Abnormal Action Recognition with Lightweight Pose Estimation Network in Electric Power Training Scene

Electric power training is essential for ensuring the safety and reliability of the system.In this study,we introduce a novel Abnormal Action Recognition(AAR)system that utilizes a Lightweight Pose Estimation Network(LPEN)to efficiently and effectively detect abnormal fall-down and trespass incidents in electric power training scenarios.The LPEN network,comprising three stages—MobileNet,Initial Stage,and Refinement Stage—is employed to swiftly extract image features,detect human key points,and refine them for accurate analysis.Subsequently,a Pose-aware Action Analysis Module(PAAM)captures the positional coordinates of human skeletal points in each frame.Finally,an Abnormal Action Inference Module(AAIM)evaluates whether abnormal fall-down or unauthorized trespass behavior is occurring.For fall-down recognition,three criteria—falling speed,main angles of skeletal points,and the person’s bounding box—are considered.To identify unauthorized trespass,emphasis is placed on the position of the ankles.Extensive experiments validate the effectiveness and efficiency of the proposed system in ensuring the safety and reliability of electric power training.

Identification of Key Links in Electric Power Operation Based-Spatiotemporal Mixing Convolution Neural Network

As the scale of the power system continues to expand,the environment for power operations becomes more and more complex.Existing risk management and control methods for power operations can only set the same risk detection standard and conduct the risk detection for any scenario indiscriminately.Therefore,more reliable and accurate security control methods are urgently needed.In order to improve the accuracy and reliability of the operation risk management and control method,this paper proposes a method for identifying the key links in the whole process of electric power operation based on the spatiotemporal hybrid convolutional neural network.To provide early warning and control of targeted risks,first,the video stream is framed adaptively according to the pixel changes in the video stream.Then,the optimized MobileNet is used to extract the feature map of the video stream,which contains both time-series and static spatial scene information.The feature maps are combined and non-linearly mapped to realize the identification of dynamic operating scenes.Finally,training samples and test samples are produced by using the whole process image of a power company in Xinjiang as a case study,and the proposed algorithm is compared with the unimproved MobileNet.The experimental results demonstrated that the method proposed in this paper can accurately identify the type and start and end time of each operation link in the whole process of electric power operation,and has good real-time performance.The average accuracy of the algorithm can reach 87.8%,and the frame rate is 61 frames/s,which is of great significance for improving the reliability and accuracy of security control methods.

Electricity-Carbon Interactive Optimal Dispatch of Multi-Virtual Power Plant Considering Integrated Demand Response

As new power systems and dual carbon policies develop,virtual power plant cluster(VPPC)provides another reliable way to promote the efficient utilization of energy and solve environmental pollution problems.To solve the coordinated optimal operation and low-carbon economic operation problem in multi-virtual power plant,a multi-virtual power plant(VPP)electricity-carbon interaction optimal scheduling model considering integrated demand response(IDR)is proposed.Firstly,a multi-VPP electricity-carbon interaction framework is established.The interaction of electric energy and carbon quotas can realize energy complementarity,reduce energy waste and promote low-carbon operation.Secondly,in order to coordinate the multiple types of energy and load in VPPC to further achieve low-carbon operation,the IDR mechanism based on the user comprehensive satisfaction(UCS)of electricity,heat as well as hydrogen is designed,which can effectively maintain the UCS in the cluster within a relatively high range.Finally,the unit output scheme is formulated to minimize the total cost of VPPC and the model is solved using theCPLEX solver.The simulation results showthat the proposed method effectively promotes the coordinated operation among multi-VPP,increases the consumption rate of renewable energy sources and the economics of VPPC and reduces carbon emissions.

A method for cleaning wind power anomaly data by combining image processing with community detection algorithms

Current methodologies for cleaning wind power anomaly data exhibit limited capabilities in identifying abnormal data within extensive datasets and struggle to accommodate the considerable variability and intricacy of wind farm data.Consequently,a method for cleaning wind power anomaly data by combining image processing with community detection algorithms(CWPAD-IPCDA)is proposed.To precisely identify and initially clean anomalous data,wind power curve(WPC)images are converted into graph structures,which employ the Louvain community recognition algorithm and graph-theoretic methods for community detection and segmentation.Furthermore,the mathematical morphology operation(MMO)determines the main part of the initially cleaned wind power curve images and maps them back to the normal wind power points to complete the final cleaning.The CWPAD-IPCDA method was applied to clean datasets from 25 wind turbines(WTs)in two wind farms in northwest China to validate its feasibility.A comparison was conducted using density-based spatial clustering of applications with noise(DBSCAN)algorithm,an improved isolation forest algorithm,and an image-based(IB)algorithm.The experimental results demonstrate that the CWPAD-IPCDA method surpasses the other three algorithms,achieving an approximately 7.23%higher average data cleaning rate.The mean value of the sum of the squared errors(SSE)of the dataset after cleaning is approximately 6.887 lower than that of the other algorithms.Moreover,the mean of overall accuracy,as measured by the F1-score,exceeds that of the other methods by approximately 10.49%;this indicates that the CWPAD-IPCDA method is more conducive to improving the accuracy and reliability of wind power curve modeling and wind farm power forecasting.

