Comprehensive evaluation of 5G+smart distribution network based on combined weighting method-cloud model

With the large-scale application of 5G technology in smart distribution networks,the operation effects of distribution networks are not clear.Herein,we propose a comprehensive evaluation model of a 5G+smart distribution network based on the combination weighting and cloud model of the improved Fuzzy Analytic Hierarchy-Entropy Weight Method(FAHP-EWM).First,we establish comprehensive evaluation indexes of a 5G+smart distribution network from five dimensions:reliable operation,economic operation,efficient interaction,technological intelligence,and green emission reduction.Second,by introducing the principle of variance minimization,we propose a combined weighting method based on the improved FAHP-EWM to calculate the comprehensive weight,so as to reduce the defects of subjective arbitrariness and promote objectivity.Finally,a comprehensive evaluation model of 5G+smart distribution network based on cloud model is proposed by considering the uncertainty of distribution network node information and equipment status information.The example analysis indicates that the overall operation of the 5G+smart distribution network project is decent,and the weight value calculated by the combined weighting method is more reasonable and accurate than that calculated by the single weighting method,which verifies the effectiveness and rationality of the proposed evaluation method.Moreover,the proposed evaluation method has a certain guiding role for the large-scale application of 5G communication technology in smart distribution networks.

Grey series time-delay predicting model in state estimation for power distribution networks

A new combined model is proposed to obtain predictive data value applied in state estimation for radial power distribution networks. The time delay part of the model is calculated by a recursive least squares algorithm of system identification, which can gradually forget past information. The grey series part of the model uses an equal dimension new information model (EDNIM) and it applies 3 points smoothing method to preprocess the original data and modify remnant difference by GM(1,1). Through the optimization of the coefficient of the model, we are able to minimize the error variance of predictive data. A case study shows that the proposed method achieved high calculation precision and speed and it can be used to obtain the predictive value in real time state estimation of power distribution networks.

An Energy Efficiency Assessment Method for Distribution Network Containing DG

Energy efficiency assessment of distribution network containing distributed generation is one of the core contents of power grid construction. Aiming at the lack of a quantitative evaluation method for energy efficiency of distribution network containing distributed generation, a novel energy efficiency assessment method based on the super-efficiency model is proposed. Starting from the basic elements and operational requirements of the distribution network containing distributed generation, the energy efficiency assessment metric set is constructed. On this basis, the concept of generalized energy efficiency function is defined, and the super-efficiency model is used to assess the energy efficiency of the distribution network containing distributed generation. Finally, an example is given to evaluate and analyze energy efficiency. The results confirm the validity of the proposed method.

Autonomous Vehicle Platoons In Urban Road Networks:A Joint Distributed Reinforcement Learning and Model Predictive Control Approach

In this paper, platoons of autonomous vehicles operating in urban road networks are considered. From a methodological point of view, the problem of interest consists of formally characterizing vehicle state trajectory tubes by means of routing decisions complying with traffic congestion criteria. To this end, a novel distributed control architecture is conceived by taking advantage of two methodologies: deep reinforcement learning and model predictive control. On one hand, the routing decisions are obtained by using a distributed reinforcement learning algorithm that exploits available traffic data at each road junction. On the other hand, a bank of model predictive controllers is in charge of computing the more adequate control action for each involved vehicle. Such tasks are here combined into a single framework:the deep reinforcement learning output(action) is translated into a set-point to be tracked by the model predictive controller;conversely, the current vehicle position, resulting from the application of the control move, is exploited by the deep reinforcement learning unit for improving its reliability. The main novelty of the proposed solution lies in its hybrid nature: on one hand it fully exploits deep reinforcement learning capabilities for decisionmaking purposes;on the other hand, time-varying hard constraints are always satisfied during the dynamical platoon evolution imposed by the computed routing decisions. To efficiently evaluate the performance of the proposed control architecture, a co-design procedure, involving the SUMO and MATLAB platforms, is implemented so that complex operating environments can be used, and the information coming from road maps(links,junctions, obstacles, semaphores, etc.) and vehicle state trajectories can be shared and exchanged. Finally by considering as operating scenario a real entire city block and a platoon of eleven vehicles described by double-integrator models, several simulations have been performed with the aim to put in light the main f eatures of the proposed approach. Moreover, it is important to underline that in different operating scenarios the proposed reinforcement learning scheme is capable of significantly reducing traffic congestion phenomena when compared with well-reputed competitors.

