共查询到19条相似文献,搜索用时 182 毫秒
1.
2.
文章旨在研究电力系统的实时负荷预测和优化调度策略,采用时间序列和深度学习技术,提高调度效率和稳定性。实验证明,成功运用时间序列和深度学习实现准确的实时负荷预测,优化策略显著降低,提高了系统稳定性和可靠性。 相似文献
3.
4.
随着电动汽车并网容量的不断增加,面向电动汽车充电负荷准确地开展功率预测对于并网电力系统的经济调度和优化运行意义重大。基于计算机交叉学科的深度学习领域算法不断进步,为准确构建电动汽车充电负荷模型提供高效工具。该文研究一种基于LSTM(long short-term memory)神经网络的复合变量电动汽车充电负荷预测方法,将电动汽车充电负荷历史数据进行预处理,采用LSTM网络对降维后的时间序列进行动态建模,完成电动汽车充电负荷预测。采用实际数据进行验证,结果证明所提方法的有效性。 相似文献
5.
6.
针对可重入制造系统处于高度不确定性环境中,其产出时间序列的非线性特征,提出了基于遗传小波神经网络的产出短期预测方法,使预测模型具有小波的优良逼近性质和神经网络的自学习自适应性质,同时,采用遗传算法训练神经网络参数,利用遗传算法隐含并行性和全局搜索性的特征,丰富优化过程中的搜索行为,增强全局和局部意义下的搜索能力和效率。通过半导体生产线实例,进行了验证,结果表明所提出的基于遗传小波神经网络的产出短期预测方法的预测性能要优于传统BP神经网络算法。 相似文献
7.
时间序列是一种广泛应用于电量预测、汇率预测、太阳能发电量预测等各种领域的数据,预测其变化具有重要的意义.与LSTM相结合的编码器-解码器被广泛应用于多元时间序列预测.由于编码器只能将信息编码成固定长度的向量,因此模型的性能随着输入序列或输出序列长度的增加而迅速下降.为此,提出了基于编解码结构与线性回归的组合模型(AR CLSTM),该模型使用基于时间步的注意力机制使解码器能够自适应选择过去的隐藏状态并提取有用的信息,并利用卷积的结构学习多元时间序列不同维度之间的内在联系,同时结合了传统的线性自回归方法来学习时间序列的线性关系,从而实现在编解码结构上进一步降低时间序列预测的误差,改善多元时间序列的预测效果.实验结果表明,AR_CLSTM模型在不同的时间序列预测上表现良好,其均方根误差、均方误差、平均绝对误差均下降显著. 相似文献
8.
《测试科学与仪器》2021,(3)
时间序列是一种广泛应用于电量预测、汇率预测、太阳能发电量预测等各种领域的数据,预测其变化具有重要的意义。与LSTM相结合的编码器-解码器被广泛应用于多元时间序列预测。由于编码器只能将信息编码成固定长度的向量,因此模型的性能随着输入序列或输出序列长度的增加而迅速下降。为此,提出了基于编解码结构与线性回归的组合模型(AR_CLSTM),该模型使用基于时间步的注意力机制使解码器能够自适应选择过去的隐藏状态并提取有用的信息,并利用卷积的结构学习多元时间序列不同维度之间的内在联系,同时结合了传统的线性自回归方法来学习时间序列的线性关系,从而实现在编解码结构上进一步降低时间序列预测的误差,改善多元时间序列的预测效果。实验结果表明,AR_CLSTM模型在不同的时间序列预测上表现良好,其均方根误差、均方误差、平均绝对误差均下降显著。 相似文献
9.
随着越来越多的新能源发电并入微电网,单一储能技术已无法满足微电网对自身频率稳定性的要求。这时需要采用多元混合储能技术来改善微电网的频率稳定性。该文主要研究了微电网孤岛运行时,通过在交流母线处配置蓄电池和超级电容器两种储能装置,并且协调控制这两种储能装置的运行,来使微电网在风速扰动时系统频率能够快速地恢复稳定。通过对仿真结果的分析及比较,验证了所提出的混合储能方案对微电网孤岛运行时频率稳定性的改善作用优于单一储能方案。 相似文献
10.
11.
With increasing penetration of variable loads and intermittent distributed energy resources (DERs) with uncertainty and variability in distribution systems, the power system gradually inherits some features (e.g., lack of rotating inertia), which leads to the voltage instability in microgrids. As a means to provide stability support for smart grid against high penetration of intermittent DERs, inverter-based smart loads across the distribution grid has been suggested recently. Accordingly, this paper presents a delay-tolerant distributed voltage control scheme based on consensus protocol for multiple-cooperative smart loads through effective demand-side management in ac microgrids, in which the time-delay effect on transmission communication occurred in information exchanges is considered. The proposed distributed voltage control scheme always enables the output voltage of each smart load to be synchronized to their reference value, which improves the robustness of system stability against transmission communication delays. The Lyapunov–Krasovskii functions are employed to analyze the stability of our proposed distributed control scheme, then the delay-independent stability conditions are derived, which allows some large communication delays. Moreover, the sensitivity analysis is developed to show how the time delay affects system dynamics in order to validate the robustness of proposed delay-independent stability conditions. Furthermore, a sparse communication network is employed to implement the proposed distributed control protocols, which thus satisfies the plug-and-play requirement of smart microgrids. Finally, the simulation results of an ac microgrid in MATLAB/SimPowerSystems are presented to demonstrate the effectiveness of the proposed control methodology. 相似文献
12.
