generation based on the climatic characteristics of the Bohai and Yellow Sea regions, reducing the negative impacts of the seasonality and intra-day uncertainty of these three energy sources on the grid. Additionally, compared to the day-ahead scheduling strategy alone, the day-ahead and intra-day rolling optimization scheduling strategy achieved a reduction in system costs by 16.1% and 22% for a typical winter day and a typical summer day, respectively.

Measurement and spatiotemporal characteristics of China's green finance.

To study the extent of green finance development in China, this article constructs a green finance index system and employs the entropy value method to measure China's green finance by using a yearly provincial panel data from 2001 to 2020. The Thiel and Moran indices are then used to systematically analyze the temporal and spatial distribution of China's regional green finance. The findings are summarized as follows. Firstly, the overall green finance index in China experiences an upward trend. The development of green finance in the eastern region is superior to that in other regions in terms of absolute value and growth rate. Moreover, the differences in China's green finance index have shown an increasing trend over the last two decades, which is mostly contributed by the intra-regional differences. Finally, the inter-regional distribution of green finance index demonstrates that green finance development has a spatial spillover effect.

Entropy Value-Based Pursuit Projection Cluster for the Teaching Quality Evaluation with Interval Number.

The issue motivating the paper is the quantification of students' academic performance and learning achievement regarding teaching quality, under interval number condition, in order to establish a novel model for identifying, evaluating, and monitoring the major factors of the overall teaching quality. We propose a projection pursuit cluster evaluation model, with entropy value method on the model weights. The weights of the model can then be obtained under the traditional real number conditions after a simulation process by Monte Carlo for transforming interval number to real number. This approach can not only simplify the evaluation of the interval number indicators but also give the weight of each index objectively. This model is applied to 5 teacher data collected from a China college with 4 primary indicators and 15 secondary sub-indicators. Results from the proposed approach are compared with the ones obtained by two alternative evaluating methods. The analysis carried out has contributed to having a better understanding of the education processes in order to promote performance in teaching.

A Machine Learning Approach to Argo Data Analysis in a Thermocline.

With the rapid development of sensor networks, big marine data arises. To efficiently use these data to predict thermoclines, we propose a machine learning approach. We firstly focus on analyzing how temperature, salinity, and geographic location features affect the formation of thermocline. Then, an improved model based on entropy value method for the thermocline selection is demonstrated. The experiments adopt BOA Argo data sets and the experimental results show that our novel model can predict thermoclines and related data effectively.

EEG artifacts reduction by multivariate empirical mode decomposition and multiscale entropy for monitoring depth of anaesthesia during surgery.

Electroencephalography (EEG) has been widely utilized to measure the depth of anaesthesia (DOA) during operation. However, the EEG signals are usually contaminated by artifacts which have a consequence on the measured DOA accuracy. In this study, an effective and useful filtering algorithm based on multivariate empirical mode decomposition and multiscale entropy (MSE) is proposed to measure DOA. Mean entropy of MSE is used as an index to find artifacts-free intrinsic mode functions. The effect of different levels of artifacts on the performances of the proposed filtering is analysed using simulated data. Furthermore, 21 patients' EEG signals are collected and analysed using sample entropy to calculate the complexity for monitoring DOA. The correlation coefficients of entropy and bispectral index (BIS) results show 0.14 ± 0.30 and 0.63 ± 0.09 before and after filtering, respectively. Artificial neural network (ANN) model is used for range mapping in order to correlate the measurements with BIS. The ANN method results show strong correlation coefficient (0.75 ± 0.08). The results in this paper verify that entropy values and BIS have a strong correlation for the purpose of DOA monitoring and the proposed filtering method can effectively filter artifacts from EEG signals. The proposed method performs better than the commonly used wavelet denoising method. This study provides a fully adaptive and automated filter for EEG to measure DOA more accuracy and thus reduce risk related to maintenance of anaesthetic agents.

Molecular epidemiological study on rubella virus strains isolated in Zhejiang province, China,2005-2010 / 中华流行病学杂志

Objective To analyze the molecular epidemiological characteristic of rubella virus strains isolated in Zhejiang province from 2005 to 2010, to provide basic data for rubella prevention and control. Methods Rubella virus strains were isolated on Vero cells from the suspected patients' specimens collected in Zhejiang province during 2005 to 2010. Partial fragments of the structural gene of Zhejiang rubella strains were amplified, using nested reverse transcription-polymerase chain reaction (RT-PCR). The amplified products were sequences and analyzed.Results In total, 7 rubella strains were isolated from 52 clinical specimens, of which six were classified as genotype I E and only one was characterized as genotype 2B. In the phylogenetic tree, the Zhejiang IE genotype rubella strains were located in the same branches with Hongkong or Hainan isolates respectively, but the Zhejiang 2B genotype strain were located in the same branch with oversea strain BuenosAires.ARG/46.08. Through p-distance analysis, results also showed that the Zhejiang 2B genotype strain was closer to the 2B strains isolated from overseas (0.011 ) than those strains from other provinces of China (0.023). Compared with Chinese vaccine strain BRD Ⅱ, the homology on three structural genes was C＞E2＞E1, but the homology of deduced amino acid sequence was E1 ＞ C ＞ E2, with corresponding 3,11 and 23 amino acid mutations. There was only one amino acid on E1 gene with entropy value higher than 0.600, but seven sites on E2 gene with entropy value appeared higher than 0.600 and one with entropy value higher than 1.000. Conclusion Two genotypes of rubella virus had circulated in Zhejiang province during 2005 to 2010. Genotype IE appeared to be the predominant genotype and 2B being an imported one. Amino acid sequence of E1 gene from Zhejiang rubella strains was comparatively conserved, but E2 gene was hypervariable.Study on rubella virus E2 and C gene should be conducted in the epidemiological surveillance program of rubella.