Framework and Key Technologies of Human-machine Hybrid-augmented Intelligence System for Large-scale Power Grid Dispatching and Control

With integration of large-scale renewable energy,new controllable devices,and required reinforcement of power grids,modern power systems have typical characteristics such as uncertainty,vulnerability and openness,which makes operation and control of power grids face severe security challenges.Application of artificial intelligence(AI)technologies represented by machine learning in power grid regulation is limited by reliability,interpretability and generalization ability of complex modeling.Mode of hybrid-augmented intelligence(HAI)based on human-machine collaboration(HMC)is a pivotal direction for future development of AI technology in this field.Based on characteristics of applications in power grid regulation,this paper discusses system architecture and key technologies of human-machine hybrid-augmented intelligence(HHI)system for large-scale power grid dispatching and control(PGDC).First,theory and application scenarios of HHI are introduced and analyzed;then physical and functional architectures of HHI system and human-machine collaborative regulation process are proposed.Key technologies are discussed to achieve a thorough integration of human/machine intelligence.Finally,state-of-theart and future development of HHI in power grid regulation are summarized,aiming to efficiently improve the intelligent level of power grid regulation in a human-machine interactive and collaborative way.

Large-Scale Distributed Photovoltaic Power Dispatching and Operation Management Review

Distributed photovoltaic power (PV) is the main development model of distributed generation. It is necessary to research on dispatching and operation management with large-scale distributed PV connected. This paper analyzes development status, technical requirement and dispatching and operation management situation of distributed PV in Germany and China. Then introduce the preparation of distributed PV dispatching and operation management criterion. Through summarizing the experiences and lessons of large-scale distributed PV development in Germany, it gives advice to the development of distributed PV dispatching and operation management in China.

Difference between grid connections of large-scale wind power and conventional synchronous generation

In China, regions with abundant wind energy resources are generally located at the end of power grids. The power grid architecture in these regions is typically not sufficiently strong, and the energy structure is relatively simple. Thus, connecting large-capacity wind power units complicates the peak load regulation and stable operation of the power grids in these regions. Most wind turbines use power electronic converter technology, which affects the safety and stability of the power grid differently compared with conventional synchronous generators. Furthermore, fluctuations in wind power cause fluctuations in the output of wind farms, making it difficult to create and implement suitable power generation plans for wind farms. The generation technology and grid connection scheme for wind power and conventional thermal power generation differ considerably. Moreover, the active and reactive power control abilities of wind turbines are weaker than those of thermal power units, necessitating additional equipment to control wind turbines. Hence, to address the aforementioned issues with large-scale wind power generation, this study analyzes the differences between the grid connection and collection strategies for wind power bases and thermal power plants. Based on this analysis, the differences in the power control modes of wind power and thermal power are further investigated. Finally, the stability of different control modes is analyzed through simulation. The findings can be beneficial for the planning and development of large-scale wind power generation farms.

Operating Analysis and Data Mining System for Power Grid Dispatching

The dispatching center of power-grid companies is also the data center of the power grid where gathers great amount of operating information. The valuable information contained in these data means a lot for power grid operating management, but at present there is no special method for the management of operating data resource. This paper introduces the operating analysis and data mining system for power grid dispatching. The technique of data warehousing online analytical processing has been used to manage and analysis the great capacity of data. This analysis system is based on the real-time data of the power grid to dig out the potential rule of the power grid operating. This system also provides a research platform for the dispatchers, help to improve the JIT (Just in Time) management of power system.

Fundamental Research on Enhancing Operation Reliability for Large-Scale Interconnected Power Grids——An interview with Zhou Xiaoxin, chief scientist of "973 Program"

At the end of last year, the editors from Power and Electrical Engineers interviewed Zhou Xiaoxin on "Fundamental Research on Enhancing Operation Reliability for Large-Scale Interconnected Power Grids", a project of "973 Program". Mr. Zhou, the chief engineer of China Electric Power Research Institute(CEPRI) and an academician of Chinese Academy of Sciences, is the chief scientist in charge of this research project.