Experiences of the Electricity System Operator Incentive Scheme in Great Britain

National Grid is the electricity system operator in Great Britain and has an unique feature in so far as it is one of the world’s few for-profit system operators. In addition, the commercially orientation of the British market rules means that nearly every action taken by National Grid to operate the system has a cost associated to it. Based on those factors and in order to encourage National Grid to seek continuous improvements and drive for efficient and economic system operation, the regulator (Ofgem) offers an incentive scheme, whereby a target is agreed annually and any savings in relation to this target are shared between consumers and National Grid in the form of a profit. It is in National Grid’s best interest to have mechanisms to mitigate the impacts of volatility in the costs it faces as system operator so that it can implement cost saving actions without the risk of windfall losses (or gains) arising from sudden changes in uncontrollable drivers. The purpose of this paper is to share the experiences of National Grid in the operation of Great Britain's electricity system, with a special interest on the mechanisms created to manage the associated costs in response to the incentive scheme. It does so by describing the market operation in Great Britain and the costs drivers impacting National Grid’s system operation and illustrating the steps recently taken by National Grid to propose volatility mitigation mechanisms. It concludes with the rationale and expected results from the latest proposals as consulted with the industry for introduction in the incentive scheme starting on 1st April 2011. It is worth noting that with this work, the authors wish to both share the experience with other system operators and regulators in the world, as well as give British market participants an insight on the inner workings of National Grid.

“人-车-桩-路-网”深度耦合下的配电网协同规划与运行优化

电动汽车(EV)作为连接交通电气化和电网清洁化的纽带和桥梁,可实现电力-交通-信息之间的深度耦合,形成电力-交通一体化的规划及运行架构。配电-交通融合系统(DTIS)中,EV充放电行为多时空动态交织、电能流-交通流-信息流深度融合、多利益主体动态博弈等大量不确定性因素使配电网的规划及运行优化的边界都将发生重大转变,但同时也给挖掘利用EV的移动储能特性和提升配电网灵活性带来了契机。为此,在分析“人-车-桩-路-网”深度耦合下配电网的形态演化特征基础上,剖析了新形态下配电网协同规划与运行优化所面临的新挑战,进而针对“人-车-桩-路-网”耦合下的EV灵活性建模、灵活域高效构建及预测、协同规划、运行优化4个方面关键技术展开讨论,并对相关技术问题的研究方向进行了展望。

基于绿电和自愿减排量交易的园区低碳电力运营优化

为保证园区电力运营经济性,提高清洁电能的使用比例,文章提出了一种基于绿电和自愿减排量交易的园区低碳电力运营优化模型。该模型综合考虑了绿电和火电的购电成本、光伏发电成本及自愿减排量收益,以总运营成本最小为目标函数,结合随机概率约束,分中长期、日前和实时三阶段对绿电、火电电量以及光伏发电量进行优化。以南京市某企业园区的数据为基础,在自愿减排量价格合理的前提下,该优化模型可小幅降低园区总运营成本,并且显著提高了清洁电能的使用比例和园区应对扰动的能力。另外,就自愿减排量价格以及置信度取值对优化结果的影响进行了分析。

新型电力系统中的规划运营与电力市场:研究进展与科研实践

“碳达峰、碳中和”战略目标下,能源结构清洁化—可再生能源并网比例不断提高、能源要素多元化—发输配用各环节海量灵活性资源接入两大趋势带来的挑战,对电力规划、调度运营、电力市场产生了重大影响。规划中如何综合考虑海量运行场景与多元化要素,运营中如何高效调度多样灵活性资源,市场如何设计机制激励主体提供灵活性,都是新型电力系统建设亟待解决的问题。该文从电力规划、调度运营、电力市场3个层面出发,对近年来新型电力系统中规划运营与电力市场的相关研究进展进行系统梳理,涵盖基础理论、机制设计、应用研究、系统研发等多类型研究文献。进一步从规划、调度、市场3个方面展望未来研究趋势,如新型要素接入下的电网韧性、电碳耦合调度理论与高效求解技术、辅助服务与容量市场交易品类、考虑储能等新型主体的市场交易机制等,以期为我国新型电力系统的建设提供有益参考。

