Jointly improving energy efficiency and smoothing power oscillations of integrated offshore wind and photovoltaic power: a deep reinforcement learning approach

This paper proposes a novel deep reinforcement learning (DRL) control strategy for an integrated ofshore wind and photovoltaic (PV) power system for improving power generation efciency while simultaneously damping oscillations. A variable-speed ofshore wind turbine (OWT) with electrical torque control is used in the integrated ofshore power system whose dynamic models are detailed. By considering the control system as a partially-observable Markov decision process, an actor-critic architecture model-free DRL algorithm, namely, deep deterministic policy gradient, is adopted and implemented to explore and learn the optimal multi-objective control policy. The potential and efectiveness of the integrated power system are evaluated. The results imply that an OWT can respond quickly to sudden changes of the infow wind conditions to maximize total power generation. Signifcant oscillations in the overall power output can also be well suppressed by regulating the generator torque, which further indicates that complementary operation of ofshore wind and PV power can be achieved.     

基于多分区自适应改进果蝇算法的风光燃储微电网协调控制策略

为了使微电网控制系统中PI控制器的参数能够更好地适应可再生能源的随机性和波动性,提出了基于自适应步长的四分区多策略果蝇优化算法(fruit fly optimization algorithm, FOA)对PI参数进行实时优化。首先,以风光燃储微电网不同微源控制系统中的变换器为控制对象,建立微电网整体控制系统模型,基于此模型实时调整PI参数。然后,根据不同果蝇个体的适应度值将果蝇种群分为4个区,同时考虑4个区果蝇收敛性以及多样性的差异,设计不同的自适应更新策略。最后,采用所提算法对各微源控制过程中的PI参数进行寻优,与其他3种智能算法进行对比,验证了所提算法的可行性和优越性。仿真结果表明,所提算法可以使系统变换器响应速度更快,输出更加稳定。     

Lateral WSe2 Homojunction through Metal Contact Doping: Excellent Self-powered Photovoltaic Photodetector

Here an IR-heating chemical vapor deposition (CVD) approach enabling fast 2D-growth of WSe₂ thin films is reported, and the great potential of metal contact doping in building CVD-grown WSe₂-based lateral homojunction is demonstrated by contacting with TiN/Ni metals in favor of holes/electrons injection. Shortening nanosheet channel to ≈2 µm leads to pronounced enhancement in the performance of diode. The fabricated WSe₂-based diode exhibits high rectification ratios without the need of gate modulation and can work efficiently as photovoltaic cell, with maximum open circuit voltage reaching up to 620 mV and a high power conversion efficiency over 15%, empowering it as superb self-powered photodetector for visible to near-infrared lights, with photoresponsivity over 0.5 A W⁻¹ and a fast photoresponse speed of 10 µs under 520 nm illumination. It is of practical significance to achieve well-performed photovoltaic devices with CVD-grown WSe₂ using fab-friendly metals and simple processing, which will help pave the way toward future mass production of optoelectronic chips.     

Evaluation of Grid-Connected Photovoltaic Plants Based on Clustering Methods

Photovoltaic (PV) systems are electric power systems designed to supply usable solar power by means of photovoltaics, which is the conversion of light into electricity using semiconducting materials. PV systems have gained much attention and are a very attractive energy resource nowadays. The substantial advantage of PV systems is the usage of the most abundant and free energy from the sun. PV systems play an important role in reducing feeder losses, improving voltage profiles and providing ancillary services to local loads. However, large PV grid-connected systems may have a destructive impact on the stability of the electric grid. This is due to the fluctuations of the output AC power generated from the PV systems according to the variations in the solar energy levels. Thus, the electrical distribution system with high penetration of PV systems is subject to performance degradation and instabilities. For that, this project attempts to enhance the integration process of PV systems into electrical grids by analyzing the impact of installing grid-connected PV plants. To accomplish this, an indicative representation of solar irradiation datasets is used for planning and power flow studies of the electric network prior to PV systems installation. Those datasets contain lengthy historical observations of solar energy data, that requires extensive analysis and simulations. To overcome that the lengthy historical datasets are reduced and clustered while preserving the original data characteristics. The resultant clusters can be utilized in the planning stage and simulation studies. Accordingly, studies related to PV systems integration into the electric grid are conducted in an efficient manner, avoiding computing resources and processing times with easier and practical implementation.     

