基于遗传算法的高速动车组列车惰行节能控制策略研究

为降低高速动车组（EMUs）的运行能耗,建立了准点约束条件下的EMUs惰行能耗模型。在此基础上,采用自适应遗传算法对EMUs中间运行阶段的惰行控制策略进行优化,寻找最优位置与数目的惰行关键工况转换点,确定列车运行的惰行速度曲线,从而达到准点和节能运行的效果。     

Energy‐Efficient Train Speed Profile Generator Combining Partial Energy‐Oriented Driving Approaches

One way of reducing the energy consumption of trains is to drive them in an energy‐efficient manner. There can be various driving patterns between two adjacent stops, or various speed profiles, because there is a gap called the running time supplement between the planned running time set in a timetable and the shortest possible running time of the train. Previous studies have proposed using up the supplement by changing the driving operation from powering to coasting at optimal points in terms of energy consumption. Others have shown that full use of regenerative braking helps save energy. In this study, we developed an energy‐efficient speed profile generator by combining these partial energy‐oriented driving approaches when the planned running time is given. We added this generator to existing shortest running time calculation software, so that it works for various vehicle and train route data. Numerical experiments showed that our profile provided superior performance compared to manually created ones for artificial and real data.     

基于最优预见控制的货运列车速度跟踪控制研究

列车速度曲线的精确跟踪是货运列车自动驾驶系统保证稳定性、精确性和安全性的关键。货运列车速度跟踪系统大时滞特性会造成控制精度下降和能耗增加的问题。为解决该问题,研究了牵引制动系统响应时间和指令传输延时特性,构建了列车速度跟踪控制滞后模型。利用差分算子处理列车动力模型中的滞后项,构造最优预见速度跟踪控制器。仿真对比试验表明,基于最优预见控制的货运列车速度跟踪控制器具有响应快、速度误差小、安全性高等特点。     

Evaluation of Automatic Train Operation Design for Energy Saving Based on the Measured Efficiency of a Linear‐Motor Train

Recently, interest in energy savings in railway systems has been increasing because of its environment‐friendly aspects, for example, CO₂ emissions. In this paper, the authors propose a scheduling and control system for automatic train operation (ATO) that saves energy. This research in ATO concentrates on the optimization of speed profiles to save energy. The differences in this system from previous work are substantiative experiments on the track and a design that explicitly considers the following energy‐saving operations. First, coasting is installed in speed profiles and maximum speed is decreased by jerk regulation. Second, power‐limiting braking is used in the braking section and regenerative energy is increased. To achieve this braking efficiency, notch operations are updated. Finally, second‐order scheduling is achieved by high speed control using ATO. For the experiments on the track, the efficiency of a linear‐motor train was measured in a pre‐experiment and used to perform accurate numerical calculations. In conclusion, the numerical study shows an energy efficiency increase by 7.3% and the plan for further experiments is determined.     

Traction Energy Cost Reduction of the WMATA Metrorail System

An energy cost reduction study was conducted on the Washington Metropolitan Area Transit Authority Metrorail system. Its primary objectives were to classify primary energy end uses and identify conservation methods which have the highest potential for reducing the electric bill. The effort involved analyzing present energy costs, developing cost- effective conservation strategies, determining the savings associated with the strategies by simulation, recommending appropriate strategies for implementation and outlining a program for executing the recommendations. Although the effort involved both traction and support energy, only the traction energy aspects of the study are reported. It is the first time that the energy management model developed for the transit industry by the Rail Systems Center at Carnegie-Mellon University was comprehensively applied to a rapid transit property. The application was verified by comparing the simulated results to actual data. For anl practical purposes, the simulated results agree to within three percent of the actual energy consumption. Four traction energy conservation strategies were recommended for implementation based on high benefit and low cost. These are coasting, passenger load factor improvement, planned catch-up operation, and regeneration of braking energy. All of these strategies have payback periods of less than three years.     