Forecasting-Based Adaptive Optimized Dispatch in Smart Grid Online

The power grid is a fusion of technologies in energy systems, and how to adjust and control the output power of each generator to balance the load of the grid is a crucial issue. As a platform, the smart grid is for the convenience of the implementation of adaptive control generators using advanced technologies. In this paper, we are introducing a new approach, the Central Lower Configuration Table, which optimizes dispatch of the generating capacity in a smart grid power system. The dispatch strategy of each generator in the grid is presented in the configuration table, and the scenario consists of two-level agents. A central agent optimizes dispatch calculation to get the configuration table, and a lower agent controls generators according to the tasks of the central level and the work states during generation. The central level is major optimization and adjustment. We used machine learning to predict the power load and address the best optimize cost function to deal with a different control strategy. We designed the items of the cost function, such as operations, maintenances and the effects on the environment. Then, according to the total cost, we got a new second-rank-sort table. As a result, we can resolve generator’s task based on the table, which can also be updated on-line based on the environmental situation. The signs of the driving generator’s controller include active power and system’s f. The lower control level agent carries out the generator control to track f along with the best optimized cost function. Our approach makes optimized dispatch algorithm more convenient to realize, and the numerical simulation indicates the strategy of machine learning forecast of optimized power dispatch is effective.

MicroGrid Designer:user-friendly design,operation and control assist tools for resilient microgrid and autonomous community

During this decade,many countries have experienced natural and accidental disasters,such as typhoons,floods,earthquakes,and nuclear plant accidents,causing catastrophic damage to infrastructures.Since the end of 2019,all countries of the world are struggling with the COVID-19 and pursuing countermeasures,including inoculation of vaccine,and changes in our lifestyle and social structures.All these experiences have made the residents in the affected regions keenly aware of the need for new infrastructures that are resilient and autonomous,so that vital lifelines are secured during calamities.A paradigm shift has been taking place toward reorganizing the energy social service management in many countries,including Japan,by effective use of sustainable energy and new supply schemes.However,such new power sources and supply schemes would affect the power grid through intermittency of power output and the deterioration of power quality and service.Therefore,new social infrastructures and novel management systems to supply energy and social service will be required.In this paper,user-friendly design,operation and control assist tools for resilient microgrids and autonomous communities are proposed and applied to the standard microgrid to verify its effectiveness and performance.

Smart Grid in CSG:Direction and Field

After describing the general situation of China Southern Power Grid (CSG), this article expounds the necessity for CSG to carry out the program of smart grid, and points out the favorable conditions and the key fields to develop smart grid. It also puts forward near-term emphases, and gives relevant suggestions.

基于动态掺氢策略的综合能源系统低碳经济调度

针对现有综合能源系统中传统碳捕集电厂灵活性较差,电负荷系数、管道长度和管道运维成本等因素对计及气网掺氢的综合能源系统调度的影响尚未明确等问题,提出了一种基于动态掺氢策略的综合能源系统低碳经济调度模型。首先,建立综合灵活碳捕集电厂模型,对二氧化碳的吸收与再生环节进行解耦;其次,建立基于动态掺氢的管道运维成本模型,实现掺氢比的动态调整,提高系统调度的灵活性;然后,引入阶梯式碳交易机制,构建考虑气网掺氢管道运维成本的综合能源系统低碳经济调度模型,利用McCormick松弛方法将非线性问题转化为线性问题,并进行求解。最后,算例仿真结果表明:气网各节点处管道运维成本系数与气体体积、输送距离等因素相关,应综合考虑上述因素对气体定价;在综合能源系统调度中综合考虑电负荷系数、气网管道长度等因素合理选择气网掺氢比上限、制定动态掺氢策略,系统的经济效益与环境效益分别提高了44.1%、47.8%。

台风灾害下提升电网韧性的实时优化调度策略

针对在台风灾害下输电线路停运可能引发的电网大停电事故,构建了提升电网韧性的实时优化调度策略。运用脆弱性曲线刻画风速与线路故障率关系,并考虑线路负载率对线路故障影响,获得台风灾害下的输电线路故障概率;通过蒙特卡罗抽样生成故障场景集,采用置信集法进行场景削减;在此基础上构建了综合考虑潮流均匀度、受灾区线路负载率和发电成本的多目标实时优化调度模型,将输电线路开断(Optimal Transmission Switching, OTS)引入到模型中以降低受台风灾害影响的线路数量。为提高优化调度模型求解的计算速度,采用Benders分解法进行求解。以IEEE 118节点系统为例进行仿真,验证了所提方法的有效性。

