Evaluation of the effect of high penetration of renewable energy sources (RES) on system frequency regulation using stochastic risk assessment technique (an approach based on improved cumulant)

Accurate wind power prediction can alleviate the negative influence on power system caused by the integration of wind farms into grid. In this paper, a novel combination model is proposed with the purpose of enhancing short-term wind power prediction precision. Singular spectrum analysis is utilized to decompose the original wind power series into the trend component and the fluctuation component. Then least squares support vector machine (LSSVM) is applied to forecast the trend component while deep belief network (DBN) is utilized to predict the fluctuation component. By this means, the performance advantages of LSSVM and DBN can be brought into full play. Moreover, the locality-sensitive hashing search algorithm is introduced to cluster the nearest training samples to further improve forecasting accuracy. Besides, the effect of LSSVM based on different kernel functions and the number of the nearest samples is investigated. The simulation results show that the normalized root mean square errors of the proposed model based on linear kernel function from1-step to 3-step forecasting are 2.13%, 5.03%, and 7.29%, respectively, which outperforms all the other comparison models. Therefore, it can be concluded that the proposed combination model provides a promising and effective alternative for short-term wind power prediction. KEYWORDS combination forecasting model, deep belief network, least squares support vector machine, locality-sensitive hashing, singular spectrum analysis, wind power

show abstract

“…The parameters b and β i can be obtained by solving Equation (22). Then the regression function for LSSVM can be expressed by…”

Section: Least Squares Support Vector Machinementioning

confidence: 99%

Retracted: Forecasting model for wind power integrating least squares support vector machine, singular spectrum analysis, deep belief network, and locality‐sensitive hashing

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, besides these benefits, their extensive deployment has posed various challenges in the energy market [6]. Considering the volatility and stochastic nature of renewable technologies operation, the efficient management of power systems, in terms of planning and operation, has been the subject of several publications [7][8][9][10][11][12]. In addition to this, the idea of energy storage has been developed [13], especially for non-interconnected islands [14].…”

Section: Introductionmentioning

confidence: 99%

Renewable Energy Sources Penetration in Greece: Characteristics and Seasonal Variation of the Electricity Demand Share Covering

2019

View full text Add to dashboard Cite

The significant penetration of renewables, in the Hellenic electricity system, during the last 12 years, was based on feed-in tariff-supporting schemes, according to the compliance to European Directives. The characteristics of this penetration are presented and analyzed in this paper based on real data. Photovoltaics, wind parks, hydroelectric plants, biomass-driven plants, and cogeneration systems are examined. The cost of the feed-in tariff incentives is qualified and analyzed. Simple but effective models are proposed to describe renewable seasonal variation: (a) A simple cosine model adequately describes the seasonal performance of various renewable technologies in terms of capacity factor; (b) a smart seasonal model based on the separation between winter and summer consumption activities (both following normal distributions) adequately describes the electricity consumption profile. The predicted values of renewable shares using the proposed models were also validated with historical data. Thus, the applied models can be used to forecast renewable shares under different penetration scenarios.

show abstract

“…The increase of the penetration of renewable agents in the energy mix [1], together with the necessity to maintain the stability of the electric power systems make the new grid codes more restrictive nowadays for grid-connected photovoltaic (PV) systems and other renewable agents [2][3][4][5]. For example, these systems must remain connected under certain conditions so as to improve the voltage profile of the utility grid when there are voltage sags [6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Modeling and Design of the Vector Control for a Three-Phase Single-Stage Grid-Connected PV System with LVRT Capability according to the Spanish Grid Code

et al. 2019

View full text Add to dashboard Cite

This article deals with the vector control in dq axes of a three-phase grid-connected photovoltaic system with single-stage topology and low-voltage-ride-through capability. The photovoltaic generator is built using an array of several series-parallel Suntech PV modules and is modeled as a Lookup Table (two-dimensional; 2-D). The requirements adopted when grid voltage sags occur are based in both the IEC 61400-21 European normative and the allowed amount of reactive power to be delivered according to the Spanish grid code, which avoids the disconnection of the inverter under grid faults by a limitation in the magnitude of the three-phase output inverter currents. For this, the calculation of the positive- and negative-sequences of the grid voltages is made and a conventional three-phase Phase-Locked Loop is used for the inverter-grid synchronization, allowing the control of the active and reactive powers solely with the dq components of the inverter currents. A detailed enhanced flowchart of the control algorithm with low-voltage-ride-through capability is presented and several simulations and experiments using Matlab/SIMULINK and the Controller Hardware-in-the-Loop simulation technique, respectively, are run for several types of one- and three-phase voltage sags in order to validate its behavior.

show abstract

Evaluation of the effect of high penetration of renewable energy sources (RES) on system frequency regulation using stochastic risk assessment technique (an approach based on improved cumulant)

Cited by 26 publications

References 24 publications

Retracted: Forecasting model for wind power integrating least squares support vector machine, singular spectrum analysis, deep belief network, and locality‐sensitive hashing

Retracted: Forecasting model for wind power integrating least squares support vector machine, singular spectrum analysis, deep belief network, and locality‐sensitive hashing

Renewable Energy Sources Penetration in Greece: Characteristics and Seasonal Variation of the Electricity Demand Share Covering

Modeling and Design of the Vector Control for a Three-Phase Single-Stage Grid-Connected PV System with LVRT Capability according to the Spanish Grid Code

Contact Info

Product

Resources

About