Search

This study presents how to improve the short-term forecast of photovoltaic plant's output power by applying the Long Short-Term Memory, LSTM, neural networks for industrial-scale solar power plants in Vietnam under possible curtailment operation. Since the actual output power does not correspond to the available power, new techniques (Global Horizontal Irradiance - GHI interval division, P/GHI factor addition (P - Power)) have been designed and applied for processing errors and missing data. The prediction model (LSTM network, structure of hidden layers, number of nodes) has been developed by the authors in a previous work. In this new version of the model, the training technique is improved by using validation and experiments to determine the appropriate relevant parameters. The forecast results show that the proposed new method is more efficient than the old method, as the MAPE (Mean Absolute Percentage Error) forecast error is reduced by 6.059% and the RMSE (Root Mean Square Error) is reduced by 6.710%.

This paper proposes a new model for short-term forecasting power generation capacity of large-scale solar power plant (SPP) in Vietnam considering the fluctuations of weather factors when applying the Long Short-Term Memory networks (LSTM) algorithm. At first, a configuration of the model based on the LSTM algorithm is selected in accordance with the weather and operating conditions of SPP in Vietnam. Not only different structures of LSTM model but also other conventional forecasting methods for time series data are compared in terms of error accuracy of forecast on test data set to evaluate the effectiveness and select the most suitable LSTM configuration. The most suitable configuration has been selected and applied on Thanh Thanh Cong No 1 (TTC) SPP with 2 input cases: real historical weather data and forecasted weather data. The results show that second case gives a much larger Mean Absolute Percentage Error (MAPE) than that of first case (10.857% versus 3.491%). Based on above experiment, new additional features are proposed to improve the selected LSTM model precision and cope with the problem of error due to weather forecast data. The result of the application of the new prediction model for TTC solar plant indicates that the MAPE is reduced from 10.857% to 9.881%.

With the increase of load demand and distributed photovoltaic (PV) systems on the electric grid, maintaining the required voltage tolerance at the point delivery (customer homes/businesses) is becoming more challenging for electric power utilities. In a residential neighborhood, the peak load typically occurs in the early evening hours while maximum PV generation occurs during mid day. As a result, the lowest voltage operating points occur in the evening hours; whereas the highest voltage operating point occur during the day, when the PV systems are injecting more power than what is locally consumed. Static VAR Compensators (SVCs) can be used to mitigate voltage violations and smooth out the overall profile of a distribution feeder by managing the voltage at the secondary side of distribution service transformers. In this paper, a new method to optimize the placement of SVC devices in a residential neighborhood on the island of Maui, Hawaii, USA with highly distributed PV penetration is presented as a case study using real data to show the efficiency of the proposed optimal placement methodology.

In this paper, a droop coefficients regulation methodology is proposed for an islanded microgrid to optimize the power losses. Based on the P-f and Q-V relations to adjust the droop coefficients at every loading condition, the optimized operating set point generates minimum power losses operation while satisfying the constraints of voltage and frequency limitation. A 9-bus case study is here implemented to show the effectiveness of this new approach as well as the improved operation quality of the system.

This paper shows how minimum cost energy management can be carried out for islanded micro-grids considering an expanded state that also includes the system's frequency. Each of the configurations outputted by the energy management system at each hour are indeed technically sound and coherent from the point of view of generation-consumption balancing by exploiting a frequency dependent load flow algorithm. A Glow-worm Swarm Optimization (GSO) algorithm carried out in a 24 hour time frame provides optimized results. A test has been carried out for a residential PV-Storage-Microturbine islanded micro-grid to show the feasibility as well as the efficiency of the proposed approach and results are compared to an existing solution method recently proposed by the authors.