基于人工蜂群算法的配电网无功优化调度研究

为了改善现有无功功率调度时算法执行效率,解决模型易陷入局部极值问题,提出一种基于改进人工蜂群算法模型。在分析等式和不等式约束的情况下,建立最小化实际功率损耗、电压偏差和电压稳定增强的无功功率调度目标函数。提出一种基于邻域半径选择的改进人工蜂群算法,设计一种新的邻域选择机制和改进的搜索策略。实验阶段,以IEEE39总线电力系统为例,对所提算法有效性和执行效率进行验证。与线性规划(LP)、粒子群优化(PSO)算法和基础人工蜂群(ABC)算法相比,改进ABC算法比其他算法执行效率更优,且解的质量更高。该模型为配电网电力调度及稳定性运行的发展提供了一定借鉴作用。

基于层次分析法的电网调度操作效率评价

基于层次分析法的电网调度操作效率评价能够从多维度评价线路操作效率、主变操作效率、母线操作效率;基于停电、复电、检修工作、许可的准时率,能够给调度操作提供辅助决策分析功能,以实现电网精益化管理。

基于电网调度系统的网络安全态势感知方法研究

由于网络外界病毒入侵的隐蔽性极高、入侵类型较多,病毒难以被全面地被感知,导致电网调度自动化系统运行安全受到威胁。为提升电网调度自动化系统网络的安全性,提出基于随机矩阵理论(random matrix theory,RMT)的电网调度自动化系统网络安全态势感知技术。采集电网调度自动化系统网络安全信息数据,构建病毒入侵环境下的安全状态分布模型,并利用该模型完成电网调度系统网络安全态势特征信息的提取。采用RMT中的M-P模型及单环定律对网络安全态势特征值在随机矩阵内的分布情况进行谱分析,根据特征值分布状态获取网络安全态势在稳定情况及异常情况下的变换规律,实现电网调度系统网络安全态势感知。实验结果表明,通过对该方法开展安全态势感知测试,验证了该方法应用在电网调度系统中组件安全态势感知及网络安全态势感知的精准度均较高,体现了该方法的有效性。

大电网调控人机混合增强智能:概念内涵、应用框架、关键技术以及系统验证

伴随深度学习等人工智能技术的飞速发展,通过数字化赋能电力来实现电网的信息化、数字化和智能化成为未来新型电力系统发展的必然趋势。人工智能技术在电网调控应用研究广泛,但是实际应用过程中,由于电网不确定性、开放性和脆弱性造成的模型可信性和可解释性等问题,使得单纯的人工智能技术应用于电网调控领域难以满足安全可靠应用的需求。为了解决上述问题,需要引入人类的监督与互动,融合调控人员的智能与机器智能,实现电网调控人机智能的混合增强。该文首先介绍混合增强智能技术的概念和内涵以及在不同领域的研究现状。随后,针对电网调控业务特点,从人工智能和调控应用两个维度,提出电网调控人机混合增强智能的应用框架以及电网调控人机交互协同的目标和基本原则。在此基础上,分析和讨论电网调控人机混合增强智能所涉及的关键技术,并研发大电网调控人机混合紧急控制决策支持验证系统,用于省级规模电网的热稳调整、频率控制等多种电网调控场景应用验证,为人机混合增强智能技术在电网调控领域的应用提供参考和借鉴。

基于网络交互与智能规则的调度操作指挥模块

针对传统的手打拟票、手工记录以及电话下令的业务开展方式已成为操作效率提升的瓶颈,提出在调度指挥控制系统(dispatch command control system,DCCS)上设计调度操作指挥模块。将电话下令转变为网络交互;构建多种基于智能规则的自动成票手段,取代传统的手打出票方式;操作完成后系统可自动记录设备状态信息并通知相关单位,实现调度操作全流程的网络化、信息化与智能化。模块上线运行结果表明,数据显示对调度操作效率的提升作用显著。

