Search

This paper proposes an hybrid approach for short term solar intensity forecasting, which combines different forecasting methodologies with a clustering algorithm, which plays the role of data filter, in order to support the selection of the best data for training. A set of methodologies based on Artificial Neural Networks (ANN) and Support Vector Machines (SVM), used for short term solar irradiance forecast, is implemented and compared in order to facilitate the selection of the most appropriate methods and respective parameters according to the available information and needs. Data from the Brazilian city of Florianópolis, in the state of Santa Catarina, has been used to illustrate the methods applicability and conclusions. The dataset comprises the years of 1990 to 1999 and includes four solar irradiance components as well as other meteorological variables, such as temperature, wind speed and humidity. Conclusions about the irradiance components, parameters and the proposed clustering mechanism are presented. The results are studied and analysed considering both efficiency and effectiveness of the results. The experimental findings show that the hybrid model, combining a SVM approach with a clustering mechanism, to filter the data used for training, achieved promising results, outperforming the approaches without clustering., This work has been developed under the European Union’s Horizon 2020 research and innovation programme, Marie Sklodowska-Curie grant agreement No 703689 (project ADAPT); EUREKA - ITEA2 Project FUSE-IT (ITEA-13023) and Project GREEDI (ANI|P2020 17822).

The increase of renewable based generation as alternative power source brings an added uncertainty to power systems. The intermittent nature of renewable resources, such as wind speed and solar intensity, requires the use of adequate forecast methodologies to support the management and integration of this type of energy resources. This paper proposes a clustering methodology to group historic data according to the data correlation and relevance for different contexts of use. Using the clustering process as a data filter only the most adequate data is used for the training process of forecasting methodologies. Artificial Neural Networks and Support Vector Machines are used to test and compare the quality of forecasts when using the proposed methodology to select the training data. Data from the Brazilian city of Florianopolis, Santa Catarina, has been used, including solar irradiance components and other meteorological variables, e.g. temperature, wind speed and humidity. Experimental findings show that using the proposed method to filter data used for training ANN and SVM achieved promising results, outperforming the approaches without clustering.

Heat Pumps to supply hot-water for domestic consumption are widely used especially in countries where electric energy is also employed for this purpose. Brazil is a country where most of the domestic hot-water requirements are supplied by electric energy, but basically it is done with electric showers. This solution, although cheap for the user in terms of initial investment, has a strong impact on the generation, transmission and distribution – GTD costs. Electric showers have an average power of more than 5 kW, and are a strong contribution to the residential electric energy end use (around 24% in Brazil (Procel/Eletrobras, 2007)). Also, they are partially responsible by the “peak hour” of the power consumption in the residential sector that occurs from 18:00 to 21:00 hours in Brazil. The consumption growth observed in the last years leads to a lack of reliability of the system, and energy efficiency measures are necessary to avoid risks and to postpone investments in GTD. Solar hot-water systems have been used as an effective way to mitigate the problems caused by the intensive use of electric showers, however, this solution faces some problems when used in low-income housing units: absence of hot-water piping, inadequate structure to install collectors and thermal storage, increase of specific thermal energy costs for small systems, and use of an electric shower as the backup system.

This paper aims at presenting the main products of Solar and Wind Energy Resource Assessment (SWERA) project for Brazil and how this information on solar and wind energy resources can be used to spread out the energy production matrix improving the energy security and reducing the dependency on fossil fuels. The SWERA project were developed in Brazil under the coordination of Climate and Environmental Division of CPTEC/INPE and illustrates how the scientific research in meteorology and climatology can contribute to the energy planning and policies developed in Brazil. The products of SWERA project include information that will be extremely useful to foster capital investments providing private sector and government institutions with reliable database of energy resources. The paper presents the main results in solar and wind energy mapping and discusses some renewable energy scenarios taking in account the technologies in use currently.