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.

计及占用影响的集成楼宇暖通空调负荷群配电网优化方法

提出了一种考虑人员占用影响的集成楼宇暖通空调(heating,ventilation and air conditioning,HVAC)负荷群配电电网优化方法。首先,依据建筑围护热阻热容网络和配电网支路潮流方程构建了集成暖通空调负荷群配电网数学模型。其次,利用梯形隶属度函数模糊化占用人数并考虑其对暖通空调负荷温度调控的影响,形成包含占用松弛函数约束的暖通空调负荷群与配电网联合优化方法。最后,通过模型预测控制方法实现了集成楼宇暖通空调负荷群配电网的滚动优化控制。改进的IEEE33节点配电网系统仿真结果表明,所提出的计及占用影响的联合优化模型,在楼宇侧能够满足人员热舒适性,同时减少楼宇暖通空调负荷能耗,在电网侧则减少配电网线路损耗和节点电压的波动,有效提高楼宇侧和电网侧整体的节能水平。

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。

基于喷泉码信息差异分簇的V2V协作数据分发方案

新兴车联网应用需要分发的数据量不断增加,车辆难以在一个RSU通信范围内收到完整数据,跨RSU通信完成率低,时效性差。针对此问题,提出一种基于喷泉码信息差异分簇的V2V协作数据分发方案。经过喷泉编码的数据由RSU广播;车辆通过XGBoots预测车速,以此计算V2V链路生存时间;链路可靠性和车辆的喷泉码信息差异构建引力模型来分簇,在簇内以V2V传输共享编码包,在保证完成率的前提下大幅降低数据分发延迟。仿真结果表明,与已有方案ECDS相比,对于不同大小的数据,该方案在保证完成率的基础上,平均时延降低了38%。

基于遗传算法和BP神经网络的矿区土壤重金属含量空间分布预测

本研究提出了一种基于遗传算法(Genetic algorithm,GA)和BP神经网络(Back propagation neural network,BPNN)的复合模型——GABP模型,以安徽省池州市某矿区及其周边为研究区,预测了土壤中p H和7种重金属元素(Cd、Pb、Cr、Cu、Ni、Hg、As)含量的空间分布,并与BPNN和反比距离权重法(Inverse distance weighting,IDW)进行了比较。研究结果表明:受采矿活动影响,研究区土壤p H和重金属含量呈显著的空间分异性;GABP复合模型的数据扩增能够有效弥补BPNN对样本数量的依赖,同时结合了地理位置和高程属性,精度评价结果显示GABP模型的平均R^(2)、r、RMSE、MAE分别是IDW和BPNN的3.03倍、2.56倍,2.93倍、2.39倍,0.85倍、0.61倍,0.79倍、0.62倍,预测精度更高。模型解决了传统空间插值方法结果中可能出现负值和边界无法插值的问题,为土壤重金属含量空间分布预测提供了一种新方法。

配电网负荷预测中信号分解和预测模型组合的双层优化策略

负荷时间序列的波动性和非线性特征的加剧对负荷预测方法提出了更高的要求,而常规组合预测方法针对海量负荷数据存在应用局限性问题。为此,提出了配电网负荷预测中时序分解方法和预测模型组合的双层优化策略。首先针对某一负荷预测数据,在时序信号分解层配置权重,以负荷均方根误差最小寻优各分解方法的权重系数,进而获得各时序信号分解方法的最优组合;在此基础上,在预测模型层进行组合方案寻优,通过配置权重系数以获得各预测模型的最优组合,进一步提升负荷预测的精度。仿真结果表明,所提策略可根据预测对象的特征优化组合各信号分解方法和预测模型,降低了配电网负荷序列的非平稳性对预测精度的影响。

基于ISSA-LSTM的储麦长期品质预测

为了解决非时序预测模型无法预测储麦品质时序劣变趋势,以及现有数据驱动的时序预测模型在长期储麦品质预测中因样本不足导致长期预测精度不高的问题,提出一种基于改进麻雀搜索算法(ISSA)优化长短时记忆网络(LSTM)的长期储麦品质预测模型。首先,提出了一种统计均匀分布方法,利用小麦稳定劣化的生理知识对原始数据进行增强扩容。其次,利用麻雀搜索算法(SSA)对LSTM模型进行优化,克服局部极值点,提高收敛速度。最后,引入t分布函数对SSA位置更新过程进行扰动避免局部最优。结果表明,储麦品质参数中的吸水率、咀嚼度、脂肪酸值和峰值黏度与储藏时间的Spearman相关性较为显著,相关系数均高于0.9,ISSA-LSTM模型预测精度相比于BP、LSTM、SSA-LSTM预测模型分别提高了11.83%、16.98%、26.50%,有助于提高小麦品质预测及分析的准确性。