考虑交通负荷时空需求及区域划分的配电网分布式经济调度策略

针对电动汽车与分布式电源高比例接入对配电网的安全经济运行所带来的挑战,以及传统集中式控制面临的通信压力大、数据隐私低等问题,提出一种考虑交通负荷时空需求的配电网分布式经济调度策略。首先,考虑不同交通区域的用户出行特性差异与实时交通信息影响,建立电动汽车充电负荷的时空分布预测模型;其次,在原有配电网的负荷特性基础上,考虑充电负荷的时空差异性,提出基于谱聚类的配电网区域划分方法;最后,提出基于交替方向乘子法的配电网分布式经济调度策略,实现经济调度模型的分布式解耦计算,并进一步提高经济调度模型的计算速度。算例表明,所提策略可降低12.76%的运行成本与59.45%的网络损耗,并提升系统的计算效率。

新型城市电网调控体系架构及关键技术

双碳目标下城市电网运行环境和形态出现新的特征,导致城市电网向新型城市电网(new urban power grid,NUPG)转变,仅依靠主网的调控模式难以满足其运行需求,亟须建立对应的NUPG调控体系架构。该文首先从系统论角度,论述新型电力系统出现的结构性矛盾,预判城市电网即将出现的新形态和新业态。在此基础上,分析NUPG的几种可能发展模式,构建初级发展模式下的NUPG调控体系架构,分析该架构对应的调控任务、调控对象和需要解决的主要基础性关键技术问题。最后,设计NUPG调控平台,可向下调控内部资源解决内部运行矛盾,向上分担主网调控压力辅助解决系统性问题,有效支撑新型电力系统运行。

面向多虚拟电厂的分层分区多层互补动态聚合调控策略

虚拟电厂(virtual power plant,VPP)是一种新型运行模式,通过有效聚合电网中大量需求侧资源并制定有效的动态聚合调控策略,实现电网不同时空的功率互补,提高电网调控的灵活性和系统的经济性。从电网调度角度分析了典型电网需求响应行为特性,提出了需求响应能力指标和虚拟电厂分类聚合方法,构建了多源虚拟电厂调控模型,以其结果支撑虚拟电厂响应资源的分层分区互补调控。最后,以某园区为案例,分析了虚拟电厂调控策略的合理性和多源虚拟电厂调控的科学性。结果表明,整体动态调控策略可以引导虚拟电厂科学合理地发挥需求响应价值,促进电网负荷平稳和系统安全稳定运行。

电网数字孪生分析模型建模及应用

为支撑新一代调度技术支持系统全局分析计算业务融合,提出一种基于数据孪生的电网分析模型构建方法。基于实际电网设备的物理和逻辑关系,构建出标准化、对象化的完整电网分析模型,并接入实时量测,使其成为真实空间物理电网的数字孪生。在传统通用数据库与专业计算应用间构建出更贴近电网分析计算业务的数据中台,为在线分析计算应用提供统一数据服务。通过在新一代调度支持系统华中试点工程的建设成效,展示了基于数字孪生模型的分析计算应用的性能提高效果。

欧洲大范围跨国电力互联在极端天气下电力安全保供中的作用分析

随着全球气候变化不断加剧,极端天气对电力系统的影响日益增强,电网在电力安全保供中发挥的作用愈发受到关注。欧洲电网作为世界上规模最大的跨国互联电网,其在极端天气下的电力安全保供中发挥的作用值得研究借鉴。首先,对欧洲电网跨国互联进程、跨国电力配置、跨国互联目的进行梳理,并从电力交易与调度的关系、跨国电网耦合机制、跨国输电通道容量分配机制等角度分析欧洲跨国电网的交易与调度特征。其次,以2022年夏季极端高温干旱天气下的欧洲电力供应紧张事件为例,从电量余缺互济、平衡资源共享、统一电力市场支撑、可再生能源消纳等方面分析欧洲跨国互联电网在电力安全保供中发挥的“四个平台”作用。然后,对欧洲跨国互联电网面临的问题进行剖析。最后,提出对中国电网发展的思考及建议。