电网调控领域人工智能技术运用分析

电网调控是一个复杂的过程,人工智能技术可以进一步完善电网调动的技术。在该研究中,该文将从智能电网入手,在了解电网调控领域的电网负荷管理相关问题后,提出了一种改进LSSVM训练的人工智能RBF神经网络预测模型,通过该模型对电网电力负荷预测调控进行分析,最后结合某地区的实际案例,对该方法的可行性展开论证。从案例的最终试验结果可知,可以通过该文介绍的人工智能技术对地区用电负荷进行预测,为电网调控提供必要的支持,具有技术优势。

Intelligent Examination Monitoring and Maintenance for the Safety of Operation of Flexible Manufacturing Systems

Based on the system of electric power supply for flexible manufacturing systems (FMS), a study has been carried out on the intelligent safety examination, monitoring and maintenance of its running environment. On the basis of the specific feature of the power supply network of an FMS, real time monitoring system of the power supply network and the fault diagnostic expert system for the power equipment have been designed. This system can diagnose not only definite fault phenomena, but also fuzzy, uncertain fault phenomena as well. Fault diagnostic knowledge base for the power equipment has been founded hierarchy architecture model and the method of fault tree analysis. Feasibility of this system has been proved by computer simulation.

Combining Market-Based Control with Distribution Grid Constraints when Coordinating Electric Vehicle Charging

The charging of electric vehicles(EVs) impacts the distribution grid, and its cost depends on the price of electricity when charging. An aggregator that is responsible for a large fleet of EVs can use a market-based control algorithm to coordinate the charging of these vehicles, in order to minimize the costs. In such an optimization, the operational parameters of the distribution grid, to which the EVs are connected, are not considered. This can lead to violations of the technical constraints of the grid(e.g., undervoltage, phase unbalances); for example, because many vehicles start charging simultaneously when the price is low. An optimization that simultaneously takes the economic and technical aspects into account is complex, because it has to combine time-driven control at the market level with eventdriven control at the operational level. Diff erent case studies investigate under which circumstances the market-based control, which coordinates EV charging, conflicts with the operational constraints of the distribution grid. Especially in weak grids, phase unbalance and voltage issues arise with a high share of EVs. A low-level voltage droop controller at the charging point of the EV can be used to avoid many grid constraint violations, by reducing the charge power if the local voltage is too low. While this action implies a deviation from the cost-optimal operating point, it is shown that this has a very limited impact on the business case of an aggregator, and is able to comply with the technical distribution grid constraints, even in weak distribution grids with many EVs.

Control strategy of LCL-type three-phase photovoltaic grid connected inverter

The grid-connected inverter with LCL filter has the ability of easily attenuating high-frequency current harmonics. However, its suppression effect on the background harmonics in grid voltage is limited. A control strategy is presented, which is composed of an inner loop of capacitor current feedforward, an outer loop of grid-current feedforward and feedforward of grid voltage. The limitations and steps of parameters design for LCL filter are analyzed. Meanwhile, the capacitor current loop is employed to damp the resonant peak caused by the LCL filter and enhance the stability. The properties of different controllers are analyzed and compared, thereinto quasi-proportional-rasonant (PR) controller realizes the control with zero steady-state error of AC variables in static coordinates. In order to suppress the current distortion effected by the background harmonics in grid voltage, the feed-forward function is calculated for the grid-connected inverter with an LCL filter. After simplifying the block diagram, a full-feedforward control strategy for grid voltage is proposed. Theoretical analysis and Matlab/Simulink simulation results show that the proposed method has the advantages of high steady accuracy, fast dynamic response and strong robustness.

Power Quality Improvement Using Grid Side Converter of Wind Energy Conversion System

This paper presents the control ofa WECS （wind energy conversion system）, equipped with a DFIG （doubly fed induction generator）, for maximum power generation and power quality improvement simultaneously. The proposed control algorithm is applied to a DFIG whose stator is directly connected to the grid and the rotor is connected to the grid through a back-to-back AC-DC-AC PWM （pulse width modulation） converter. The RSC （rotor side converter） is controlled in such a way to extract a maximum power, for a wide range of wind speed. The GSC （grid side converter） is controlled in order to filter harmonic currents of a nonlinear load coupled at the PCC （point of common coupling） and ensure smooth DC bus voltage. Simulation results show that the wind turbine can operate at its optimum energy for a wide range of wind speed and power quality improvement is achieved.

Research on Wind Farm Participation in Power Grid AGC Control

Since wind power has the features of being intermittent and unpredictable, and usually needs transmission over long distances, grid integration of large-scale wind power will exert signif icant influence on power grid planning and construction, and will make a heavy impact on the safe and reliable operation of power systems. To deal with the diff iculties of large scale wind power dispatch, this paper presents a new automatic generation control (AGC) scheme that involves the participation of wind farms. The scheme is based on ultra-short-term wind power forecast. The author establishes a generation output distribution optimization mode for the power system with wind farms and verif ies the feasibility of the scheme by an example.