Resilience Against Replay Attacks:A Distributed Model Predictive Control Scheme for Networked Multi-Agent Systems

In this paper,a resilient distributed control scheme against replay attacks for multi-agent networked systems subject to input and state constraints is proposed.The methodological starting point relies on a smart use of predictive arguments with a twofold aim:1)Promptly detect malicious agent behaviors affecting normal system operations;2)Apply specific control actions,based on predictive ideas,for mitigating as much as possible undesirable domino effects resulting from adversary operations.Specifically,the multi-agent system is topologically described by a leader-follower digraph characterized by a unique leader and set-theoretic receding horizon control ideas are exploited to develop a distributed algorithm capable to instantaneously recognize the attacked agent.Finally,numerical simulations are carried out to show benefits and effectiveness of the proposed approach.

雷达转台液压系统可靠性影响评价预测研究

针对当前雷达液压系统可靠性合理建模及影响评价体系难以构建及评估的现状,以某典型机载雷达转台液压系统为研究对象,提出一种基于危害性分析的可靠性影响评价预测方法。利用模糊判断矩阵以获得指标的权重系数,对可靠性进行建模仿真分析,从而为准确预测系统的可靠性提供理论支撑。在此基础上,通过对转台液压系统故障原因进行全面梳理,构建了液压系统可靠性影响评价体系。运用Elman网络,结合实证分析对可靠性影响评价模型进行预测,为雷达转台液压系统故障的综合分析提供了整体解决方案。这也为进一步提高雷达液压系统的可靠性提供了合理思路。该研究可为雷达其他分系统可靠性分析提供参考。

分布式光伏接入的配电网规划综合评价方法

为充分考虑分布式光伏接入对配电网规划评价的影响,基于传统配电网的规划评价体系,提出一种计及光伏输出功率随机性和相关性的有源配电网规划评价方法。首先,为精准刻画光伏出力的随机性与波动性,提出基于改进最优粒子群算法的高斯混合模型,计算多个光伏出力的联合概率密度函数;然后,将潮流方程线性化,推导节点电压和线路潮流线性表达式,分别获取多节点电压和多线路潮流的联合概率分布,并基于此构建考虑光伏接入后的配电网可靠性指标和电压质量指标等。最后,将新构建的电压越限风险指标、电压偏差指标以及潮流断面越限风险指标等新型电网规划评价指标纳入评估体系中,采用层次分析法计算得到组合权重并组合得到最终综合评价结果。仿真结果验证了该评价方法的有效性。

槐树关水库大坝渗流安全评价与预测

为评价槐树关水库大坝的渗流稳定性,收集大坝近年来面板周边缝与坝基监测点处渗压计数据,库水位、气温、降雨量、坝后渗流的监测数据及大坝工程建设与地质资料,先将监测点处渗压计值和坝前水位进行Pearson相关性分析,再根据大坝工程建设及地质资料绘制大坝断面模型并导入Autobank7.7软件计算坝后渗流量,最后将气温、库水位、降雨量等影响因子代入PCA BP神经网络与随机森林、BP神经网络模型对坝后渗流量进行预测。结果表明:除P_(3)、P_(6)、P_(9)外的监测点渗压计值、坝后量水堰监测渗流量值与库水位相关性较强,符合大坝渗流场的一般规律,初步判定大坝较稳定;实际监测的坝后渗流量是Autobank软件模型理论计算值的8倍,判定大坝有出现渗流破坏的可能,后续应采取相应措施除险加固加强监测以保证大坝的稳定性;PCA BP神经网络与随机森林、BP神经网络3种模型最佳预测准确度分别为83.20%、79.35%、69.41%,其中PCA BP神经网络的预测效果最佳,通过模型预知渗流量防止渗流破坏对保证大坝的安全运行具有重要意义。

基于冗余矢量的T型三电平双向变换器中点电位平衡模型预测控制

T型三电平双向变换器因其具有损耗小、输出电能质量高等优势适合应用于低压交直流混合配电网互联等场景。针对T型三电平双向变换器存在直流侧中点电位不平衡等问题,模型预测控制因其易于实现多目标优化的特点具有良好的应用价值。为了解决传统有限集模型预测控制(FCS-MPC)权重因子整定困难,中点电位控制效果不佳的问题,提出一种基于冗余矢量的中点电位平衡模型预测控制,利用冗余小矢量的特性实现对中点电位平衡的控制,避免了权重因子的选择。在此基础上,利用代价函数计算矢量的作用时间并预测输出最优开关序列,提升系统的稳态性能。最后,通过实验测试验证了所提策略的有效性。

