17 research outputs found
Photovoltaic Power Nowcasting Using Decision-Trees Based Algorithms and Neural Networks
No full textPrecise Photovoltaic (PV) power forecasting tools are needed to integrate PV into the new framework of the energy sector. Also, the related intermittent and random nature needs to be appropriately considered. In this context, this paper examines various machine learning algorithms used for one hour ahead forecasting of PV power production. Specifically, the performances of two Long Short-Term Memory (LSTM) recurrent neural networks, a Gradient Boost Machine (GBM) model and an Extreme Gradient Boosting (XGB) model, are compared. Six years of data are retrieved from the 81 kW PV power plant in the Savona campus of the University of Genoa and are used to train and test the algorithms. The performances of all the algorithms are compared over the original dataset, composed of meteorological variables linked with the PV production, a dataset using seasonal and trend decomposition (STL) of the meteorological variables, and some reduced datasets that mimic the situation in which some of the features are not available at least for some time steps. By comparing the results through different case studies, it can be justified that the XGB outperforms the other algorithms and the STL decomposition is helpful in increasing the performance of the model
An Energy Management System to Optimize the Participation in the Day Ahead and Ancillary Service Markets
No full textThis paper presents the evolution of an Energy Management System developed by University of Genoa aimed at minimizing the operation costs of plants and Microgrids (MGs). In the updated version, the Ancillary Service Market (ASM) and Day Ahead Market (DAM) mechanisms are modelled to include the possibility of trading in these markets. Since the Transmission System Operator (TSO) rejection or acceptance in the ASM cannot be forecasted, a statistical approach is proposed. Specifically, the optimization process is divided in two steps: initially the optimal dispatching program is computed, identifying DAM offers and ASM bid and offers that can be proposed. Then, a Monte Carlo method is implemented: by receiving a user defined acceptance rate, the TSO decisions are simulated by extracting sets of awarded proposals from a Probability Density Function (PDF). For each extraction, the second step of the optimization re-dispatches the units based on the bidding program. A PDF of the revenues/costs is the final outcome. Thereafter, the statistical moments of the resulting PDF can be analysed to estimate the profitability of the participation to the markets. A test performed on a real plant over one year demonstrates that longtime horizons may be simulated within reasonable computational time allowing to maintain a high level of details to model devices and markets
Cost Optimization Incorporating Photovoltaic Power Forecasts Using Neural Networks in an Energy Management System
No full textThis paper introduces a receding horizon method designed to integrate updated Photovoltaic (PV) power generation forecasts into an effective Energy Management System (EMS). At first, three RNN PV-based forecasting algorithms are compared to find the best architecture based on evaluation metrics, and the most accurate is utilized to estimate the PV power production. Secondly, the best-performing algorithm feeds into the EMS PV power production data. In addition, the feeding process compares two approaches. In the first one, PV forecasts are updated every hour, and the EMS is run to optimize dispatch decisions for the upcoming 23 hours. In the second method, the PV forecast is received at midnight, and the EMS optimizes decisions. The proposed joint approach is verified using an accurate EMS and by comparing the results with the real PV power data benchmark. Hence, the results indicate that the dispatching of units can be accurately predicted using the proposed forecasting techniques, with the hourly update approach yielding the most precise outcomes
A Simulator for Long Term Planning and Real Time Scheduling of Polygenerative Microgrids
No full textA sliding mode based controller for no inertia islanded microgrids
No full textThe papers presents a new concept for controlling voltage and frequency in islanded microgrids composed by a Battery Energy Storage System (BESS) and Photo-Voltaic (PV) Units. The proposed approach is totally decentralized as each source is equipped with a purely local controller and no communication infrastructure is needed. Moreover, a centralized secondary control is not required as the developed local controllers are able to nullify both frequency and voltage errors. Finally, the physical constraints related to BESS power and State Of Charge (SOC) limits are accounted and some theoretical hints are provided to justify why the frequency can be used as a triggering signal for the controllers to switch among the different operation modes even in absence of synchronous machines directly connected to the grid
Assessment of unsymmetrical voltage sag effects on AC adjustable speed drives
No full textThis paper analyses the influence of unsymmetrical voltage sags on the increase of torque and speed deviation induction motor adjustable speed drives. The three following general types of induction motor drives control are analyzed: scalar controlled (V/Hz), rotor-field-oriented (RFO) and direct-torque-controlled(DTC). The analytical expression for variations of dc link voltage incorporated into the corresponding drive models and formulas for assessment of current/torque deviation are derived depending on the applied control algorithm. Afterwards, the presented theoretical results for the deterioration of motor drive performance due to voltage sags are validated experimentally. Measurements of sag-caused mechanical vibrations are used for the additional verification of the obtained results. .</jats:p
Application of Repetitive Ripple Estimator in Synchronization of Three Phase Grid Tie Inverters
No full text
Voltage sag drop in speed minimization in modern adjustable speed drives
No full textThis paper researches behavior of rotor field oriented (RFO) and direct torque controlled (DTC) drives in speed controlled application in voltage sags circumstances. Problems in application will be able to appear especially in work cases with speed and torque close to rated, even in a case when typical voltage tolerance curves show no drive trips. To overcome appeared drop in speed it was posed a field weakening algorithm during voltage sag. Analytic calculation and numerical simulation were presented in detail in this work. Knowing delay in RFO flux response and prompt DTC flux recall, methods for dynamic performance improving were advised.</jats:p