A Real-Time Power Controller for Grid-Connected Inverters in LV Smart Microgrids

This paper presents a real-time power flow controller for VSIs （voltage source inverters） interfaced to low voltage microgrids. The proposed controller is modular, flexible, intelligent, inexpensive, portable, adaptive and designed to positively contribute in low voltage microgrids in which the lines R/X ratio is greater than the transmission lines. Therefore, the proposed control strategy is developed for operation in distribution lines. The controller strategy is different from the conventional grid-connected inverters which are designed based on transmission line characteristics. This controller, using a Texas Instrument general purpose DSP （digital signal processor）, is programmed and tuned using MATLAB/SIMULINK in order to enhance self-healing, reliability and stability of the grid. This general purpose controller makes proper decisions using its local measurements as the primary source of data. The controller has the capability of communicating with the adjacent controllers and sharing the information if/when needed. The power flow output of the inverter is tested for both islanded and grid-connected modes of operation. The inverter positively contributes to active and reactive power supply while operating in grid-connected mode. The proposed control method has been implemented on a Texas Instrument DSC （digital signal controller） chip and tested on a hardware test bench at the Alternative Energy Laboratory at WVU1T （West Virginia University Institute of Technology）. The system＇s experimental results veri~ the validity and efficiency of the proposed controller.

A game-theoretic method for prediction of microgrid growing trends in China

This paper presents a game-theoretic method to predict microgrid(MG) development tendency in China. As many distribution generators(DGs) are integrated in distribution systems, analysis of MG formation necessity is conducted from the aspect of DGs. In order to maximize the profit brought by DGs and to earn money from arbitrage, it may be necessary for customers to combine their DGs and loads and to construct an MG to obtain maximal control ability. A game model is built to emulate trading between MGs and the distribution system based on MG power control, in which both trading profit and outage cost are considered for each MG. Nash equilibrium(NE) is calculated, and sensitivities of NE to some boundary conditions are studied. The results show that variable MG trading prices with appropriate net generation cost(i.e., DG generation cost minus government subsidy price) may encourage the growth of MGs. Government subsidies, generation costs, and trading prices may also affect DG use, and therefore they may impact customer motivation to build MGs.

Multi-level multi-area hybrid automatic voltage control system and its trial operation in Northeast China Grid

In order to coordinate automatic voltage control （AVC） systems of a large interconnected system, a multi-level multi-area hybrid automatic voltage control （MLMA-HAVC） system was constructed. This system began its trial operation in the Northeast China Grid in January 2010, and for the first time in China and abroad it realized automatic close-loop control of multi-area and multi-level interconnected power grid and multi-objective self-approaching optimization in aspects of security, high quality and economic operation. This system has three breakthroughs in theory and engineering application： l） Established the MLMA-HAVC theory to solve multi-objective optimization of large-scale system; 2） proposed reactive power/voltage coordination control method to inhibit or further eliminate regional oscillations; 3） presented advanced state estimation algorithm to guarantee acquisition of high reliability data. This paper summarizes the basic principle of MLMA-HAVC, and reports engineering realization of MI ,MA-HAVC system in tha Northeast China Grid.

Study on ESS Control Strategy for Distribution Network with PV

Environmentally clean photovoltaic(PV)generation has found wider application,but the power f luctuation generated from PV can negatively impact the operation of power system.A properly designed energy storage system(ESS)can stabilize power system by absorbing and injecting instantaneous power.Suitable control strategy of ESS is studied in order to accommodate the power f luctuation.It adopts negative feedback which considers the relationship between real power and voltage in the distribution network because resistor is comparable to reactance of the lines in the distribution network.A universal model of ESS is established,the characteristic parameters such as time-delay of system response,limitation of charging and discharging and restraint of energy storage capacity are taken into account.The validity of the proposed model is verif ied by user-def ined modules in power system analysis software package(PSASP).The operation of PV generation at Wuhan Railway Station in both grid-connected mode and island mode at Wuhan Railway Station is analyzed in detail.The performances of the local distribution network with PV under different weather conditions are summarized,and the key parameter of ESS suitable for PV generation at Wuhan Railway Station is also recommended.

Study on the Online Mode of Micro-Grid

Smooth switchover of micro-grid from parallel operation mode to island operation mode is a signif icant method to guarantee the continuous power supply to important loads.This paper puts forward an online work mode on the basis of analyzing the features of parallel operation mode and island operation mode.According to the features of online work mode,the paper gives a f ixed and unf ixed DC bus voltage control strategy and builds the simulation model of unf ixed DC bus voltage control strategy based on Matlab/Simulink.The simulation results show that online work mode based on the unf ixed DC bus voltage control strategy can avoid the unstable problem caused by handoff process between parallel mode and island mode,ensure uninterrupted power supply for important loads,and achieve maximum power tracking of photovoltaic power generation,in addition to reducing the complexity and cost of the system.