考虑预测不确定性的微电网实时控制策略研究

风能、光伏等可再生能源的高比例并网成为了缓解全球能源危机的一项重要措施。然而,可再生能源实时出力中的间歇性和波动性给系统的安全性带来了一定的挑战。为了在提高可再生能源利用率的同时保证系统安全性,提出了一种基于深度强化学习(DRL)算法的运行优化实时调度模型。首先,构建了负荷预测模型实现负荷预测和高斯混合模型拟合预测误差;其次,考虑系统各节点的约束条件,以系统运行成本和安全运行作为优化目标,建立相应优化模型;然后,将优化问题转化为马尔可夫决策过程,并采用双延迟深度确定性策略梯度算法求解;最后,利用DRL算法的环境交互机制和策略自由探索,获得联合调度策略的最优结果。实验结果表明,所提方法具有良好的适应性,并且可以进行在线实时调度。     

Artificial intelligence for operation and control: The case of microgrids

Research on artificial intelligence (AI) has advanced significantly in recent years. A variety of AI algorithms have shown great promise in a large number of applications for power system operation and control. This article examines the potential of applying AI in microgrids (MGs). Specifically, as MGs commonly employ onsite generation including an increasing penetration of non-dispatchable distributed energy resources (DERs) and require seamless transition between operation modes (e.g., grid-connected and island) for different operation scenarios, the energy management within an MG is particularly complicated. Many factors including lack of inertia needed for system stability, generation uncertainty from DERs, and complex MG network topology composition (e.g., AC, DC, and hybrid AC/DC MGs) contribute to the difficulty of microgrid energy management. AI techniques such as deep learning (DL) and deep reinforcement learning (DRL) have recently demonstrated their excellence in tackling problems pertinent to decision making, providing a possible solution to overcome the above-mentioned challenges. This article discusses the applications of AI to MG operation and control, with an emphasis on DL and DRL. We survey the available DL and DRL technologies and their applications to power grids. We also investigate the unique issues associated with MGs including their layered control architecture, single vs. networked structure, and topology optimization. Perspectives on the ongoing challenges and viable AI solutions to MG operation and control are presented.     

具有限定功率运行的永磁直驱风力发电并网控制设计

当风力发电或光伏电站这些间歇式可再生能源因外界环境影响而出力过高时,会使得配网系统潮流发生变化,并网处电压会超出运行的安全限值范围。为使系统处于可控范围,可对这些能源进行实时容量限制。对直驱式永磁同步风力发电系统的控制策略进行了研究,分析了风机输出功率曲线,设计了最大风能跟踪和限定功率运行输出的控制方法和系统后级逆变并网控制方法,使得风力发电系统具有最大功率跟踪或限定功率运行、并网有功/无功功率独立控制等功能。最后建立了风力发电并网系统仿真模型,仿真结果对所设计控制策略进行了验证。     

基于深度强化学习的电网自主控制与决策技术

高比例可再生能源和电力电子设备渗透率的不断增加给电力系统运行与调控带来诸多挑战。本文基于深度强化学习技术（深度确定策略梯度, DDPG）提出了具有在线学习功能的电网自主优化控制与决策框架，即“电网脑”系统；通过不断的学习和经验累积，AI智能体可以在亚秒级时间内根据实时量测数据给出调控指令及预期效果。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。本文以电网电压和联络线潮流控制为例，从多方面详细介绍了自主调控的方法，包括问题描述、控制目标和样本设定、奖惩机制定义、状态空间和控制动作集定义、算法实现流程等。大量的数值仿真实验验证了所提方法强大的学习能力以及应用于电力系统自主控制与决策的可行性。     

基于ACPI的风力发电系统MPPT控制方法

针对直驱永磁同步风力发电系统存在非线性、参数不确定性以及转矩扰动等问题,研究了一种基于自耦PI控制理论的最大功率跟踪控制方法。该方法以转速跟踪为目标,将发电机内部动态与外部输入转矩的不确定性定义为一个总和扰动,从而将非线性不确定系统映射为未知线性系统,并构建了一个在总和扰动反相激励下的受控误差系统。据此设计了基于误差速度因子的自耦PI控制器模型,理论分析了自耦PI闭环控制系统的鲁棒稳定性和抗扰鲁棒性。仿真结果表明了该控制方法能稳定保持最大功率系数,在风力发电系统的最大功率跟踪领域具有良好的应用前景。     

