A statistically-driven Coral Reef Optimization algorithm for optimal size reduction of time series

Durán-Rosal, Antonio Manuel; Gutiérrez, Pedro Antonio; Salcedo‐Sanz, Sancho; Hervás-Martı́nez, César

doi:10.1016/j.asoc.2017.11.037

Cited by 27 publications

(17 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent papers addressing wind power forecasts could be broadly classified into 5 categories: papers focused on how to increase NWP accuracy [4][5][6][7][8], good-practice prediction guidelines [9][10][11], comparisons of accuracy across prediction models [12][13][14][15], hybrid and ensemble methods [16][17][18][19][20][21][22][23][24][25][26][27], and conventional methods improved by, among other things, preprocessing [28][29][30][31][32][33][34][35]. At this point, clear distinction should be made between hybrid, ensemble and improved models.…”

Section: Related Workmentioning

confidence: 99%

“…Papers concerning improved models are more data-focused. Durán-Rosal et al, 2018 [28] propose an algorithm for optimal reduction of the size of time series and the authors of [29] investigate the influence of reduced numerical weather prediction (NWP) data on forecast quality. Research by Yu et al, 2020 [30] and Fan et al, 2020 [31] focuses on assimilating spatial data with Graph Networks, while Li et al, 2020 [32] present an adaptive time resolution method to deal with the error hidden in the data due to error averaging.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid and Ensemble Methods of Two Days Ahead Forecasts of Electric Energy Production in a Small Wind Turbine

et al. 2021

View full text Add to dashboard Cite

The ability to forecast electricity generation for a small wind turbine is important both on a larger scale where there are many such turbines (because it creates problems for networks managed by distribution system operators) and for prosumers to allow current energy consumption planning. It is also important for owners of small energy systems in order to optimize the use of various energy sources and facilitate energy storage. The research presented here addresses an original, rarely predicted 48 h forecasting horizon for small wind turbines. This topic has been rather underrepresented in research, especially in comparison with forecasts for large wind farms. Wind speed forecasts with a 48 h horizon are also rarely used as input data. We have analyzed the available data to identify potentially useful explanatory variables for forecasting models. Eight sets with increasing data amounts were created to analyze the influence of the types and amounts of data on forecast quality. Hybrid, ensemble and single methods are used for predictions, including machine learning (ML) solutions like long short-term memory (LSTM), multi-layer perceptron (MLP), support vector regression (SVR) and K-nearest neighbours regression (KNNR). Original hybrid methods, developed for research of specific implementations and ensemble methods based on hybrid methods’ decreased errors of energy generation forecasts for small wind turbines in comparison with single methods. The “artificial neural network (ANN) type MLP as an integrator of ensemble based on hybrid methods” ensemble forecasting method incorporates an original combination of predictors. Predictions by this method have the lowest mean absolute error (MAE). In addition, this paper presents an original ensemble forecasting method, called “averaging ensemble based on hybrid methods without extreme forecasts”. Predictions by this method have the lowest root mean square error (RMSE) error among all tested methods. LSTM, a deep neural network, is the best single method, MLP is the second best one, while SVR, KNNR and, especially, linear regression (LR) perform less well. We prove that lagged values of forecasted time series slightly increase the accuracy of predictions. The same applies to seasonal and daily variability markers. Our studies have also demonstrated that using the full set of available input data and the best proposed hybrid and ensemble methods yield the lowest error. The proposed hybrid and ensemble methods are also applicable to other short-time generation forecasting in renewable energy sources (RES), e.g., in photovoltaic (PV) systems or hydropower.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Hybrid and Ensemble Methods of Two Days Ahead Forecasts of Electric Energy Production in a Small Wind Turbine

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The RF is a process of studying a novel and an ensemble machine 36 . CRO 37 is evolutionary‐type search and optimization algorithms depend on behavior of procedures that take place in a true coral reef. Where, CRO can be able to enhance the underlying uneven arrangements as well as connect the pursuit room for superior level.…”

Section: A Hybrid Technique For Energy Management System In Grid Connmentioning

confidence: 99%

A hybrid RFCRO approach for the energy management of the grid connected microgrid system