基于DPSO-LSTM超参数调优的股市价格预测

长短期记忆网络(Long Short-Term Memory,LSTM)适合处理和预测时间序列中间隔和延迟较长的重要事件。由于其复杂的网络结构、不确定的超参数和耗时的网络训练,使得人工寻找高效的网络配置成为一项具有挑战性的工作。文中采用分布式粒子群算法(Distributed Particle Swarm Optimization,DPSO)来有效解决LSTM的超参数调优问题,研究LSTM中最优的隐藏元个数、激活函数以及学习率等超参数的选择,寻找高性能的LSTM。基于沪深300历史交易数据进行价格预测,实验结果表明该方法是有效的,这为超参数调优与股市价格预测提供了新的思路和方法。

基于LSTM网络的分散式电采暖负荷仿真分析

基于等效热参数模型的分散式电采暖负荷存在参数识别困难、仿真误差大,不能满足电网调节需求的问题,为此提出基于长短时记忆网络的分散式电采暖负荷仿真模型。首先,根据分散式电采暖负荷与建筑物之间的传热过程,确定模型参数。然后,结合模型输入变量与输出变量确定长短时记忆网络参数,建立负荷模型。并通过对测试集输入数据中的室内温度进行动态更新,实现了长时间尺度的温度仿真。接着,为衡量模型的准确性,提出了纵向与横向两种维度上的模型误差评价指标。最后,算例分析结果表明,相比于分散式电采暖负荷二阶等效热参数模型,基于长短时记忆网络的分散式电采暖负荷模型仿真结果的纵向误差与横向误差更小,模型精度更高。

新能源配电网低碳运行长期负荷预测研究

为解决新能源配电网持续低碳运行时的长期负荷预测难度问题。提出利用多时间尺度分析法获取电力负荷数据的小波尺度,选取多个尺度进行分析获取的初步长期负荷数据,采用指数平滑法对获取的初步长期负荷数据进行平滑处理。通过对平滑处理后长期负荷数据的累加累减以及还原,构建一阶微分方程,利用灰色关联方法实现配电网低碳运行长期负荷预测。结果表明,所提方法的预测结果接近电力负荷实际值,预测误差始终低于0.3 MW,且在配电网不同时期的预测误差范围均较小。

基于大数据分析的配电网低电压变化态势预测研究

针对当前配电网低电压变化态势预测误差大、耗时长等不足,为了准确描述配电网低电压变化态势的特点,获得高精度的预测结果,研究基于大数据分析的配电网低电压变化态势预测模型。首先采集配电网低电压变化态势数据,并采用粗糙集理论对原始数据进行预处理,去除冗余数据,然后采用BP神经网络设计配电网低电压变化态势预测模型,最后进行配电网低电压变化态势预测的仿真实验,结果表明所提方法高精度描述配电网低电压变化态势,不仅预测精度超过94%,而且建模效率高,具有较高的实际应用价值。

基于多目标粒子群算法的柔性交直流混合配网变电站检修工时预测

当多个变电站同时需要检修的情况下,受到多种因素限制,难以获取到准确的工时预测结果。为了合理安排工作班组,减少检修时间,设计一种基于多目标粒子群算法的柔性交直流混合配网变电站检修工时预测方法。以检修工时作为目标函数,检修过程中的时间段、检修互斥量、检修班组资源等作为约束条件建立柔性交直流混合配网变电站检修工时预测模型,设计多目标粒子群算法的系数寻优流程,完成变电站检修工时的预测。算例分析结果表明,该方法应用下的预测值与实际值之间标准曲线相关系数更接近1,平均绝对偏差和平均绝对百分比误差更小,预测偏差更低。

基于贝叶斯网络的百色市生态环境综合评价与预测

为了研究百色市生态环境质量状况和识别关键影响因子,依据目的性、整体性、主导性、动态性和相关性等原则,建立百色市生态环境综合评价指标体系,利用AHP法、熵值法二者组合确定生态环境综合评价指标的权重,以驱动力-响应-效应为主线构建贝叶斯网络模拟和预测模型,通过敏感性分析揭示影响研究区生态环境的主要驱动因子,从定性和定量两个角度系统评估2013-2020年百色市生态环境质量状况及时序演变特征。研究表明,影响研究区生态环境的前五个核心驱动因子分别是森林覆盖率、年平均气温、年降水量、工业废水排放量、教育支出,百色市生态环境质量在2013-2020年不断得到改善,生态环境保护工作取得阶段性成效。最后,依据敏感性分析、人类活动因素对模型设置因果推理和诊断推理,对百色市生态环境综合模型进行预测研究,研究结果可为地方政府制定环境保护政策提供科学依据。

