基于深度强化学习的电网自主控制与决策技术

高比例可再生能源的并网和电力电子设备的不断增加给电力系统运行与实时控制带来诸多挑战。人工智能技术的飞速发展为解决高维度、高非线性、高时变性优化控制和决策问题提供了新的思路。文中基于深度强化学习技术,提出了具有在线学习功能的电网自主优化控制和决策框架,即“电网脑”系统。该系统可通过离线和在线学习不断积累经验,从而在亚秒时间内(1 s以内)根据电网实时量测数据给出调度控制指令及预期控制效果。该系统近期可用于辅助调度员决策,远期可为自动调度提供技术手段。为验证“电网脑”理论框架的可行性,文中以电网自主电压控制和联络线潮流控制为例,介绍了电力系统自主控制与决策方法及其实现流程,并通过数值实验验证了所提方法学习能力及其应用于电力系统自主控制与决策的可行性。

Pseudo channel:time embedding for motor imagery decoding

Motor imagery(MI)based electroencephalogram(EEG)represents a frontier in enabling direct neural control of external devices and advancing neural rehabilitation.This study introduces a novel time embedding technique,termed traveling-wave based time embedding,utilized as a pseudo channel to enhance the decoding accuracy of MI-EEG signals across various neural network architectures.Unlike traditional neural network methods that fail to account for the temporal dynamics in MI-EEG in individual difference,our approach captures time-related changes for different participants based on a priori knowledge.Through extensive experimentation with multiple participants,we demonstrate that this method not only improves classification accuracy but also exhibits greater adaptability to individual differences compared to position encoding used in Transformer architecture.Significantly,our results reveal that traveling-wave based time embedding crucially enhances decoding accuracy,particularly for participants typically considered“EEG-illiteracy”.As a novel direction in EEG research,the traveling-wave based time embedding not only offers fresh insights for neural network decoding strategies but also expands new avenues for research into attention mechanisms in neuroscience and a deeper understanding of EEG signals.

A framework for end-to-end RSVP context transfer in mobile IPv6

A framework for end-to-end RSVP context transfer in Mobile IPv6(MIPv6) based on the architecture of F-HMIPv6 is proposed in this paper. The scheme provides an end-to-end RSVP context transfer for real-time applications to overcome the weakness of Context Transfer Protocol which can not meet the need of end-to-end QoS mechanisms because contexts are only transferred between Access Routers(ARs), therefore they can promptly get the same forwarding process, minimize the handover service disruption, and avoid initiating the end-to-end RSVP signaling from scratch after an MN performs handovers. It may also reduce the signaling overhead and handover latencies by adopting the F-HMIPv6architecture. The performance of the approach is compared with the re-initiating RSVP signaling to re-establish QoS states using network simulator, and the numerical results show that the scheme has the less latency and packet loss than that of the re-initiating approach.

Authorization Administration in a Distributed Multi-application Environment

To meet the authorization administration requirements in a distributedcomputer network environment, this paper extends the role-based access control model with multipleapplication dimensions and establishes a new access control model ED-RBAC(Extended Role Based AccessControl Model) for the distributed environment. We propose an extendable hierarchical authorizationassignment framework and design effective role-registeringi role-applying and role-assigningprotocol with symmetric and asymmetric cryptographic systems. The model can be used to simplifyauthorization administration in a distributed environment with multiple applications.

A brief study of ＂new media＂ on the ethical problems and countermeasures

Modern media technology on the dramatic changes that took place in the context of globalization, new media also came in- to being. Its scope, mainly related to blogs, wikis, micro-blogging, micro-letter network, media NET, driving NET, computer networks, mobile text messaging, mobile TV, digital TV, touch-sensitive media and other free collections of a range of media production and timely dissemination of information. This article will explain the features of the new medium, unlike traditional media, characteristics of new me- dia, new media, moral perspective, combines technical, ethical and management in exploring the three causes of relevant ethical issues. The related ethical issues have been on public morals and social ethics of media brought new challenges. Looking for ethical issues related to new media strategy, new media system of ethics and oversight mechanisms, strengthen self-discipline and new media new media profes- sional philosophy and moral consciousness is now the important issues we face.

Models for Teaching Culture in Computer-Assisted Language Learning

CALL （computer-assisted language learning） has tremendously transformed the teaching of language, with its wide application in many aspects of language teaching. However, how to integrate CALL into the teaching of culture is still rarely discussed. The purpose of the paper is to explore feasible models for teaching culture in CALL and their effects on students＇ acquisition process. Based on two fundamental pedagogical approaches （participatory pedagogy and multiliteracies pedagogy） for teaching culture, this paper proposes three pedagogical models （problem-posing model, web-quest model, and computer-supported collaborative learning model） for teaching culture in CALL. In the end, this paper illustrates a combination of the three models in real CALL setting by a cultural teaching case. A questionnaire survey and interviews are conducted to reflect on students＇ feedback, which gives an insight into possible adjustments in teaching models and the paper also proposes future possibilities in applying these models into teaching culture

Development of the Investigation Tool of a Study State and Practical Use of MyPage

Internetwork environment at university has been improved to supply often the lecture materials to students through websites. Along with such a tendency, the number of students who use PC （Personal computer） has also increased during the lesson at university. Hereupon, the authors investigate whether the students will get high scores in tests when some limitations are imposed on the students＇ use of the PC during lecture and when they are not. The authors create the tool to check the students＇ learning situation and to grasp which student is performing the PC operations, which are not related to the ongoing lesson, during the lecture. Teaching assistant carrying the iPad is made to walk around the class during the lecture and collect data of the students. In addition, the authors develop ＂MyPage＂ that the students can be given access to their personal information including individual class absence/tardiness, lesson comprehension and question understanding level of them and after using MyPage, the authors examine its effectiveness as a tool and its relationship with their attendance rate.

