Search

Wind speed plays a pivotal role in ensuring the stability of power grid operations. However, the inherent high volatility and non-stationarity of wind patterns pose significant challenges to achieving accurate predictions. To tackle this issue and enhance the interpretability of existing wind speed prediction models, this study proposes an innovative short-term wind speed prediction model that combines two-stage decomposition, meteorological data feature engineering, adaptive differential evolution with optional external archive (JADE) algorithm, and temporal fusion transformers (TFT). To begin, the wind speed data is subjected to decomposition using improved complete ensemble empirical mode decomposition with adaptive noise (IEEMD), yielding multiple eigenmode functions. Subsequently, the nonlinear decomposition subsequence undergoes further decomposition into multiple submodes via empirical wavelet transform (EWT), followed by the careful screening of nonlinear quadratic decomposition submodes. Additionally, meteorological features are ingeniously reconstructed into combined and statistical meteorological features, enhancing the effectiveness of input features. Next, the hyperparameters of the TFT are meticulously optimized using the powerful JADE algorithm. Empirical results unequivocally demonstrate that the IEEMD-EWT-JADE-TFT model achieves remarkably high prediction accuracy. Meanwhile, this interpretative experimental process and its results chart a novel path for decision-makers seeking reliable wind speed forecasting processes and outcomes. • A scientific feature engineering method for meteorological data is proposed. • An effective linear-nonlinear two-stage decomposition method is introduced. • An explainable wind speed forecasting methodology named ICEEMDAN-EWT-JADE-TFT is proposed. • Impacts of input variables are analyzed by TFT's interpretability capability. [ABSTRACT FROM AUTHOR]

Establishing a precise model for proton exchange membrane fuel cell (PEMFC) is vital to simulate, manage, control, and estimate the optimal parameters accurately. However, the process has some challenges due to the nonlinear nature of fuel cells (FCs) and the missing parameters in datasheet. Also, the reported approaches have some restrictions in their behaviors. This paper proposes a new methodology incorporated exponential distribution optimizer (EDO) to construct PEMFC's equivalent circuit through estimating their parameters with the aid of experimental data. The algorithm is characterized by exploration/exploitation balance that avoids falling in local solutions. Sum square error (SSE) between the measured and estimated terminal voltages is selected as the target to be mitigated. The analysis is performed on four different FCs which are Ballard Mark V 5 kW, BCS-500 W, SR-12 500 W, and NedStack PS6. The proposed EDO is compared to reported approaches of mayfly optimization algorithm (MOA), chaotic mayfly optimization algorithm (CMOA), modified Harris hawks optimizer (MHHO), fractional order modified HHO (FMHHO), hybrid vortex search algorithm and differential evolution (VSDE), and other programmed approaches of sine cosine algorithm (SCA), seagull optimization algorithm (SOA), tunicate swarm algorithm (TSA), and gold rush optimizer (GRO). The best scores are 0.852056, 1.16978E-02, 1.056628, and 2.079166 obtained through the proposed EDO for Ballard Mark V 5 kW, BCS-500 W, SR-12 500 W, and NedStack PS6 cells, respectively. The absolute error ratios of CMOA, MOA, FMHHO, MHHO, VSDE, SOA, SCA, GRO, and TSA attributed to the error obtained by the proposed EDO in case of BSC-500W are 0.17%, 3.49%, 0.62%, 15.50%, 3.78%, 29.12%, 86.30%, 0.90%, and 10.33%, respectively. Despite the nine approaches considered in comparative analysis having some issues with convergence speed, they converged the best solution. Moreover, the dynamic model of PEMFC is established in Simulink and its performance is assessed through applying step load disturbance. The fetched results demonstrated the superiority of the proposed EDO in establishing reliable models of various PEMFCs. • EDO is proposed to estimate the optimal parameters of different PEMFCs. • Comparison to MOA, CMOA, MHHO, FOHHO, VSDE, SCA, SOA, TSA, and GRO is conducted. • The dynamic behavior of the established model is assessed at different demands. • The obtained results demonstrated the efficacy and reliability of the proposed EDO. [ABSTRACT FROM AUTHOR]