区域微电网群两级能量调度策略优化研究 总被引:2,自引:0,他引:2
针对现阶段微电网能量管理技术发展趋势,在满足其内部经济调度的基础上,还需要关注微电网间的能量互补机制。对并网型区域微电网群提出了一种两级能量优化调度模型。引入条件风险指标(CVaR)衡量可再生能源与负荷预测误差对调度方案造成的影响,结合微电网运行收益,作为微电网内部能量调度的优化目标;采用多目标粒子群优化算法(MOPSO)进行求解,研究收益风险比作为优化调度策略的筛选指标,提出微电网内部能量优化调度策略;以区域微电网群公共并网点有功功率梯度变化最小化为前提,获得最佳微电网净功率组合方案,由此平抑微电网群对配电网造成的功率波动;考虑电力传输距离制定了微电网间净功率互补机制,提高功率传输效率。算例仿真结果表明,该模型能够合理实现微电网内与微电网间经济运行与功率平衡,为微电网群日前调度计划提供了有效设计流程。 相似文献
13.
As the output power of a microgrid with renewable energy sources should be regulated based on the grid conditions, using robust controllers to share and balance the power in order to regulate the voltage and frequency of microgrid is critical. Therefore a proper control system is necessary for updating the reference signals and determining the proportion of each inverter in the microgrid control. This paper proposes a new adaptive method which is robust while the conditions are changing. This controller is based on a modified sliding mode controller which provides adapting conditions in linear and nonlinear loads. The performance of the proposed method is validated by representing the simulation results and experimental lab results. 相似文献
14.
针对主从式控制结构的独立微电网中可再生能源发电及负荷随机波动的问题,提出了一种基于净负荷超短期预测的微电源协调控制策略,以保障独立微电网的稳定运行.介绍了独立微电网的结构,阐述了净负荷的概念.通过在线采集功率数据,运用最小二乘支持向量机(LS-SVM)方法分别对微电网内负荷及可再生能源出力进行了滚动预测,实现了对净负荷的超短期预测.在预测结果的基础上,主动修正了可控电源日前出力计划,提前响应系统净负荷变化,减轻主电源的调节压力,提高了独立微电网系统的可靠性.算例结果证明了该预测方法的精度,并验证了该控制策略的有效性. 相似文献
15.
构建直流微网容错控制对象模型,调节直流微电网的输出回路参数;以输出功率、直流微网的 参考电压、弱电网下系统惯性响应特征等为约束参量,构建直流微网容错控制目标函数,在不同电网强度下 进行直流微网容错控制的参数自整定性调节,采用无功环比例积分控制方法进行直流微网容错寻优分析, 建立模糊 PID控制模型,采用变结构的模糊 PID控制方法进行直流微网容错控制过程中的自适应加权学习 和误差反馈调节,实现直流微网容错控制改进设计。仿真结果表明,采用该方法进行直流微网控制的容错 性能较好,输出稳定性较强,具有较好的直流微网输出增益。 相似文献
16.
The generalized Heffron–Phillips model (GHPM) for a microgrid containing a photovoltaic (PV)-diesel machine (DM)-induction motor (IM)-governor (GV) (PDIG) has been developed at the low voltage level. A GHPM is calculated by linearization method about a loading condition. An effective Maximum Power Point Tracking (MPPT) approach for PV network has been done using sliding mode control (SMC) to maximize output power. Additionally, to improve stability of microgrid for more penetration of renewable energy resources with nonlinear load, a complementary stabilizer has been presented. Imperialist competitive algorithm (ICA) is utilized to design of gains for the complementary stabilizer with the multiobjective function. The stability analysis of the PDIG system has been completed with eigenvalues analysis and nonlinear simulations. Robustness and validity of the proposed controllers on damping of electromechanical modes examine through time domain simulation under input mechanical torque disturbances. 相似文献
17.
18.
This paper proposes a novel indirect adaptive fuzzy wavelet neural network (IAFWNN) to control the nonlinearity, wide variations in loads, time-variation and uncertain disturbance of the ac servo system. In the proposed approach, the self-recurrent wavelet neural network (SRWNN) is employed to construct an adaptive self-recurrent consequent part for each fuzzy rule of TSK fuzzy model. For the IAFWNN controller, the online learning algorithm is based on back propagation (BP) algorithm. Moreover, an improved particle swarm optimization (IPSO) is used to adapt the learning rate. The aid of an adaptive SRWNN identifier offers the real-time gradient information to the adaptive fuzzy wavelet neural controller to overcome the impact of parameter variations, load disturbances and other uncertainties effectively, and has a good dynamic. The asymptotical stability of the system is guaranteed by using the Lyapunov method. The result of the simulation and the prototype test prove that the proposed are effective and suitable. 相似文献
19.
具有自适应动载滤波与校零功能的起重机超载限制器原理分析 总被引:4,自引:0,他引:4
起重机械工作过程中产生的随机性动载荷以及载荷传感器的零位漂移对起重机超载限制器工作稳定性和测量精度造成严重影响,本文提出一种基于参考模型的自适应动载荷滤波与自动零位跟踪方案。根据这一方案,研制了一种新型的具有自适应动载荷滤波与自动校零功能的高性能起重机超载限制器,显著地提高了起重机超载限制器的工作性能。 相似文献