In this paper, a generalized formulation for intelligent energy management of a microgrid is proposed using Artificial Intelligence (AI) techniques jointly with linear programming based multiobjective optimization. The proposed Multiobjective Intelligent Energy Management (MIEM) aims to minimize the operation cost and the environmental impact of a microgrid taking into account its pre-operational variables as future availability of renewable energies and load demand. An artificial Neural Network Ensemble (NNE) is developed to predict 24 hour ahead photovoltaic generation, one hour ahead wind power generation and load demand. The proposed machine learning is characterized by enhanced learning model and generalization capability. The efficiency of the microgrid operation strongly depends on the battery scheduling process, which cannot be achieved through conventional optimization formulation. In this study, a fuzzy logic expert system is used for battery scheduling. The proposed approach can handle uncertainties regarding to the fuzzy environment of the overall microgrid operation and the uncertainty related to the forecasted parameters. The results shows considerable minimization on operation cost and emission level comparing to literature microgrid energy management approaches based on opportunity charging and heuristic flowchart battery management. Index Terms-MultiobjectiveIntelligent Energy Management (MIEM), Neural Network Ensemble (NNE), Fuzzy Logic, Shortterm Forecasting, Microgrid.

No abstract

Necessity to solve global warming problems by reducing CO 2 emission in electricity generation field had led to increasing interest in Micro-Grids (MGs), especially those contain the renewable sources such as solar and wind generation. Wind speed fluctuations cause high variations in the output power of wind turbine which cause fluctuation in frequency and voltage of the MG during islanding mode and originate stability problems. In this study, three techniques are proposed for solving and reducing the consequences of this problem. In the first technique, we develop a new fuzzy logic pitch angle controller. In the second technique, we design an energy storage ultra capacitor which directly smoothes the output power of the wind turbine and enhance the performance of the MG during the islanding mode. In the third technique, storage batteries are used to support the MG in the islanding mode.Index Terms-Micro-Grid, dynamic response, islanding, fuzzy pitch controller, wind power smoothing, ultra capacitor, storage batteries.

No abstract

This paper presents the applicability of artificial neural networks for 24 hour ahead solar power generation forecasting of a 20 kW photovoltaic system, the developed forecasting is suitable for a reliable Microgrid energy management. In total four neural networks were proposed, namely: multi-layred perceptron, radial basis function, recurrent and a neural network ensemble consisting in ensemble of bagged networks. Forecasting reliability of the proposed neural networks was carried out in terms forecasting error performance basing on statistical and graphical methods. The experimental results showed that all the proposed networks achieved an acceptable forecasting accuracy. In term of comparison the neural network ensemble gives the highest precision forecasting comparing to the conventional networks. In fact, each network of the ensemble over-fits to some extent and leads to a diversity which enhances the noise tolerance and the forecasting generalization performance comparing to the conventional networks.