随着电动汽车关键技术的日趋成熟以及配套基础设施的不断完善,电动汽车产业进入了飞速发展的阶段.提出了对电动汽车用户行为特征分析的意义,以深圳电动汽车智能充电管理平台系统数据为基础,采用k-means聚类分析方法,通过对电动汽车用户行为热力图分析和用户充电时间分布分析,总结了电动汽车用户的行为特征.

为了应对电动汽车充电需求规模越来越大的现状,提出了一种基于针对单一充电站负荷的随机森林电动汽车充电负荷预测方法,通过对Cart回归算法完成对于具体充电站的短期充电负荷预测,从时间及空间角度对区域内各充电站充电负荷的数据分析,将该算法付诸实践,确定了当前电动汽车充电负荷数据在算法中的应用形式,并验证了预测算法的准确性,能可靠投入实用,通过充电负荷的预测为供电商和用户提供参考.

随着信息化技术在智能电网的应用逐步深入,在智能电网的运维中能及时自动检测到不良数据,如网络攻击数据和设备故障数据,对电网的稳定和持续运行有着重要意义.该文提出一种基于多视角低秩分析的电力状态不良数据检测算法.该算法使用来自多个观测源的观测数据综合估计电力系统的状态,算法使用低秩模型挖掘出来自多个观测源数据间的共享本真数据,同时使用稀疏模型对不良数据建模.针对所提出的目标方程,给出了一种基于交叉迭代的优化算法.最后,在IEEE多个节点测试系统上的实验证明了该算法相对于已有算法的先进性.

This paper presents an integrated route planning algorithm to provide optimal routes and corresponding charging schemes for EVs (Electric vehicles) users with different travel objectives based on spot price and traffic conditions. With the development of EVs, more users are facing difficulties to find a charging route that satisfy their demands. To solve the problem, the route planning algorithm is improved based on classified travel objectives, meanwhile the spot price forecast model is established to provide the user's economic assessment. Firstly, the classification of user's travel objectives is completed and the evaluation indicators are proposed. Secondly, a time-window electricity price forecasting based on the GRU (Gated recurrent unit) neural network is established to generate pricing information for route planning algorithm. Finally, SAA (Simulated annealing algorithm) is combined with A* (A-star) algorithm and Dijkstra algorithm to gain the integrated route planning algorithm. Also, the algorithm provides the users with optimal charging paths considering travel objective and price prediction. The results of the optimal routes are displayed on App (application) so that the users can choose their own charging paths and control EV's charging at any time. The simulations prove the effectiveness and accuracy of the proposed algorithm.

Smart grid plays a critical role in national production. The stability and security of smart grid is essentially impor-tant. As a result, it is significant to detect the bad and malicious data from daily observations. This paper proposes a novel outlier detection method based on low-rank representation. Specifically, the observation is decomposed into two parts:a low-rank part for clean data and a sparse part for outliers. In addition, this paper deploys ALM(Augmented Lagrange Mul-tiplier)to optimize the objective. Extensive experiments on two popular benchmarks verify the advantages of the pro-posed method.

With the popularization of electric vehicles, the maintenance of power batteries has gradually become a major research topic in the maintenance of electric vehicles.A battery aging detection method was proposed, based on the real-time conditions of electric vehicles.Changes of ohmic internal resistance of the power battery were observed by monitoring current changes.Furthermore, battery health status was estimated through state of charge(SOC) variation tendency of the electric vehicle, thus providing reference for vehicle maintenance on the part of the users.According to changes of SOC, state of health(SOH) and ohmic internal resistance of the power battery, it could be judged whether the power battery should be replaced or not.

With the popularization of electric vehicles, the maintenance of power batteries has gradually become a major research topic in the maintenance of electric vehicles. This paper proposes a battery aging detection method based on the real-time vehicle condition of electric vehicles. Through the monitoring of current changes, the change of ohmic internal resistance of power battery is observed. And through the SOC changing trend when the electric vehicle is running, the battery health status is estimated, thereby effectively providing a reference for the user's electric vehicle maintenance. According to changes in the SOC, SOH, and ohmic resistance of the power battery, it is determined whether the power battery needs to be replaced.

To cope with the increasing charging demand of electric vehicle (EV), this paper presents a forecasting method of EV charging load based on random forest algorithm (RF) and the load data of a single charging station. This method is completed by the classification and regression tree (CART) algorithm to realize short-term forecast for the station. At the same time, the prediction algorithm of the daily charging capacity of charging stations with different scales and locations is proposed. By combining the regression and classification algorithms, the effective learning of a large amount of historical charging data is completed. The characteristic data is divided from different aspects, realizing the establishment of RF and the effective prediction of fluctuate charging load. By analyzing the data of each charging station in Shenzhen from the aspect of time and space, the algorithm is put into practice. The application form of current data in the algorithm is determined, and the accuracy of the prediction algorithm is verified to be reliable and practical. It can provide a reference for both power suppliers and users through the prediction of charging load.

