• Energy Research

In this paper, we propose to study four meteorological and seasonal time series coupled with a multi-layer perceptron (MLP) modeling. We chose to combine two transfer functions for the nodes of the hidden layer, and to use a temporal indicator (time index as input) in order to take into account the seasonal aspect of the studied time series. The results of the prediction concern two years of measurements and the learning step, eight independent years. We show that this methodology can improve the accuracy of meteorological data estimation compared to a classical MLP modelling with a homogenous transfer function.

Reliable forecasting methods increase the integration level of stochastic production and reduce cost of intermittence of photovoltaic production. This paper proposes a solar forecasting model for short time horizons, i.e. one to six hours ahead. In this time-range, machine learning methods have proven their efficiency. But their application requires that the solar irradiation time series is stationary which can be realized by calculating the clear sky global horizontal solar irradiance index (CSI), depending on certain meteorological parameters. This step is delicate and often generates additional uncertainty if conditions underlying the calculation of the CSI are not well-defined and/or unknown. As a novel alternative, we introduce a so-called periodic autoregressive (PAR) model. We discuss the computation of post-sample point forecasts and forecast intervals. We show the forecasting accuracy of the model via a real data set, i.e., the global horizontal solar irradiation (GHI) measured at two meteorological stations located at Corsica Island, France. In particular, and as opposed to methods based on CSI, a PAR model helps to improve forecast accuracy, especially for short forecast horizons. In all the cases, PAR is more appropriate than persistence, and smart persistence. Moreover, smart persistence based on the typical meteorological year gives more reliable results than when based on CSI.

This paper presents an application of Artificial Neural Networks (ANNs) in the renewable energy domain and, more particularly, to predict solar energy. We look at the Multi-Layer Perceptron (MLP) network which has been the most used of ANNs architectures both in the renewable energy domain and in the time series forecasting. In previous studies, we have demonstrated that an optimized ANN with endogenous inputs can forecast the solar radiation on a horizontal surface with acceptable errors. Thus we propose to study the contribution of exogenous meteorological data to our optimized PMC and compare with different forecasting methods used previously: a naive forecaster like persistence and an ANN with preprocessing using only endogenous inputs. Although intuitively the use of meteorological data may increase the quality of prediction, the obtained results are relatively mixed. The use of exogenous data generates a decrease of nRMSE between 0.5% and 1% for the two studied locations. The absolute error (RMSE) is decreased by 52 Wh/m2/day in the simple endogenous case and 335 Wh/m2/day for the persistence forecast.

Numerous methods exist and were developed for global radiation forecasting. The two most popular types are the numerical weather predictions (NWP) and the predictions using stochastic approaches. We propose to compute a parameter noted constructed in part from the mutual information which is a quantity that measures the mutual dependence of two variables. Both of these are calculated with the objective to establish the more relevant method between NWP and stochastic models concerning the current problem. International Journal of Energy Technology and Policy (2014)

Abstract A global horizontal irradiation prediction (from 1 h to 6 h) is performed using 2 persistence models (simple and “smart” ones) and 4 machine learning tools belonging to the regression trees methods family (normal, pruned, boosted and bagged). A prediction band is associated to each forecast using methodologies based on: bootstrap sampling and k-fold approach, mutual information, stationary time series process with clear sky model, quantiles estimation and cumulative distribution function. New reliability indexes (gamma index and gamma test) are built from the mean interval length (MIL) and prediction interval coverage probability (PCIP). With such methods and error metrics, good prediction bands are estimated for Ajaccio (France) with a MIL close to 113 Wh/m2, a PCIP reaching 70% and a gamma index lower than 0.9.

Abstract This paper features a Multi-Objective Particle Swarm Optimization for a power plant integrated in a micro grid. The plant modeling is flexible and can be set up for a wide range of sources, storages and loads. The model contains 12 parameters representing the size of each component which are modeled with power dependent efficiencies. The optimization goals are to reduce the annualized cost of system and the imported energy without failing to supply the load. The study is carried out in two locations (Tilos and Ajaccio) to show the problem dependence on the meteorological conditions. As a result, a pattern stands out for each site with a preferred source and a plant configuration according to the energetic autonomy wanted.