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。

基于数据驱动预测控制的有源配电网电压控制策略

高比例分布式光伏接入配电网使得系统的不确定性更加严峻,而配电网的网络拓扑与线路参数等数据很难准确获取,使得基于精确物理建模的传统配电网控制方法难以发挥作用。随着配电网量测装置的普及应用,配电网运行数据的获取愈发容易。文中提出一种基于配电网量测数据的有源配电网无模型电压控制方法。首先,基于配电网历史数据构建Hankel矩阵,建立网络节点电压与储能输出功率的关系;其次,利用局部量测数据,在考虑不确定干扰因素以及储能寿命衰减模型的同时,构建数据驱动预测控制下的配电网电压优化框架,实现控制周期内配电网电压的滚动优化;最后,通过IEEE 34节点标准算例与改进的IEEE 123节点算例仿真验证了所提方法的有效性和优越性。

链路预测的若干基础问题探讨

链路预测是网络科学最具活力的分支之一,其目标是基于已知的网络拓扑结构估计未观察到的链接的存在可能性。该文对链路预测中仍需重点关注的4个基础性问题——网络选取、链路抽样、模型训练和算法评价进行了研究,报告了这4个方面目前的研究进展,并指出尚未解决的关键问题。最后,对亟待解决的一些关键研究问题进行了总结。

考虑感应电机负荷特性的主动配电网电压模型预测控制

针对高比例新能源并网引发主动配电网电压越限问题,提出了一种考虑感应电机负荷特性的主动配电网电压模型预测控制方法。首先,通过建立感应电机负荷的稳态模型,分析了其有功和无功与并网点电压的耦合关系,提出考虑感应电机负荷特性的配电网状态估计方法,实现了对关键状态量的实时在线监测。然后,计及各类电压调节资源,构建考虑感应电机负荷特性的电压模型预测控制方法,并通过状态预测、滚动优化和反馈控制3个关键环节,在维持配电网电压安全的前提下,以最低调节成本实现感应电机负荷并网点电压与设定值的偏差最小化。最后,基于IEEE33节点系统算例进行仿真,验证了所提方法在提高状态估计精度、改善电压控制效果方面的有效性。

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。

燃料电池预测模型输出结果统计分析

基于神经网络算法建立的燃料电池寿命预测模型,输出结果都因随机性存在不确定的问题,即每次预测的输出结果都不同。针对此问题,基于长短时记忆(LSTM)神经网络算法建立燃料电池寿命预测模型,多次运行试验样本数据,利用统计学方法对输出结果的分布规律进行统计特性分析,发现基于LSTM神经网络的寿命预测模型,输出结果符合正态分布规律。根据此结论,可采用多次平均结果作为燃料电池寿命预测模型的输出结果,以提升输出结果的预测精度及稳定性。

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。

城市固废焚烧过程炉温非线性模型预测控制

为实现城市固废焚烧(MSWI)过程炉温的稳定控制,本文提出一种炉温非线性模型预测控制(NMPC)方法.首先,采用炉排温度与一次风温作为炉温控制的中间变量,将串级控制策略融入到NMPC中,以获得一种新的MSWI炉温控制结构.其次,利用随机配置网络(SCN)离线建立炉温静态非线性预测模型,并通过递推最小二乘法在线更新SCN隐含层神经元的输出权值,从而建立炉温动态非线性预测模型.最后,将改进的海鸥优化算法同设定值评价与学习模型相融合,得到一种改进的滚动优化策略,以提升NMPC滚动优化的求解性能.实验结果表明,炉温动态非线性预测模型可以准确预测炉温,提出的控制方法具有良好的自适应性及鲁棒性,能够实现MSWI过程炉温的平稳控制.

基于双层级联模型预测电流控制的零序环流抑制策略

逆变器并联系统在运行过程中,由于功率分配不均、控制参数失配等因素导致两逆变器开关状态不同步,使得环路中产生零序环流。为此,提出一种基于双层级联模型预测电流控制的零序环流抑制策略,通过将零序环流加入综合目标函数,选取最优开关状态组合实现零序环流的抑制。同时,通过改变目标函数结构、利用双层级联的方式进行开关状态组合选取,在消除权重系数对控制系统影响的同时减轻计算负担。最后,通过仿真和试验验证了所提控制策略的有效性。