基于准最小二乘法的光伏阵列模型鲁棒参数估计方法

光伏阵列的模型参数估计在光伏发电系统的仿真、输出功率预测、最大功率点跟踪等方面有重要意义。当测量数据中只含随机误差时,以加权最小二乘（WLS）为优化函数的参数估计方法有较好的辩识效果。但是当测量数据中含有显著误差时,WLS参数辩识的效果较差。为解决此问题,本文提出了一种以准加权最小二乘法（QWLS）为优化函数的参数估计方法来减小显著误差的影响,采用了赤池信息量准则(AIC)设计QWLS最优参数,将该方法应用于光伏阵列中构造模型鲁棒参数估计问题。最后将WLS和QWLS分别结合序列二次规划（SQP）算法,进行光伏阵列模型的参数估计仿真与实验测试。测试结果显示QWLS参数估计结果更准确,验证了准最小二乘法的鲁棒性与有效性。     

含氢储能的多源联合发电系统调度研究

风电和光伏发电具有间歇性和随机性,为了降低在多源联合发电系统中的弃风弃光率,采用含氢储能系统和火电机组配合来平滑风电和光电机组出力。文中以系统运行成本最小和弃电惩罚成本最小为目标,以系统功率平衡、火电机组出力和爬坡、热备用、风电和光电出力及储能系统储氢罐容量、电解槽和燃料电池功率等为约束条件构建了多源联合发电系统日前调度模型。通过YALMIP工具箱对模型进行编程,并调用CPLEX对编写的程序进行求解。对含有风电、光电、火电机组以及储能系统的多源联合发电系统进行算例分析,通过对比有无储能系统的弃风弃光量和系统总运行成本,证明了含氢储能系统可以有效降低系统的弃风弃光率,并提高系统的经济性。     

基于深度学习的航拍光伏板红外图像热斑检测方法研究

针对光伏电站光伏板热斑故障难以检测的问题,结合无人机巡检技术,提出一种基于深度卷积神经网络的光伏板热斑快速检测方法。首先设计了光伏板识别模型,将Yolov4主干特征提取网络替换成轻量级网络MobileNetV2,并将PAnet网络中标准3×3卷积替换为深度可分离卷积,实现了将光伏板快速从红外图像中识别出来。为快速识别热斑并解决光伏板反光噪声问题,将MobileNetV2网络引入DeeplabV3+模型中,改进由于下采样造成的目标缺失,并将交叉熵损失函数修改为Dice损失函数来进一步提高分割精度。试验结果表明,该方法能够准确识别光伏板热斑,光伏板识别准确率为99. 56%,检测速度为22. 1帧/秒。光伏板识别后的热斑分割准确度达到95. 99%,交并比mIou达到85. 58,检测速度为24. 5帧/秒,该方法能够满足光伏板故障检测的需要。     

含光伏电站的电力系统低频振荡广域阻尼协同控制方法

大规模新能源接入电网增加了弱阻尼振荡模式被激发的风险。首先,考虑同步发电机和光伏的动态特性,建立了详细的小信号模型,分析了光伏对低频振荡模式的影响,提出了含光伏电站的电力系统低频振荡广域阻尼控制架构,实现光伏-同步机协调阻尼控制;然后,以特征值分析结果为依据,提出了广域阻尼控制参数的优化模型,并对控制参数进行优化整定;最后,在PSCAD/EMTDC平台中搭建了含光伏电站的四机两区域系统电磁暂态仿真模型,验证了所提广域阻尼控制方法的有效性。     

基于BP神经网络与改进粒子群的光伏MPPT算法

针对光伏阵列在环境突变情况下尤其是局部阴影下的多峰值现象,提出一种基于反向传播(BP)神经网络与改进粒子群的最大功率点跟踪(MPPT)算法。该算法利用BP神经网络近似定位最大功率点,并利用对粒子群算法中的惯性权重值进行非线性动态优化后的改进粒子群精确定位最大功率点。仿真结果表明,复合算法可以更好地跟踪最大功率点,有效避免前期易陷入局部极值的问题,提高了精度,减小了功率振荡。     

光伏快速充电站配电变压器端电能质量综合控制研究

针对光伏快速充电站将光伏发电与电动汽车快速充电站有机结合,在充分发挥清洁能源优势和大量提升充电效率的同时所带来的电能质量扰动类型复杂、变化快速等问题,提出了一种基于串并联组合配电网柔性交流输电(distribution flexible AC transmission system, DFACTS)的新型电能质量补偿器的电能质量综合控制方法。深入研究了新型电能质量补偿器主电路拓扑,建立起了动态工作模型。详细分析了新型电能质量补偿器线性自抗扰控制方法的工作原理,设计出线性自抗扰控制器。并针对各DFACTS控制器间的交互影响,提出多DFACTS控制器的协调控制策略。最后搭建仿真模型,进行仿真验证。仿真结果表明,所提出的新型电能质量补偿器采用线性自抗扰控制方法相比传统PI控制方法,提高了电能质量扰动快速变化时的综合补偿能力和动态响应能力。并且验证了该协调控制能有效提高系统电压稳定能力,具有良好的可行性和有效性。