分频风力发电系统最优功率输出控制

对变速变频(VSVF)运行的分频异步风力发电系统进行无风速检测的最优功率输出控制策略进行了研究.将转子磁链定向的矢量控制技术应用于异步风力发电机,通过控制异步风力发电机电磁转矩来调节风力发电机组的转子转速,控制风力机组的风能利用系数;在PSCAD/EMTDC中建立了分频异步风力发电系统的模型,计及了尾流效应:并对最优风能捕获和最优功率输出这2种控制策略进行对比分析.通过仿真算例进行了验证,结果表明,在自然风速波动的情况下,采用最优输出功率控制,可以有效地减小风力发电机组转轴机械应力以及输出功率的波动,提高输出功率的质量.     

级联式光伏电站直流并网拓扑及其控制策略

为解决光伏电站远距离输送并网问题,同时提高光伏电站并网系统稳定性,将光伏电站与电压源型高压直流(Voltage Source Converter-High Voltage Direct Current,VSC-HVDC)输电系统相结合,设计了一种光伏电站通过级联直流变换器经VSC-HVDC输电线路并网拓扑方案。研究了光伏发电模块均压特性,分析了光伏发电模块控制策略和VSC换流站直流电压控制策略,提出了改进的直流电压-功率偏差斜率控制策略。在PSCAD/EMDTC电磁暂态软件下进行了不同光照强度仿真分析。仿真结果验证了系统可行性,表明了所提出控制策略有效保持光伏电站系统电压稳定性。     

大规模风光互补发电系统建模与运行特性研究

建立了大规模并网风光互补发电系统动态分析模型,提出了基于功率变化率改进扰动观察最大功率跟踪算法。风电及光伏系统均采用有功、无功解耦双环电流控制策略。应用静止同步补偿器分析模型的暂态故障电压。含风电、光伏及风光互补运行的电力系统仿真计算验证了该模型的有效性及其功率波动特性和母线电压的暂态影响。仿真结果表明,该风光互补发电系统模型有效降低了输出功率波动,实现了风光系统低电压穿越,确保故障情况下风光系统不脱网运行以及电网安全稳定运行。     

大规模风光接入下梯级水电站调度方式研究

风光接入流域梯级水电系统联合打捆外送是解决新能源消纳难题的有效途径,但也使得传统面向单一水电系统的调度方式面临极大挑战。为此,本文系统研究大规模风光接入背景下梯级水电站在长期、日前和实时尺度上的调度方式,并以雅砻江流域锦官梯级多能互补调度为实例,系统评估互补调度效益和风险。结果表明：大规模风光接入背景下,大型水电站水库的中长期水位应提前并加深消落,以增加枯期发电量并减少汛期弃水;互补运行能提升系统调峰能力,且调节水电日出力过程可缓解外送通道竞争;充分发挥梯级水电站的联合调度作用,能分别在日前和实时尺度上对风光功率进行电力补偿调节,弥补风光预测不确定性导致的发电偏差,提高供电可靠性。     

基于超扭曲优化算法的风机最大功率跟踪控制

针对风力发电系统在低风速区采用传统控制方法具有风能转换效率较低、风轮转速跟踪实时风速的性能较差、发电机转矩波动范围较大等问题,提出了一种将超扭曲算法与最佳转矩法相结合的最大功率跟踪改进控制策略。为进一步改善控制性能,采用粒子群算法对控制器参数进行优化。最后以风轮角速度、发电机输出功率、发电机转矩、功率系数等为评价指标,通过Matlab/Simulink平台验证所提方法的可行性与有效性。仿真结果表明,所提控制策略在提高最大风能捕捉能力的同时可有效地抑制发电机转矩的抖振。     