Contemporary wind speed prediction research methodologies often employ two-stage decomposition preprocessing techniques to leverage the temporal correlation of wind speed. However, they frequently neglect to investigate the interpretability within the wind speed prediction model. To this end, a novel and interpretable hybrid forecasting model that combines two-layer decomposition, adaptive differential evolution with optional external archive (JADE), and temporal fusion transformers (TFT) is proposed. Primarily, on the basis of the linear-nonlinear decomposition criterion, a set of subcomponents is obtained using two-stage decomposition to fully extract the wind speed series prediction information for high-fluctuation and multi-resolution modes. Utilizing the JADE algorithm for intelligent and efficient optimization of parameter combinations in the TFT model guarantees the stability and reliability of the prediction model. Later, the obtained two-layer decomposition subseries are used as historical variables, and the meteorological and temporal data are entered into the TFT model as future known inputs. Empirical studies show that the proposed model demonstrates remarkable suitability and effectiveness in short-term wind speed forecasting. The utilization of the interpretable model has catalyzed significant advancements in wind speed prediction, while the analysis of its interpretable results empowers managers in formulating effective policies. • Introduce a novel linear-nonlinear two-stage decomposition method. • Propose an interpretable wind speed prediction methodology named EMD-EEMD-JADE-TFT. • Impacts of two-stage decomposition sub-sequences are analyzed by TFT's interpretability capability. • EMD-EEMD-JADE-TFT is used to achieve better forecasting accuracy for four cases. [ABSTRACT FROM AUTHOR]

Wind farm layout optimization is a challenging issue which demands to discover some trade-off solutions considering various criteria, such as the power generated and the cost of the farm. Due to the complexity of the problem, we developed a reinforcement learning-based multi-objective differential evolution (RLMODE) algorithm to address the issue. In the developed algorithm, RL technique is applied to coordinate the parameter of DE algorithm, which can balance the local and global search. A tournament-based mutation operator is used to accelerate the convergence of the RLMODE algorithm. We tested the performance of the proposed RLMODE in two wind scenarios. The spread and spacing indicators of the algorithm are the best; the power generated by the solution from the RLMODE algorithm is the most when compared with some representative optimization algorithms and existing methods. • The WFLO problem is constructed as a multi-objective item. • The total power generated and the cost of the farm are considered. • A RL-based multi-objective DE (RLMODE) algorithm is established. • The RLMODE is used to optimize the multi-objective WFLO problem. [ABSTRACT FROM AUTHOR]

Accurate estimation of the model parameters of a fuel cell is extremely important to study its system behavior. This paper presents a parameter identification method based on improved artificial bee colony algorithm (IABC). Inspired by the cross operation of genetic algorithm and the cross and mutation operation of differential evolution algorithm, this study improves the position update formula of ABC in the parameter optimization process, thus the convergence accuracy and speed of IABC algorithm are improved. The algorithm was used to identify 3 typical standard test cases, namely 250W FC, BCS 500W and NedStack PS6 stack, and the minimum sum of squares (SSE) error between PEMFC measured voltage data and estimated voltage data was defined as the objective function. The SSE values of the three PEMFCs reached 0.29686, 0.011718 and 2.9848, respectively. The model I/V polarization curve estimated by IABC algorithm has a high fitting degree with the experimental measured curve, which indicates the accuracy of IABC algorithm. To verify the superiority of the proposed IABC algorithm, the identification results obtained by some optimization algorithms are compared and ANOVA (analysis of variance) is performed. Results show that the IABC algorithm has faster convergence speed and better robustness. • In this paper, a PEMFC parameter identification method based on improved artificial bee colony algorithm (IABC) is proposed to improve the original artificial bee colony. • The improved artificial bee colony algorithm further improves the accuracy of parameter identification and accelerates the convergence speed of the algorithm. • Three typical PEMFC stacks are tested and the results are compared with other algorithms to verify the advantages of IABC. [ABSTRACT FROM AUTHOR]

