Loading...
9 results
Search Results
Now showing 1 - 9 of 9
- A bat optimized neural network and wavelet transform approach for short-term price forecastingPublication . Bento, P.M.R.; Pombo, José Álvaro Nunes; Calado, M. do Rosário; Mariano, S.In the competitive power industry environment, electricity price forecasting is a fundamental task when market participants decide upon bidding strategies. This has led researchers in the last years to intensely search for accurate forecasting methods, contributing to better risk assessment, with significant financial repercussions. This paper presents a hybrid method that combines similar and recent day-based selection, correlation and wavelet analysis in a pre-processing stage. Afterwards a feedforward neural network is used alongside Bat and Scaled Conjugate Gradient Algorithms to improve the traditional neural network learning capability. Another feature is the method's capacity to fine-tune neural network architecture and wavelet decomposition, for which there is no optimal paradigm. Numerical testing was applied in a day-ahead framework to historical data pertaining to Spanish and Pennsylvania-New Jersey-Maryland (PJM) electricity markets, revealing positive forecasting results in comparison with other state-of-the-art methods.
- Daily Operation Optimization of a Hybrid Energy System Considering a Short-Term Electricity Price Forecast SchemePublication . Bento, P.M.R.; Nunes, H.G.G.; Pombo, José Álvaro Nunes; Calado, M. do Rosário; Mariano, S.The scenario where the renewable generation penetration is steadily on the rise in an increasingly atomized system, with much of the installed capacity “sitting” on a distribution level, is in clear contrast with the “old paradigm” of a natural oligopoly formed by vertical structures. Thereby, the fading of the classical producer–consumer division to a broader prosumer “concept” is fostered. This crucial transition will tackle environmental harms associated with conventional energy sources, especially in this age where a greater concern regarding sustainability and environmental protection exists. The “smoothness” of this transition from a reliable conventional generation mix to a more volatile and “parti-colored" one will be particularly challenging, given escalating electricity demands arising from transportation electrification and proliferation of demand-response mechanisms. In this foreseeable framework, proper Hybrid Energy Systems sizing, and operation strategies will be crucial to dictate the electric power system’s contribution to the “green” agenda. This paper presents an optimal power dispatch strategy for grid-connected/off-grid hybrid energy systems with storage capabilities. The Short-Term Price Forecast information as an important decision-making tool for market players will guide the cost side dispatch strategy, alongside with the storage availability. Different scenarios were examined to highlight the effectiveness of the proposed approach.
- Hybrid artificial intelligence algorithms for short-term load and price forecasting in competitive electric marketsPublication . Bento, Pedro Miguel Rocha; Mariano, Silvio José Pinto SimõesThe liberalization and deregulation of electric markets forced the various participants to accommodate several challenges, including: a considerable accumulation of new generation capacity from renewable sources (fundamentally wind energy), the unpredictability associated with these new forms of generation and new consumption patterns, contributing to further electricity prices volatility (e.g. the Iberian market). Given the competitive framework in which market participants operate, the existence of efficient computational forecasting techniques is a distinctive factor. Based on these forecasts a suitable bidding strategy and an effective generation systems operation planning is achieved, together with an improved installed transmission capacity exploitation, results in maximized profits, all this contributing to a better energy resources utilization. This dissertation presents a new hybrid method for load and electricity prices forecasting, for one day ahead time horizon. The optimization scheme presented in this method, combines the efforts from different techniques, notably artificial neural networks, several optimization algorithms and wavelet transform. The method’s validation was made using different real case studies. The subsequent comparison (accuracy wise) with published results, in reference journals, validated the proposed hybrid method suitability.
- Collaborative swarm intelligence to estimate PV parametersPublication . Nunes, H.G.G.; Pombo, José Álvaro Nunes; Bento, P.M.R.; Mariano, S.; Calado, M. Do RosárioTo properly evaluate, control and optimize photovoltaic (PV) systems, it is crucial to accurately estimate the equivalent electric circuit parameters from the respective mathematical models that characterize the PV cells or modules behavior. This is currently a hot research topic that has attracted the attention of numerous researchers. In this paper, we propose a new hybrid methodology that combines diversification and intensification mechanisms from different metaheuristics (MHs) to estimate PV parameters precisely. The proposed methodology has the capacity to adapt to the specific optimization problem and maintain diversity when building solutions, thus mitigating premature convergence and population stagnation. This methodology can incorporate several MHs (two or more swarms) with different potentialities, enabling a good balance between diversification and intensification mechanisms. Furthermore, it is able to explore a multidimensional search space in different regions simultaneously. To validate its performance, the proposed methodology was compared with other wellestablished MHs in several benchmark functions, and used to estimate PV parameters in single and double-diode models in two case studies, the first using standard literature data, and the second using measured data from a real application with and without the occurrence of partial shading. The proposed methodology was able to find highly accurate solutions with reduced computational cost and high reliability. Comparisons with the other MHs demonstrate that the proposed methodology presents a very competitive performance when solving the PV parameter estimation problem.