光伏电站直流汇集接入系统的建模分析

与传统的光伏交流接入系统相比,光伏直流汇集接入系统具有控制方式简单、系统损耗较小、光伏利用率高的特点。以某市一光伏直流汇集接入系统为例,给出光伏直流汇集接入系统的拓扑结构;构建光伏电池、多模块Boost全桥隔离变流器(BFBIC)及箝位双子模块型模块化多电平变流器(CDSM-MMC)的PSCAD模型。提出光伏变流站的2种控制策略,通过仿真对比分析2种控制策略的抗光照干扰能力及光伏发电电能输送能力,并给出控制策略的使用建议。     

Comparative evaluation of different power management strategies of a stand-alone PV/Wind/PEMFC hybrid power system

This study presents different power management strategies of a stand-alone hybrid power system. The system consists of three power generation systems, photovoltaic (PV) panels, a wind turbine and a proton exchange membrane fuel cell (PEMFC). PV and wind turbine is the main supply for the system, and the fuel cell performs as a backup power source. Therefore, continuous energy supply needs energy storing devices. In this proposed hybrid system, gel batteries are used. The state of charge (SOC), charge-discharge currents are affecting the battery energy efficiency. In this study, the battery energy efficiency is evaluated with three different power management strategies. The control algorithm is using Matlab-Simulink®.     

基于功率预测的变速变桨距风电系统的优化控制

为了增强风电场主动融入大电网的能力,基于风速和功率的超短期提前一步预测,以最大风能捕获和输出功率平滑为优化目标,以发电机转速和桨矩角为控制变量,为了有效地减少桨矩角系统和机械系统的压力,制定了最小化控制标准,建立了相应的多目标优化模型。运用遗传算法求解出模型的优化解,将该优化解作用于风力发电机组来优化系统的性能。通过对1.5 MW的变速恒频风力发电系统进行仿真研究表明,与传统的最大功率追踪控制相比较,所提出的控制策略提高了发电机输出功率,同时抑制了输出功率的低频波动。     

风储联合并网发电系统建模与运行控制

针对并网风力发电的随机波动,在风电场配置规模化电池储能系统,采用结构简单且控制性能良好的永磁同步风电机组,构建风储联合并网发电系统模型并实现其运行控制。基于最大功率捕获和有功无功解耦控制设计风力发电机组的控制系统,釆用定周期比控制策略和反馈线性化理论实现电池储能系统的功率传输控制。在PSCAD/EMTDC仿真软件中搭建了风储联合发电系统仿真模型,结果表明,釆用定周期比控制策略和反馈线性化理论设计电池储能单元可以快速跟踪参考控制指令,实现对风电功率波动的平抑,进而验证了所提出风储联合并网发电系统模型和控制系统的有效性。     

计及多约束条件的风光互补容量配比研究

为了提高可再生能源利用效率以及土地资源利用率,研究了风电和光伏同场互补共建的容量匹配问题。分析影响光伏增建容量的相关因素,在此基础上建立了反映风电与光伏同场共建互补发电效益与相关约束的指标,并给出增建光伏容量的计算方法及流程。所提方法计及了风光互补发电特性、功率外送限制等运行约束,同时也考虑了光照强度、已建风场设施遮挡阴影等因素对增建光伏容量的影响,方法具有较强的工程实用性。以甘肃某实际风场为例,运用Sunlight和PVsyst仿真软件进行测算,并对风电光伏同场发电的经济效益和相关指标进行分析。仿真结果验证了所提配置方法的合理性和实用性。     

计及光伏出力不确定性的氢能综合能源系统经济运行策略

针对分布式光伏出力的不确定性特征对系统运行经济性的影响,提出了一种计及光伏出力不确定性的氢能综合能源系统经济运行策略.首先,搭建氢燃料电池的热电输出控制模型和氢能综合能源系统的热力系统模型;然后,在光伏出力预测数据的基础上,通过分析光照强度变化的不确定性以修正光伏出力预测曲线;最后,以最小化系统日运行成本为目标函数,建立包含光伏、氢燃料电池、热电联产机组的氢能综合能源系统的运行优化模型.算例分析结果表明,考虑光伏出力不确定性对氢燃料电池输出的影响,可使系统设备的出力更加合理,对降低运行成本、提高氢能综合能源系统的运行可靠性具有积极作用.     