考虑风电置信区间的水风火短期优化调度方法

风电出力的不确定性影响电网的稳定运行,大规模风电并网后“弃风”问题突出。为了充分考虑风电出力的不确定性,本文提出基于风电置信区间的风-水-火短期联合调度运行方法。利用梯级水电站启停灵活、爬坡速度快等优点平抑风电出力波动,构建了发电成本最小与清洁能源消纳最大的多目标优化调度模型。基于分层求解思想,将模型分为风电运行层、水电调度层与火电调度层,并提出了集成非参数法、启发式算法与改进的粒子群算法的总体求解框架,实现了模型的快速求解。某区域电网短期调度模拟运行结果表明,所提方法求解速度快,仅需83.5 s,在满足电力系统安全稳定运行约束与清洁能源消纳最大的前提下,水电、风电多发45.56万kWh,煤耗成本减少23.33万元。     

考虑光伏集成5G基站用能模式的多主体共享储能优化配置

光伏集成5G基站能够有效降低电信运营商的用能成本,然而含分布式光伏的5G基站用能模式将对主动配电网的稳定运行造成影响,致使电信运营商与主动配电网均存在储能配置需求。出于安全性与经济性考虑,文中引入储能运营商作为第三方共建共享储能系统,提出了一种考虑光伏集成5G基站用能模式的多主体共享储能优化配置方法。首先,提出了面向规模化光伏集成5G基站与主动配电网储能配置需求的共享储能系统动态容量租赁模型;其次,基于双层混合整数规划模型(BiMIP)构建共享储能系统容量配置与运行双层联合优化问题;最终,采用重构与分解(R&D)算法对双层联合优化问题进行求解。仿真结果表明,所提出的多主体共享储能优化配置方法能够实现主动配电网的削峰填谷与多主体间的互利共赢。     

An Integrated Approach to Economic Emission Load Dispatching Using Neural Network and Goal-Attainment Methods

This paper presents an integrated approach comprising artificial neural network (ANN) and goal-attainment (GA) methods to economic emission load dispatching (EELD) in power system operation and scheduling phases. The GA method, which is one of the most powerful tools for multiobjective optimization problems, is quantitatively performed to grasp trade-off relations between the two conflicting objectives (economy and emission impact) in the training set creation phase. Finally, a radial basis function ANN is trained by the orthogonal least squares learning algorithm to reach the optimal generations. The ANN models so developed have been tested to solve EELD problem on 6-bus and 71-bus power systems. The test results demonstrate that the proposed approach is capable of obtaining well-coordinated optimal solutions suitable both in accuracy and speed while allowing flexibility in the operation of the generators.     

基于深度强化学习的光储充电站储能系统优化运行

优化储能充放电策略有利于提升光储充电站运行经济性,但是现有模型驱动的随机优化方法无法全面考虑储能系统的复杂运行特性以及光伏发电功率、电动汽车充电负荷的不确定性.因此,提出一种基于深度强化学习的光储充电站储能系统全寿命周期优化运行方法.首先对储能运行效率模型和容量衰减模型进行精细化建模.然后考虑电动汽车充电需求、光伏出力和电价的不确定性,在满足电动汽车充电需求和光伏消纳的条件下,以光储充电站收益最大化为目标,建立了基于强化学习的储能优化运行问题.考虑到储能充放电决策动作的连续性,采用双延迟深度确定性策略梯度算法进行求解.采用实际历史数据对模型进行训练,根据当前时段状态对储能充放电策略进行实时优化.最后,对所提方法及模型进行测试,并将所提出的方法与传统模型驱动方法进行对比,结果验证了所提方法及模型的有效性.     

计及分时电价的5 G基站光储系统容量优化配置方法

随着第5代移动通信技术（5G通信）的迅速发展,5G基站数量不断增加,5G通信耗电量大、用电成本高的问题日益突出。为此,提出了考虑光伏和储能接入的5G基站光储系统优化配置方法,以提高5G基站运行的经济性。首先,考虑5G基站负荷情况和配电网分时电价,建立了5G基站光储系统的经济调度模型;然后,通过量子粒子群优化算法计算典型日内5G基站光储系统的最小综合成本,以此确定光伏和储能的最优接入容量;最后,通过算例证明合理配置光伏和储能容量可以提高5G基站系统的经济性。光伏和储能容量的配置受储能成本和峰谷电价差的影响较大,且光储系统所能带来的经济效益随峰谷电价差的增大和储能成本的降低而增大。     