某纯电驱动重载车辆能耗预测模型

高精度能耗预测模型是准确预测车辆续驶里程的重要前提。针对载荷大幅度变化且非结构化道路运行的纯电驱动重载车辆,建立其组合能耗模型,该模型由能耗计算基本模型与长短时记忆(Long Short-Term Memory,LSTM)神经网络差值修正两部分组成。基于能量流动过程驱动电机和变速器效率建模,结合汽车行驶动力学建立能耗计算基本模型;采用LSTM神经网络来修正基本模型能耗预测结果与车辆典型工况功率测试值的差值,有效提高了大幅变载荷且低信噪比坡度环境下的车辆能耗预测精度,因此组合能耗模型具有参数简单和模型拟合不需解释能耗规律的优点。经试验测试分析,与VT-Micro能耗模型和径向基(Radial Basis Function,RBF)神经网络能耗模型相比,所提组合能耗模型的功率预测平均误差率分别降低了17.76%和3.35%,能够实现纯电驱动重载车辆复杂工况下能耗的准确实时预测。

Koopman原理内嵌MLP神经网络模型驱动的电力系统非线性振荡特征分析方法

针对电力系统非线性动态特性表征与物理机理融合不清晰、精度低的问题,提出了一种Koopman原理内嵌多层感知机(MLP)神经网络模型驱动的电力系统非线性特性表征与分析方法。阐明了Koopman算子的基本原理,分析了Koopman算子在非线性系统时序演化中的作用。采用MLP神经网络构建编码、解码映射,进而形成Koopman原理内嵌的神经网络深度学习模型,通过深度学习实现非线性系统“编码映射-线性演化-解码映射”3种结构的演化逼近。分析了将所提方法应用于电力系统动态特性分析的物理机理,建立了所提方法的求解与应用流程。通过单机与4机系统算例对所提方法进行对比验证,结果表明所提方法可以精确表征平衡点稳定域内的系统动态过程,可用于电力系统非线性振荡动态特性解析。

考虑电力-交通耦合网动态协调的EV集群灵活性挖掘与优化调度

电动汽车(EV)作为兼具交通与能量双重属性的跨域主体,发挥其时空灵活性将助力电力-交通耦合网的协调运行。为此,文中考虑电力-交通耦合网综合效益,提出了EV集群调控策略。首先,基于弧阻抗函数构建了动态交通网络加载模型。其次,考虑EV用户的各特征参数存在的差异性与耦合性,构建了单体EV灵活运行域模型,并采用基于zonotope线性近似的闵可夫斯基和算法对其聚合,得到EV集群的时变灵活运行域。在此基础上,提出了动态交通流最优分配下EV集群灵活性调控的双层模型,迭代求解得到上下两层耦合变量构成的瞬时单位流量出行成本,从而引导EV的出行与充放电行为。最后,通过与最短路径引导策略进行比较,验证了所提EV集群调控策略的有效性。

Overview of condition monitoring and operation control of electric power conversion systems in direct-drive wind turbines under faults

Electric power conversion system （EPCS）, which consists of a generator and power converter, is one of the most important subsystems in a direct-drive wind turbine （DD-WT）. However, this component accounts for the most failures （approximately 60% of the total number） in the entire DD-WT system according to statistical data. To improve the reliability of EPCSs and reduce the operation and maintenance cost of DD-WTs, numerous researchers have studied condition monitoring （CM） and fault diagnostics （FD）. Numerous CM and FD techniques, which have respective advantages and disadvantages, have emerged. This paper provides an overview of the CM, FD, and operation control of EPCSs in DD-WTs under faults. After introducing the functional principle and structure of EPCS, this survey discusses the common failures in wind generators and power converters; briefly reviewed CM and FD methods and operation control of these generators and power converters under faults; and discussed the grid voltage faults related to EPCSs in DD-WTs. These theories and their related technical concepts are systematically discussed. Finally, predicted development trends are presented. The paper provides a valuable reference for developing service quality evaluation methods and fault operation control systems to achieve high-performance and high-intelligence DD-WTs.

考虑灵活爬坡产品的虚拟电厂两阶段分布鲁棒优化运营策略

随着“碳达峰·碳中和”目标的提出,可再生能源大规模并网对电力系统灵活运行提出了更高要求。虚拟电厂(VPP)通过聚合分布式资源,将灵活爬坡产品(FRP)纳入运营策略,参与多类型电力市场以提升运营收益。基于此,提出了考虑FRP的VPP两阶段分布鲁棒优化(DRO)运营策略。首先,考虑高比例可再生能源渗透率下的FRP市场,结合多类型分布式资源运行特性,提出VPP参与多类型电力市场的优化运营框架;其次,结合基于Wasserstein距离的可再生能源出力不确定集和基于场景分析法的电力市场价格典型场景集,构建考虑FRP的VPP日前投标和日内调度两阶段DRO模型;最后,以某VPP为例对所提模型进行有效性验证。算例结果表明,所提VPP运营策略具有较好的调度经济性与风险鲁棒性,在参与多类型电力市场交易中能够实现运营收益最大化。