考虑频率安全约束及风电综合惯性控制的电力系统机组组合

随着风电渗透率上升,电力系统惯性响应和一次调频能力下降,频率安全问题凸显,有必要在机组日前发电计划安排中考虑频率安全约束。依据电力系统频率安全要求,提出了考虑频率跌落最低值的频率安全约束构造方法。同时引入风电综合惯性控制使风电机组参与一次调频,在此基础上建立了考虑频率安全约束及风电综合惯性控制的机组组合模型。运用M语言动态控制多机频率响应模型进行Simulink仿真,并将其嵌入到改进粒子群优化算法中迭代求解。含风电的IEEE39节点系统算例结果表明,所提模型和方法能有效提升系统频率响应能力,保证系统安全运行。     

Energy storage system-based power control for grid-connected wind power farm

Wind power is characterized as intermittent with stochastic fluctuations, which can result in deviation of grid frequency and voltage when the wind power ratio is high enough. These effects have a definite impact on stability and power quality of grid operation. This paper proposes an energy storage system (ESS) based power control for a grid-connected wind power system to improve power quality and stability of the power system. Vanadium redox flow battery (VRB), as an environmentally-friendly battery provided with many advantages, is employed in the ESS. A dynamic mathematical model of VRB is built by using an equivalent circuit, and its charging and discharging characteristics are analyzed. The VRB’s stable voltage is available in a wide range (around 20–80% state of charge), which is suitable for utilization of a single-stage AC/DC converter in the VRB-based ESS. With a proposed energy storage control method, VRB-based ESS is added at the exit of the grid-connected wind farm to filter fluctuations of wind power, which ensures that smooth power will be injected into the grid and which improves power quality of the power system. Simulations and experiments are carried out to verify the proposed power control method for these grid-connected wind power systems. The grid-connected wind farm with VRB-based ESS, wind speed (characterized as gust and stochastic wind), and wind turbines are modeled in simulations. Simulation results show that the grid-injected active power from the wind farm is effectively smoothed, and reactive power support can be provided for the grid by the designed VRB-based ESS. Experimental verification is achieved with a low power bench, where a RT-LAB real-time simulation platform and a direct torque controlled induction motor simulate a real wind turbine and a wind speed model is built in the RT-LAB real-time simulation platform. The experimental results verify the proposed scheme through demonstrating a stable and smooth power flow injected into the grid though the wind power fluctuated.     

Evaluation of Power Surpluses and Shortfalls Due to Error in Forecasting of Photovoltaic Generation Output

The 2011 Tohoku earthquake had a great impact on Japanese energy policy. It is expected that nuclear power plants will be phased out and a large amount of generation from renewable energy sources will be installed. Attention is particularly focused on photovoltaic (PV) generation, technology in which Japan is superior, and a high price is set in the feed‐in tariff policy, which started in 2012. However, large integration of PV into power grids may cause imbalances between power supply and demand. It will be indispensable to use PV power generation forecasts in economic‐load dispatching control (EDC), so that the economics and reliability of power systems networks can be maintained. Thus, in the previous study, we proposed an EDC method with unit commitment (UC) based on the results provided by a day‐ahead PV forecast. In this study, we evaluate the frequency and trend of shortfalls and surpluses of power due to error in forecasting PV power generation by numerical simulations using the power system model of the Kanto area in Japan. The results showed that shortfalls or surplus power occur not only due to overestimations or underestimations of PV power, but also due to the operating conditions of the power systems.     

边远通信基站风光互补发电协调控制系统

文章根据边远地区通信基站的供电特点,结合风光互补发电技术,提出一套适用于边远通信基站的风光互补发电协调控制系统方案。该方案介绍了风光互补发电协调控制系统的组成结构,以及围绕蓄电池的有效充放电和正常运行而开展的协调控制策略。该协调控制系统在保障边远通信基站安全、高效地利用风光互补发电的同时,也为边远地区各类无法接入市电的电力用户合理利用风光互补发电提供了借鉴。