Two of the most critical issues encountered in the day-ahead scheduling of regional integrated energy systems are the uncertainty of renewable energy resources and complexity of load demand. Furthermore, varying operating conditions also pose challenges for economical day-ahead scheduling. This paper proposes a scenario-based day-ahead scheduling approach for regional integrated energy systems to minimize operating costs by mining historical data. A hybrid dynamic energy hub model with variable efficiency that integrates an extreme gradient boosting (XGBoost) algorithm and analytical formulation is proposed. We developed a scenario-based scheduling optimization model in which climate data and load data are predicted using XGBoost and the probability distributions of their predicted errors are estimated using a Gaussian mixture model. Monte Carlo simulation and K-means clustering were used to generate and reduce scenarios and a success-history-based adaptive differential evolution algorithm was adopted to search for optimal solutions for day-ahead scheduling. Furthermore, a weighted average electricity purchasing strategy was adopted to address uncertainty and further improve operating economy by adjusting the output of gas turbines and electricity purchasing for actual scheduling. Case studies were conducted to verify that the proposed approach can reduce daily operating costs and enhance the operating economy of regional integrated energy systems. • A hybrid DEH model integrating operating data and an analytical formulation characterizes flexible performance accurately. • Considering the uncertainty by scenario-based stochastic optimization method increases the operating cost. • A weighted average electricity purchasing strategy can address the uncertainty and further improve operating economy. [ABSTRACT FROM AUTHOR]

As increasing demand of electric energy and deterioration of environment pollution in global, economic emission dispatch (EED) problem has become one of the most important problems in power systems. In order to improve the quality of life and further reduce emissions, plug-in electric vehicle (PEV) has become a popular transportation. But the frequent and random charging of PEVs will bring potential risk that undermines the stability of the power grid. Therefore, dynamic economic emission dispatch considering plug-in electric vehicles (DEED-PEV) as a new hot-spot issue has gradually become more and more important in the power system. In this paper, an improved differential evolution using self-adaptable cosine similarity (DE-SCS) is proposed for EED and DEED-PEV problems. First, a dynamic cosine similarity calculated replaces the F of the differential evolution algorithm (DE) to scale the perturbation by self-adaptability. Second, a result-driven selection operation for multiple mutation strategies is implemented in each iteration. Third, a modified environment selection changes the usual way to ranking in the vectors pool during the update on Pareto front. Last, an evaluation mechanism that involves two series of solution sets and three types of comparing approaches is conducted on our proposed algorithms in the experiment. DE-SCS improves the equilibrium between exploration and exploration of the DE. The cosine similarity makes the convergence more self-adaptive. The modified environment selection maximizes the worth of previous generation vectors and brings the randomness into the next iteration. DE-SCS matching various environmental selection are tested on twelve unconstrained multi-objectives problems, six EED cases and six DEED-PEV cases containing charging load, discharging power, valley filling, and peak shaving. Experimental results confirm that DE-SCS is capable of obtaining such excellent and feasible solutions that it has good potential to deal with EED and DEED-PEV problems. • An improved DE using self-adaptable cosine similarity (DE-SCS) is developed. • A modified environment selection helps DE-SCS to rapidly find feasible solutions. • DE-SCS is used to solve economic emission dispatch (EED) problem. • Dynamic EED with plug-in electric vehicles problem (DEED-PEV) is studied. • DE-SCS has satisfactory performance for the DEED-PEV. [ABSTRACT FROM AUTHOR]

In the present paper, a bi-level optimization approach is proposed to synthesize Heat Exchanger Networks (HEN), based on a hybrid meta-heuristic method. Simulated Annealing (SA) is used to optimize the HEN topologies and Differential Evolution (DE) is applied to the continuous variables. The model is derived from a superstructure and considers streams split and non-isothermal mixing. The code was implemented in C++, which leads to an improvement in the execution times in comparison to previous literature studies. Four case studies were used to test the applicability of the developed model and results showed that it is possible to achieve optimal values, better than those presented in the literature. [ABSTRACT FROM AUTHOR]