Roy

Mandal

2020

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

Energy management of the grid connected microgrid (MG) systems with low cost using a novel hybrid algorithm is implemented in this paper. The novel proposed hybrid technique is the combined performance of both the Random Forest (RF) and Coral Reefs Optimization (CRO) algorithm and in this way it is named as RFCRO. Optimum operation of micro-sources for decreasing the electricity production cost by hourly day-ahead and real-time scheduling is the main objective of the paper. The proposed hybrid technique is to manage the power flows between the energy sources and the grid. To achieve this point, demand response and minimum cost of energy are determined. This technique is involved with the mathematical optimization problems that necessitate more than one fitness function to be optimized simultaneously. By using the inputs of MG-like wind turbine, photovoltaic array, battery, and fuel cell with corresponding cost functions, the RF is employed to predict the load demand. CRO clarifies the squirrel in optimizing the configuration of MG based on the load demand. The proposed hybrid technique is implemented in MATLAB/ Simulink working platform and compared with other solution techniques like

show abstract

“…The original Coral Reefs Optimization (CRO) Algorithm [31,35,36] is an evolutionary-based algorithm that simulates the processes occurring in a coral reef. Furthermore, when substrate layers (each representing a different exploration mechanism) are implemented constituting the so called Substrate Layers Coral Reefs Optimization algorithm (SL-CRO), survival of coral larvae depending on the substrate is emulated, and competitive co-evolution is added to the the original CRO algorithm [32,37].…”

Section: The Multi-objective Substrate Layers Coral Reefs Optimizatiomentioning

confidence: 99%

“…At the same time, optimal cross-sectional areas of the lines that should be installed in the MG to minimize energy losses and total cost are determined. According to the normalized cross-sectional areas referred in the IEC 60364-5-52:2009/Corr:2011 (Low-voltage electrical installations) [51], the set of possible line CSAs considered in this work is: a ik ∈ {6, 10,16,25,35,50,70,95,120,150,185,240, 300, 400, 500, 630} [mm 2 ].…”

Section: Description Of the Mg And The Generators And Loads Usedmentioning

confidence: 99%

Optimal Microgrid Topology Design and Siting of Distributed Generation Sources Using a Multi-Objective Substrate Layer Coral Reefs Optimization Algorithm

et al. 2018

Self Cite

View full text Add to dashboard Cite

In this work, a problem of optimal placement of renewable generation and topology design for a Microgrid (MG) is tackled. The problem consists of determining the MG nodes where renewable energy generators must be optimally located and also the optimization of the MG topology design, i.e., deciding which nodes should be connected and deciding the lines’ optimal cross-sectional areas (CSA). For this purpose, a multi-objective optimization with two conflicting objectives has been used, utilizing the cost of the lines, C, higher as the lines’ CSA increases, and the MG energy losses, E, lower as the lines’ CSA increases. To characterize generators and loads connected to the nodes, on-site monitored annual energy generation and consumption profiles have been considered. Optimization has been carried out by using a novel multi-objective algorithm, the Multi-objective Substrate Layers Coral Reefs Optimization algorithm (Mo-SL-CRO). The performance of the proposed approach has been tested in a realistic simulation of a MG with 12 nodes, considering photovoltaic generators and micro-wind turbines as renewable energy generators, as well as the consumption loads from different commercial and industrial sites. We show that the proposed Mo-SL-CRO is able to solve the problem providing good solutions, better than other well-known multi-objective optimization techniques, such as NSGA-II or multi-objective Harmony Search algorithm.

show abstract

A statistically-driven Coral Reef Optimization algorithm for optimal size reduction of time series

Cited by 27 publications

References 29 publications

Hybrid and Ensemble Methods of Two Days Ahead Forecasts of Electric Energy Production in a Small Wind Turbine

Hybrid and Ensemble Methods of Two Days Ahead Forecasts of Electric Energy Production in a Small Wind Turbine

A hybrid RFCRO approach for the energy management of the grid connected microgrid system

Optimal Microgrid Topology Design and Siting of Distributed Generation Sources Using a Multi-Objective Substrate Layer Coral Reefs Optimization Algorithm

Contact Info

Product

Resources

About