基于分解协调方法的光储系统配置—运行协同优化

以光伏-储能电池系统为研究对象,构建光储系统的配置-运行优化分解协调模型.首先,将考虑储能投资成本与光储系统运行成本在内的综合费用作为目标函数,利用Benders分解方法将模型分解为规划配置主问题和运行调度子问题,然后,通过分解协调优化得到储能电池的最优配置方案与系统的优化运行策略,通过设定光伏消纳率、自给率、内部收益率、动态投资回收期等一系列指标,对模型进行评价.此外,实现了 Benders分解法收敛过程和Bender割集累积过程的可视化,直观展现出容量配置与优化运行的交互作用.基于此,进一步利用K-means聚类分析算法建立了年光伏出力模型,求解长时间尺度上储能电池的最优配置,探讨了分解协调优化模型在中长期尺度下求解的可行性.     

Design of energy‐efficient train speed profiles considering fixed‐block signaling system

In dense traffic railway networks, trains may often slow down or stop between stations owing to previous train delays. If preceding train trajectory can be predicted, energy‐efficient driving can be achieved by suppressing unnecessary speed changes. In this paper, we propose an algorithm to find energy‐efficient driving considering fixed‐block signaling (FBS) system by using dynamic programming (DP). DP is suitable for use because it can optimize the control inputs with discrete and state constraints. In this paper, we discuss energy‐efficient driving by considering a FBS system using some case studies of simulation. In the simulation, we examine a technique to drive an express train in an energy‐efficient way when the preceding local train is running toward the station with passing loops. The results show that the proposed method can derive complex speed profiles for energy‐efficient driving and the train can be operated with a maximum reduced energy consumption of 8.3%.     

Automatic Train Operation Using Autonomic Prediction of Train Runs

In this paper, we present an automatic train control method adaptable to disturbed train traffic conditions. The proposed method presumes transmission of detected time of a home track clearance to trains approaching the station by employing equipment of Digital ATC (Automatic Train Control). Using the information, each train controls its acceleration by a method that consists of two approaches. First, by setting a designated restricted speed, the train controls its running time to arrive at the next station in accordance with predicted delay. Second, the train predicts the time at which it will reach the current braking profile generated by Digital ATC, along with the time when the braking profile transits ahead. By comparing them, the train correctly chooses the coasting drive mode in advance to avoid deceleration due to the current braking profile. We evaluated the effectiveness of the proposed method regarding driving conditions, energy consumption, and reduction of delays by simulation. © 2011 Wiley Periodicals, Inc. Electr Eng Jpn, 175(3): 65–73, 2011; Published online in Wiley Online Library ( wileyonlinelibrary.com ). DOI 10.10020/eej.21080     

基于互补机制的水火电力系统短期节能发电调度

为充分提高水火电力系统联合运行的经济性,将减少非可再生能源的使用量及降低火电成本为主要目标的水火电力系统短期发电调度问题,转化为水力发电量最大、耗水量最小和火力发电燃料总耗量最小且具有时序的3个优化子问题。该优化模型不仅可确定水电的最佳放水策略和火电的最佳出力,还可描述水电和火电的互补作用,充分体现节能和效益的理念。针对水电系统具有强非线性的特点,采用改电磁学算法进行求解,对火电子系统则采用内点法进行求解。算例结果验证了该方法的有效性。     

Implementation of an artificial-neural-network-based real-time adaptive controller for an interior permanent-magnet motor drive

This paper presents the implementation of an artificial-neural-network (ANN)-based real-time adaptive controller for accurate speed control of an interior permanent-magnet synchronous motor (IPMSM) under system uncertainties. A field-oriented IPMSM model is used to decouple the flux and torque components of the motor dynamics. The initial estimation of coefficients of the proposed ANN speed controller is obtained by offline training method. Online training has been carried out to update the ANN under continuous mode of operation. Dynamic backpropagation with the Levenburg-Marquardt algorithm is utilized for online training purposes. The controller is implemented in real time using a digital-signal-processor-based hardware environment to prove the feasibility of the proposed method. The simulation and experimental results reveal that the control architecture adapts and generalizes its learning to a wide range of operating conditions and provides promising results under parameter variations and load changes.     