- A Modified Multidimension Diode Model for PV Parameters Identification Using Guaranteed Convergence Particle Swarm Optimization AlgorithmPublication . Nunes, H.G.G.; Bento, P.M.R.; Pombo, José Álvaro Nunes; Mariano, S.; Calado, M. do RosárioThis paper proposes a modified multidimension diode model to identify the photovoltaic (PV) parameters using the guaranteed convergence particle swarm optimization algorithm. The main advantage of this model is that it allows adjusting the number of diodes of the PV model by finding the configuration that most accurately characterizes a PV device under a certain operating condition and of different PV technologies. The proposed model was validated from experimental data measured at different irradiance and temperature levels, as well as for six different PV technologies. The results show that the model is able to accurately characterize the behaviour of PV devices.
- Daily Operation Optimization for Grid-Connected Hybrid System Considering Short-Term Electricity Price Forecast SchemePublication . Bento, P.M.R.; Nunes, H.G.G.; Álvaro Nunes Pombo, José; Mariano, S.; Calado, M. do RosárioWith an increasing public and governmental awareness regarding environment protection and sustainable resources, hand-in-hand with an escalating electricity demand, the exponential growth of renewable energy generation capacity has been the “answer”. Mitigating the environmental harms associated with the more conventional energy sources such as: coal, oil, gas and nuclear. Nonetheless, some challenges remain, particularly concerning the integration of these technologies into the conventional generation mix. Hybrid energy systems allow a paradigm shift from a concentrated conventional generation to a more distributed one. This paper discusses the optimized PVwind with hydro and battery storage capabilities for a gridconnected application considering the Short-Term Price Forecast information. The proposed technique has been tested in different scenarios, and results demonstrate the effectiveness of the proposed approach.
- Optimization of neural network with wavelet transform and improved data selection using bat algorithm for short-term load forecastingPublication . Bento, P.M.R.; Pombo, José Álvaro Nunes; Calado, M. Do Rosário; Mariano, S.Short-term load forecasting is very important for reliable power system operation, even more so under electricity market deregulation and integration of renewable resources framework. This paper presents a new enhanced method for one day ahead load forecast, combing improved data selection and features extraction techniques (similar/recent day-based selection, correlation and wavelet analysis), which brings more “regularity” to the load time-series, an important precondition for the successful application of neural networks. A combination of Bat and Scaled Conjugate Gradient Algorithms is proposed to improve neural network learning capability. Another feature is the method's capacity to fine-tune neural network architecture and wavelet decomposition, for which there is no optimal paradigm. Numerical testing using the Portuguese national system load, and the regional (state) loads of New England and New York, revealed promising forecasting results in comparison with other state-of-the-art methods, therefore proving the effectiveness of the assembled methodology.
- Short-Term Load Forecasting using optimized LSTM Networks via Improved Bat AlgorithmPublication . Bento, P.M.R.; Pombo, José Álvaro Nunes; Mariano, S.; Calado, M. Do RosárioShort-term load forecasting plays a preponderant role in the daily basis system's operation and planning. The state- of-the-art comprises a far-reaching set of methodologies, which are traditionally based on time-series analysis and multilayer neural networks. In particular, the existence of countless neural network architectures has highlighted its ability to cope with 'hard' nonlinear approximation tasks, thus making them appropriate to perform load forecasts. Following this successful path, long short-term memory networks were employed in an optimized arrangement as forecasters, this type of recurrent neural networks has received in recent years a renewed interest for machine learning tasks. Firstly, a preprocessing stage takes place, where through the selection of similar days and correlation analysis, meaningful statistics and characteristics are extracted from the load time-series, to assemble the proper training sets. Then, Bat Algorithm is used to excel the long short-term memory network functioning, by fine-tuning its size and its learning hyperparameters. Numerical testing conducted on the Portuguese load time-series reveals promising forecasting results in an overall assessment, when compared with other state-of-the-art methods.
- Spot price forecasting for best trading strategy decision support in the Iberian electricity marketPublication . Magalhães, Bianca G.; Bento, Pedro M. R.; Pombo, José; Calado, M. do Rosário; Mariano, Sílvio J. P S.The increasing volatility in electricity markets has reinforced the need for better trading strategies by both sellers and buyers to limit the exposure to losses. Accordingly, this paper proposes an electricity trading strategy based on a mid-term forecast of the average spot price and a risk premium analysis based on this forecast. This strategy can help traders (buyers and sellers) decide whether to trade in the futures market (of varying monthly maturity) or to wait and trade in the spot market. The forecast model consists of an Artificial Neural Network trained with the Long Short Term Memory architecture to predict the average monthly spot prices, using only market price-related data as input variables. Statistical analysis verified the correlation and dependency between variables. The forecast model was trained, validated and tested with price data from the Iberian Electricity Market (MIBEL), in particular the Spanish zone, between January 2015 and August 2019. The last year of this period was reserved for testing the performance of the proposed forecast model and trading strategy. For comparison purposes, the results of a forecasting model trained with the Extreme Learning Machine over the same period are also presented. In addition, the forecasted value of the average monthly spot price was used to perform a risk premium analysis. The results were promising, as they indicated benefits for traders adopting the proposed trading strategy, proving the potential of the forecast model and the risk premium analysis based on this forecast.