System Recovery-Aware Virus Propagation Model and Its Steady-State Analysis

Network structures and human behaviors are considered as two important factors in virus defense currently. However, due to ignorance of network security, normal users usually take simple activities, such as reinstalling computer system, or using the computer recovery system to clear virus. How system recovery influences virus spreading is not taken into consideration currently. In this paper, a new virus propagation model considering the system recovery is proposed first, and then in its steady-state analysis, the virus propagation steady time and steady states are deduced. Experiment results show that models considering system recovery can effectively restrain virus propagation. Furthermore, algorithm with system recovery in BA scale-free network is proposed. Simulation result turns out that target immunization strategy with system recovery works better than traditional ones in BA network.

Independent Source Separation of Multichannel Electroencephalogram Based on Neural Network

A neural network method for independent source separation (ISS) of multichannel electroencephalogram (EEG) is proposed in this paper.Using the denoising function of wavelet multiscale decomposition,the high-frequency noises are removed from the original (raw) EEGs.Then the multichannel EEGs are treated as the weighted mixtures and the expression of weight vector is obtained by seeking the local extrema of the fourth-order cumulants (i.e.kurtosis coefficients) of the mixtures.After these process steps,the weighted mixtures are used as the input of neural network,so the independent source of EEGs can be separated one by one.The experimental results show that our method is effective for ISS of multichannel EEGs.

脑梗死继发癫痫的脑电图与经颅多普勒检查分析

目的分析探讨脑梗死继发癫痫的原因以及其与脑血管病变的关系。方法应用脑电图(EEG)和经颅多普勒(TCD)分别对48例脑梗死继发癫痫患者进行检查,并对检查结果进行分析。结果48例EEG正常6例,异常42例,异常率87.5%,其中轻度异常5例,中度异常17例,重度异常8例;局限性异常12例。48例TCD异常38例,异常率79.2%,其中血流速度增快13例,减慢19例,增快、减慢同时存在6例;两侧流速不对称13例,出现涡流、湍流频谱5例。结论脑梗死继发癫痫多由于脑血管舒缩功能失调影响脑供血以及各种原因造成脑血管血流量减少,使脑组织缺血、缺氧而导致癫痫发作。

The role of microglia in thalamic reticular nucleus in acupuncture regulating cognitive deficits in insomnia rats

Objective:To explore the mechanism of acupuncture in regulating cognitive deficits in insomnia rats by observing the effect of acupuncture on microglia in thalamic reticular nucleus(TRN).Methods:Thirty rats were randomly divided into a control group,a model group and an acupuncture group,with 10 rats in each group.The insomnia model was established by intraperitoneal injection of para-chlorophenylalanine(PCPA)once a day for 2 d.Rats in the control group were intraperitoneally injected with the same amount of normal saline.Rats in the acupuncture group received acupuncture at Neiguan(PC 6)and Zusanli(ST 36)for 5 consecutive days.The CLOCKLAB 2 data acquisition system was used to dynamically observe the sleep of the rats throughout the experiment.The cognition of rats was evaluated by event-related potentials(ERPs).After intervention,brain tissue was extracted.Immunofluorescence was used to test the fluorescence expression in TRN region.The concentrations of interleukin(IL)-1βand tumor necrosis factor(TNF)-αwere detected by enzyme-linked immunosorbent assay.Results:After intraperitoneal injection of PCPA suspension,the spontaneous activity in light period of rats in the model group and acupuncture group increased significantly compared with the control group(both P<0.01).After acupuncture treatment,the rats in the acupuncture group had much less spontaneous activity during the light period than those in the model group(P<0.01),and the results indicated that acupuncture could effectively improve the sleep quality of insomnia rats.Compared with the control group,rats in the model group showed that the P3 latency,the average optical density of microglia,and the concentrations of IL-1βand TNF-αincreased significantly(all P<0.05),and the P3 amplitude decreased significantly(P<0.01).Compared with the model group,rats in the acupuncture group presented that the P3 latency,the average optical density of microglia,and the concentrations of IL-1βand TNF-αwere significantly decreased(all P<0.05),and the amplitude of P3 was significantly increased(P<0.05).Conclusion:Acupuncture possesses an ability to improve the cognitive state in insomnia rats.The mechanism may be related to inhibiting the microglial activation,diminishing the levels of pro-inflammatory mediators like IL-1βand TNF-α,and promoting the recovery of central nervous system function.