基于事件建模的机组检修模型及其在电力系统中长期运行中的应用

发电机组检修计划是电力系统中长期运行的重要内容,对于维护设备安全运行、保障高比例新能源电力系统中长期电力电量平衡十分重要。由于检修持续时间、检修间隔时间等检修约束较为复杂,机组检修在建模中存在模型整数变量与约束条件数目多的难题,这增加了电力系统中长期运行的问题规模与求解难度。针对以上问题,该文提出基于事件建模的机组检修模型,能够用较少的变量完整地描述机组检修约束。在此基础上,计及机组检修约束、机组运行约束和系统运行约束,建立电力系统中长期运行模型。基于改编的IEEE-RTS79开展算例分析,验证提出的机组检修模型在电力系统中长期运行问题中的有效性,不仅求解效率提高,而且优化结果更好。

空间高温区自由活塞斯特林发电机工作特性试验研究

测试了不同冷端温度下,外负载、运行压力和加热功率对高温区自由活塞斯特林发电机的热端温度、电电效率、输出功率、频率的影响。研究结果表明,在同一冷端温度时,加热功率的增加使发电机的电电效率、输出功率、热端温度上升,而外负载、运行压力的增加则起相反作用;发电机的频率与外负载呈负相关变化,与运行压力、加热功率呈正相关变化。提升冷端温度使发电机的输出功率、电电效率和频率下降,热端温度上升。在三种不同冷端温度下,外负载、加热功率和运行压力对发电机输出特性的影响规律不变。经过测试,发电机在运行温区为495~1058 K时,最大输出功率103.681 W,电电效率20.5%。

交通网络和电力网络融合承载力的研究综述

电动汽车作为交通电气化的核心,对减少温室气体排放和提高能源效率起到了积极的作用。显著增长的电动汽车保有量和市场占比对充电基础设施产生了一定的影响,如充电设施不足和电网负荷波动等问题凸显。本文深入梳理了交通网络承载力和电力网络承载力的基本概念、计算方法和评估指标,分析了交通与能源网络两网评估方法与两网融合韧性,并探讨了交通-电力融合系统潜在的挑战与策略;揭示出目前亟待开展的研究领域并指出了未来的研究方向,以期提高充电设施效率,缓解交通拥堵,保障电网稳定运行。

基于循环神经网络的异常用电数据检测方法

针对用电数据检测时受电量敏感度的影响,导致异常数据检测时电能消耗过量的问题,提出了基于循环神经网络的异常用电数据检测方法。在循环神经网络体系中,根据窃电系数指标求解结果,计算电量压差的实际数值,实现对异常用电数据特征的提取。构建异常数据样本集合,通过填充缺失数据的处理方式,推断检测评价指标所属区间范围,完成基于循环神经网络的异常用电数据检测方法的设计。对比实验结果:循环神经网络作用下,由异常用电数据造成的电能消耗量最高为3.2×10^(8)kW·h,不会引发明显的电能过量消耗问题,符合维护电网运行稳定性的实际应用需求。

电力通信网络智能运维故障诊断系统研究

当前,电力通信网络需要进一步提高对网络节点的感知能力,从而加快网络的故障运维效率。设计了智能运维故障诊断系统,以监测网络中节点状态、实时感知网络节点的运行参数,并实现故障诊断输出运维策略。系统的网络感知模块中加入了扩频调制技术,使模块能够感知到更大范围内的网络节点状态,提高了模块的通信范围和抗干扰能力。故障诊断模型中融合了生成对抗网络和决策树算法,通过各网络故障数据的拟合得到大量可靠数据集,输入最优特征组合以完成故障检测。试验结果显示,系统故障诊断模型的故障诊断率最高为99.8%,损失值最低为0.03。该研究确保了自动化诊断和检测的精确性。

基于胶囊网络的异常多分类模型

国网公司日益庞大的服务器集群产生的大量生产运行数据,以及实时分析各类设备、系统产生的海量监控数据成为电力IT运维工作的新挑战。异常检测技术作为智能电网信息运维工作的关键技术,可以有效检测运维故障并及时告警,避免损坏敏感设备。目前一些传统异常检测方法检测的异常种类少且精度低,导致故障发现不及时。为了应对这一挑战,提出了基于胶囊网络的多维时间序列异常多分类模型NNCapsNet。首先,应用无监督算法结合专家知识对电网营销业务应用服务器性能监控数据进行预处理和标注。其次,引入胶囊网络进行分类和异常检测。五折交叉验证的实验结果表明,NNCapsNet在包含15类异常的数据集上实现了91.21%的平均分类准确度。还在包含2万条监控数据的数据集上与4个基准模型进行了对比,NNCapsNet在关键评估指标上均取得了较好的结果。