Search

This paper presents a new probabilistic forecasting model of the hourly mean power production in a Photovoltaic (PV) plant. It uses the minimal information and it can provide probabilistic forecasts in the form of quantiles for the desired horizon, which ranges from the next hours to any day in the future. The proposed model only needs a time series of hourly mean power production in the PV plant, and it is intended to fill a gap in international literature where hardly any model has been proposed as a reference for comparison or benchmarking purposes with other probabilistic forecasting models. The performance of the proposed forecasting model is tested, in a case study, with the time series of hourly mean power production in a PV plant with 1.9 MW capacity. The results show an improvement with respect to the reference probabilistic PV power forecasting models reported in the literature.

The integration of renewable energies, specifically solar energy, in electric distribution systems is increasingly common. For an optimal operation, it is very important to forecast the final net demand of the power distribution network, considering the variability of solar energy combined with the variability of the electric energy consumption habits of population. This paper presents the methodology followed to forecast the net demand in a power distribution substation. Two approaches are considered, the net demand direct prediction, and the indirect prediction with the forecasts of PV power generation and load demand. Artificial Neural Network (ANN) based models and autoregressive models with exogenous variables (ARX) are used to predict the net demand, directly and indirectly, for the 24 hours of the day-ahead. The methodology is applied to a medium voltage distribution substation and the direct and indirect forecasts are compared.

The development of Short-Term Forecasting Techniques has a great importance for power system scheduling and managing. Therefore, many recent research papers have dealt with the proposal of new forecasting models searching for higher efficiency and accuracy. Several kinds of artificial intelligence (AI) techniques have provided good performance at predicting and their efficiency mainly depends on the characteristics of the time series data under study. Load forecasting has been widely studied in recent decades and models providing mean absolute percentage errors (MAPEs) below 5% have been proposed. On the other hand, short-term generation forecasting models for photovoltaic plants have been more recently developed and the MAPEs are in general still far from those achieved from load forecasting models. The aim of this paper is to propose a methodology that could help power systems or aggregators to make up for the lack of accuracy of the current forecasting methods when predicting renewable energy generation. The proposed methodology is carried out in three consecutive steps: (1) short-term forecasting of energy consumption and renewable generation; (2) classification of daily pattern for the renewable generation data using Dynamic Time Warping; (3) application of Demand Response strategies using Physically Based Load Models. Real data from a small town in Spain were used to illustrate the performance and efficiency of the proposed procedure.

The expansion of electric distribution networks in new geographic areas is a tedious task. Once the position of the low voltage power substations has been decided, the planning engineers need to select the routes for the new power lines ensuring more efficient connections among the substations. This paper presents the methodology followed to plan the set of overhead power lines which achieves the optimal distribution network with the minimum installation and maintenance costs. The methodology is based on the use of Geographic Information Systems, which provide the needed functions to find feasible and economic routes for the new overhead power lines linking the substations, and an evolutionary algorithm which selects the optimal links. The application of the proposed methodology allows finding the optimal solution under an economic perspective in an automatic manner.

This paper presents the results obtained in the development of probabilistic short-term forecasting models of the power production in a photovoltaic power plant for the day-ahead. The probabilistic models are based on quantile regression neural networks. The structure of such neural networks is optimized with a genetic algorithm which selects the values for the main parameters of the neural network and the variables used as inputs. These input variables are selected among a set of variables which includes chronological, astronomical and forecasted weather variables related to the location of the power plant. The forecasts correspond to quantiles of the hourly power generation in the photovoltaic power plant for the daytime hours of the day-ahead. The forecasts are obtained in the first hours of the day, allowing their use for preparing bid offers for the day-ahead in electricity markets.

The construction of new high voltage overhead power lines (HVOPLs) has become a controversial issue for electricity companies due to social opposition. Citizens are concerned about how these power lines may have an impact on their lives, basically caused by their effects on health and safety. Visual impact is one of the most easily perceived. Although there are several published works that deal with the assessment of the visual impact produced by HVOPLs, no methodology has been proposed to assess this impact from an objective perspective. This work presents an original methodology which helps to identify the optimal routes for a new HVOPL under an objective observability criterion, enabling the selection of those with the lowest visibility in a zone. The application of the proposed methodology achieves a set of routes that links new HVOPL origin and destination points creating a corridor which includes all possible routes with an observability of its towers under a threshold limit. This methodology is illustrated by a real-life use corresponding to the selection of the route with least observability for a new power line in La Rioja (Spain). The results obtained may help to achieve a consensus between key stakeholders since it is focused on the specific issues of the planned HVOPL and its observability from an objective perspective.

This paper presents a new statistical short-term forecasting system for a grid-connected photovoltaic (PV) plant. The proposed system comprises three modules composed of two numerical weather prediction models and an artificial neural network based model. The first two modules are used to forecast weather variables used by the third module, which has been selected from a set of different models. The final forecast value is the hourly energy production in the PV plant. The forecasting horizon ranges from 1 to 39 h, covering all of the following day. The forecast values can be used for determining the most favourable hours to carry out maintenance tasks in the plant, and for preparing bid offers to the electricity market.

Despite the advantages that power plants based on renewable energies offer, there are some restrictions to the social acceptance of these facilities. One of these restrictions is the visual impact that large power plants may generate on people. This paper presents a new methodology for ranking the feasible places in a zone for the construction of new photovoltaic (PV) power plants according to their visibility. The methodology is based on the fuzzy viewshed and the distance decay methods, which enable to calculate the maximum number of hours in a mean day in which the new PV plant may be viewed by each possible observer. This number is related to the inhabitants in the zone, the size of the plant, the possible observers from paths and roads, and their distance to the PV plant. The proposed methodology is implemented in a Geographical Information System which allows the presentation of visual results that help to identify the best areas in the zone under study. This methodology can be useful to local authorities who have to authorize the installation of the new power plant, or investors who are trying to find the best locations from the point of view of visual impact.