110 kV及以下区域配电网供电能力评估方法

提出了一种110 kV及以下区域配电网供电能力评估方法,以配电网的负载供电能力为核心,构建了区域配电网供电能力评估模型。在具体评估过程中,采用重复潮流的方法,以评估配电网的初始负荷参数为初始值,负荷增长值为补偿,将满足约束条件的临界负荷参数作为新的初始值,通过缩小步长进行二次迭代,重复操作,直至连续两次迭代结果一致且均满足约束条件,最终的解作为区域配电网供电能力的评估结果。该方法使用节点及支路的运行配置作为约束条件,将供电能力评估问题转化为模型求解问题,从而有效解决了受配多种约束条件限制的评估问题。测试结果表明,该评估方法能稳定地评估区域配电网供电能力,评估结果与实际参数值的误差均保持在较低水平。

基于小样本数据深度学习的砂体厚度预测方法及应用

沾化凹陷渤南洼陷北部Y184井区沙四上亚段储集层为多期扇三角洲沉积,具有单砂体厚度小、横向变化快、砂泥岩互层等特征,无法定量预测,制约了该井区的高效开发。综合利用深度学习和地震属性预测方法,通过构建虚拟井,解决研究区深度学习训练样本不足的问题,从而挖掘出砂体厚度与地震属性之间的非线性关系,建立了利用地震属性预测砂体厚度的网络模型,该方法能够较为准确地预测砂体厚度及其横向展布特征,提高了预测精度,为致密砂岩储集层预测提供了新的思路和方法。

神经网络预测模型在高速铁路地震响应中的性能对比

为明确何种深度学习模型适用于高速铁路地震响应预测分析,该文利用振动台技术建立高速铁路无砟轨道Ⅱ型板缩尺模型,使用准分布式光纤光栅采集地震时缩尺桥梁响应,建立3种评估指标.从预测精度和稳定性等方面深入研究,对比多层前馈网络(multilayer feedforward network,BP)、长短期记忆神经网络(long short-term memory neural network,LSTM)和循环神经网络(recurrent neural network,RNN)在地震响应中的效果.实验结果说明LSTM网络比BP、RNN网络模型具有更高的预测精度,且在不同应变范围中表现稳定.LMST模型预测结果的平均误差最小,均方根误差、平均绝对误差、决定系数分别达到了0.22582、0.1471、0.91542,可以获得最佳预测精度.

电动汽车与直流配电网协同的分布式自适应滚动预测调度

为充分挖掘电动汽车(EV)的灵活调度潜力,提出了EV与直流配电网协同的分布式自适应滚动预测调度方法。首先,建立了电压源型换流器、储能及直流配电网潮流的数学模型;然后,构建了不可调度、只充电和可充放电3类EV充电偏好的数学模型,并以日电能损耗和弃光电量的加权和最小为目标建立了直流配电网自适应滚动预测调度模型,通过实时EV集群的取车时间动态更新调度窗口,以满足每辆EV的期望电量需求;最后,建立了直流配电网分布式滚动预测调度模型,并采用交替方向乘子法实现分布式求解,以解决集中式调度通信量大的问题。仿真结果表明,通过对EV与直流配电网灵活性资源的协同调度可显著降低电能损耗、提升分布式电源接纳能力,同时,所采用的分布式算法具有良好的收敛性能和计算速度。

含分布式光伏的配电网模型预测控制优化方法

分布式光伏的高渗透率和不确定性对节点电压和潮流分布产生了较大影响,给配电网的安全运行带来了新的挑战,如何对含分布式光伏的配电网进行有效准确的优化控制是亟须解决的问题。为此,文中提出一种含分布式光伏的配电网模型预测控制优化方法,以减小节点电压偏差和网络损耗为目标,基于模型预测控制方法不断更新预测信息并构建优化模型,对分布式光伏和储能设备进行滚动优化控制。采用修改的IEEE 33节点系统作为算例进行验证,仿真结果表明配电网的节点电压偏差和网络损耗得到了有效降低,优化效果相较于日前优化方法更贴近实际结果。基于模型预测控制,所提方法有助于配电网在分布式光伏接入下安全运行,且能减小控制方案与实际情况的偏差。