On the design of a single-sided linear induction motor for urban transit

Single-sided linear induction motor (SLIM) propulsion and wheel-on-rail support and guidance for urban transit has been developed in Canada and Japan. The maximum speed for urban transit is about 70 km/h, with the trains repeatedly performing powering, coasting, and braking operations within relatively short distances between stations. In the design of SLIM's operating under such conditions, we must take into account energy consumption as well as motor weight, input KVA, and performance characteristics. In this paper, we conduct a theoretical examination of such a SLIM design, estimating its performance characteristics in using space harmonic analysis. Energy consumption is reduced by decreasing the mechanical clearance. The flux density, then, should be a low value of from 0.5 T to 0.6 T. A motor length of from 2 to 2.5 m and pole pitch of about 300 mm are advisable.     

考虑需求响应与储能寿命模型的火储协调优化运行策略

针对大规模新能源并网带来的系统调峰和消纳难题,以及已有优化调度策略对储能寿命成本考虑不足的问题,提出了一种考虑需求响应与储能寿命模型的火储协调优化运行策略。上层通过分时电价引导用电,以净负荷波动性最小为目标得到优化后的负荷曲线,旨在减轻火储的调峰压力、提高新能源消纳量;下层以系统总调度成本最低为目标协调优化风光火储运行,考虑火电深度调峰并在优化调度中嵌入储能寿命模型,求解得到各电源以及储能的最优运行方式。以某区域实际系统为例进行仿真,结果表明所提策略可以有效改善系统的调峰压力,提高新能源消纳能力,同时合理反映了储能的寿命成本,提高了系统运行的经济性。     

NEURAL NETWORK APPROACH TO DYNAMIC VOLTAGE STABILITY PREDICTION

ABSTRACT

The application of artificial neural network (ANN) on dynamic voltage stability analysis is presented. Two ANN models have been utilized, in which the first ANN model is used to classify the power system as to whether it is dynamically stable or unstable. Then the second ANN model is used for the dynamically stable system to predict the voltage magnitudes at load busbars. Both ANN models are based on the multiperceptron model, and the training is done using the error back propagation scheme. The training set patterns are generated by carrying out dynamic simulations, using induction motor and constant P-Q load models. This paper highlights the method for selection of the optimum number of training sets so as to minimise the time taken in the ANN learning process. The performance of the ANN models have been tested and shown to give good results.     

计及需求响应的智慧能源小区热电耦合系统用能优化方法

针对智慧能源小区热电耦合系统中能量间纵向转换和用能负荷横向搬移的协同用能优化问题,通过负荷侧需求响应用能精细化建模,提出一种计及需求响应的热电耦合系统用能优化方法。在分析典型热电耦合系统结构框架基础上,通过用能负荷分类及其用能响应过程的数学建模,建立了含热电耦合系统的能源供给侧与用能负荷侧的能量枢纽方程,实现了用能负荷响应与能源供给之间能量转换的量化描述;其次将用能负荷的需求响应程度表示为可转移负荷参与比和可转换负荷参与比,建立了系统运行成本最小的热电耦合系统用能最优化模型,并提出了灵活尺度多次参与用能优化的模型求解方法。最后,算例结果表明,在高可转移负荷参与比和低可转换负荷参与比时,在降低供给侧峰值段负荷的同时使系统总成本降低,实现了热电耦合系统用能最优化运行。     

Block-Layout Design Using MAX–MIN Ant System for Saving Energy on Mass Rapid Transit Systems

This paper presents a method of block-layout design between successive stations for mass rapid transit systems (MRTSs). The aim is to save energy under the framework of the fixed-block signaling (FBS) system and the equi-block principle. Unlike past research regarding the energy savings of train operation, this paper proposes a combinatorial optimization model to reduce the computation time. In the presented approach, the problem of minimizing the energy consumption between successive stations is first formulated as a combinatorial optimization problem. Then, the train-speed trajectory for saving energy is optimized by a MAX–MIN ant system (MMAS) of ant colony optimization (ACO) algorithms. Finally, the block layout is designed in accordance with the shortest block length under the equi-block principle. It is shown that the method presents a significant improvement for the reduction of computational burden on the block-layout design. The feasibility and benefits are verified via simulation study. Analyses and discussions are also given.