随着电动汽车的普及,电动汽车的车主们对于出行路径规划的需求日益增加.一种计及分时电价及交通工况的电动汽车最优出行路径规划算法,通过出行路径上的充电站电价及道路交通情况,构建道路简化模型和最优路径规划模型,实现实时的电动汽车最优路径规划.该算法可实际应用于电动汽车的智能终端上,引导用户经济可靠地驾车出行.

电力综合服务平台基于新的IT架构,以客户为中心,通过数据驱动,为电力生态圈相关利益方提供的应用集合,以支撑利益方之间网状、并发、实时工作协同,支撑利益相关方之间简单、快捷、低成本交易与结算,支撑政策开放、社会认知等前提下公司多元化业务延伸,最终构建合作结盟、多方共赢新型商业体系.随着公司业务发展及信息化水平的提高,业务数据采集难、数据质量较低、应用水平低、运营管理效率低等问题越发突出.电力综合服务平台作为业务数据采集、存储、维护等的重要载体,亟需通过数据资产全生命周期管理,从数据基础、数据治理、数据运营、数据应用等层次深入挖掘数据资产价值,依靠数据驱动,实现资产增值,促进公司运营管理有效提升.

本文提出了一种计及电网峰谷运行的电动汽车充电服务费定价策略,介绍了峰谷分时电价对电动汽车用户充电行为的影响.通过仿真对比分析了电动汽车随机接入电网充电负荷变化趋势、基于峰谷分时电价、电动汽车并网充电负荷变化趋势以及征收计及电网峰谷运行的充电服务费模式下负荷变化趋势,仿真结果证实征收计及电网峰谷运行的电动汽车充电服务费可以减小电动汽车充电对电网负荷的影响.

智能电网容易受到虚假数据注入攻击.对虚假数据的检测有助于提高电网状态估计准确性,从而提高智能电网的稳定性.为了能自动检测出智能电网中的虚假注入数据,提出一种基于双低秩约束的智能电网虚假数据检测算法.与已有算法相比,该算法不使用训练数据自身作为低秩学习字典,而是引入一个低秩特征转换矩阵,使得用于低秩学习的字典具有更好的灵活性,以及学习到的模型具有更强的泛化能力.该算法可应用于智能电网的电力状态估计.在多个IEEE节点测试系统上的实验表明该算法比目前广泛使用的主成分分析算法和鲁棒主成分分析算法具有更好的性能.

At present, the status quo of safe production management in power supply enterprises is mainly to carry out in the periodic maintenance mode. It causes frequent temporary maintenance,inadequate or excess maintenance,blind maintenance and so on. At the same time,the enterprise managers' ideas and acts still tend to stay in a rut, which gives expression to the information system construction whose top-level design is provided with neither longitudinal business correlation nor horizontal business collaboration. The disjoint phenomenon among strategy, business and information technology leads to failure of business reform and a large number of waste of IT investment.A safe production management information system of equipment as the core, plan as the main line and connecting "three risks" (power grid risk, equipment risk and operational risk), managing and controlling the entire process of safe production in real time, is researched and implemented based on the management philosophy of the CSG (China Southern Power Grid Co., Ltd) Risk Management System of Safe Production in this paper, in order to achieve a new practice which not only satisfies power supply enterprises running the periodic maintenance as a mainstream mode, but also supports the power grid, equipment and personnel risks assessment and dynamic management and control. Reasonable arrangement of special maintenance work saves power supply enterprise human cost, reduces the operation risk of power grid and equipment and improves the economic and social benefit of enterprises.

This paper discusses the construction of a unified, standardized and secure mobile terminal access management platform for power supply enterprises. The platform takes the mobile terminal security protection system and SOA-oriented service as its core foundation, and implements the functions including equipment management, secure access and on-site supervision using the mobile terminal controlling technology in order to provide thorough support for on-site management and auxiliary decision for platform operation and data managers. With the aid of the unified access management platform, the work efficiency of on-site operators is improved and enterprise’s operation cost is also saved.

This paper proposes a brand new light-weight high performance server framework(LHP-Svrframe) for new generation server development, whose intension is for building a high performance server of massive connection and massive data. The difference from current frameworks is LHP-Svrframe focuses on TCP stack and process model and does especial optimization design, such as load balancing in NIC interrupts, dynamic adjust size of the congestion window, and optimization of the delayed ACK mechanism, et al. Experimental results in the end prove that the LHP-Svrframe performs much better than its counterparts like Apache, Lighttpd and ACE, with four times even eight times better.

<正>20世纪80年代以来,随着电力电子技术的发展及其在工业领域应用范围的扩大,以及工业电弧炉、轧钢机、大型半导体变流装置等非线性、冲击性负荷的日益增加,电网无功功率变化剧烈,造成系统电压波动和不对称,同时向系统注入大量的谐波,严重影响电力系统的安全运行。在电力系统无功、谐波和不对称问题出现之后,人们就试图通过各种方法解决这些问题。综合起来,这些方法