The current study analyzes the potential of an environmentally benign integration of a parabolic trough solar collector (PTSC) with a heat-intensive multi-effect evaporator (MEE) used in pulp and paper industry. Actual plant data was used to simulate the MEE and estimate the steam economy (SE) and steam consumption (SC), which are used to judge the performance of PTSC-MEE system. Four distinct alternatives for the integration are investigated with Self-adaptive Differential Evolution (SaDE) utilized for optimization. Initially, a normal PTSC with four different model configurations of MEE, basic or with energy reduction schemes (ERSs) are tested and found that SE is slightly increased for each. Next, a geometrically optimized/combinatorial optimized PTSC with basic MEE is examined, a rise of ∼3.4% in SE is noted for both, with current integration outperforming one out of three ERSs. Subsequently, geometrical plus combinatorial optimized PTSC with basic MEE is inspected, increase in SE reached 7.59% and two of the three ERSs outperformed. Economic analysis is conducted to estimate the steam saving with different PTSC-MEE systems and corresponding payback periods. The possibility of decarbonization with the various integration possibilities is also explored by evaluating the fuel savings and related CO 2 savings. • Integration of PTSC with an MEE used in pulp and paper industry is investigated. • The fusion of PTSC with MEE is studied with various possibilities. • Self-adaptive Differential Evolution (SaDE) is used for various optimizations. • The steam savings and payback times are estimated for various PTSC-MEE systems. • Decarbonization is studied by analyzing fuel savings and CO 2 reductions. [ABSTRACT FROM AUTHOR]

The generation forecast helps to develop the scheduling plan of power sources, build a power balance system and ensure the adequacy of power supply to the power system at the macro level. Therefore, a novel structurally adaptive discrete grey Bernoulli model, called DHGBM(1,1), is proposed in this paper for the prediction of power generation. Firstly, the Hausdorff fractional order cumulative generation operation makes it possible to achieve new information prioritisation. As for the structure of the model, we have extended the nonlinear grey Bernoulli model with the introduction of a nonlinear dynamic structure term, which allows the model to simulate variable generation data and improves the adaptability of the model. In a comparative test of the algorithms, the well-performing differential evolution algorithm was used for hyperparameter optimisation of the model to obtain better predictive performance. Monte Carlo simulations and probability density analysis verified the excellent robustness of the model. In addition, through the simulation tests, we obtained a reasonable range of parameters for the structural terms, thus limiting the complexity of the model, and the phenomenon of model overfitting was effectively prevented. Finally, five actual cases of China's hydro, China's thermal, China's nuclear, China's wind power generation and China's electricity exports are predicted. • A novel nonlinear dynamic structural term is proposed. • A novel structural adaptive discrete grey Bernoulli model is developed. • The robustness analysis of the novel model is established. • Comparative study shows that the novel model is superior to other six models. [ABSTRACT FROM AUTHOR]

Owing to slowly lessening of fossil fuel, economical use of obtainable fuel for electric power and heat generation has turn out to be an important worry of utility industries. In this manuscript, fuel constrained combined heat and power unit commitment incorporating renewable energy sources and electric vehicle parking lot is undertaken for addressing the optimum generation scheduling of the committed units. Here thermal generating units (TGUs), cogeneration units (CGUs), heat only units (HOUs), cascaded hydro power plants (CHPPs) and solar PV plants (SPVPs) and wind turbine generators (WTGs) are considered. A number of plug-in electric vehicles (PEVs) with charging and discharging behaviours is also considered. The problem is solved with and without fuel constraints. The UC problem is solved by using binary differential evolution (BDE) along with priority list (PL). Numerical results of the test systems are included to provide valued minutiae for operational and planning problems. [Display omitted] • Fuel constrained combined heat and power commitment scheduling has been studied. • Cascaded hydro power plants, solar PV plants, wind turbine generators are considered. • 50 000 PEVs have been incorporated with both G2V mode and G2V/V2G modes. [ABSTRACT FROM AUTHOR]

Standalone photovoltaic system is promising sustainable energy source. Accurate modeling and sizing of these systems strongly affect the system's feasibility. Thus, in this paper, optimal sizing of standalone photovoltaic system is conducted based on multi-objective differential evolution algorithm integrated with hybrid multi-criteria decision making methods. Multi-objective differential evolution algorithm is used to optimize set of configurations of a system by minimizing technical and cost objective functions simultaneously. After that, an analytical hierarchy process integrated with a technique for order preference by similarity to ideal solution are used to order preference of configurations based on the loss of load probability and life cycle cost of system. The results of the proposed sizing method are validated by a numerical method to explain the superiority of the proposed method. According to results, the proposed sizing method is faster than numerical method by around 27 times. This is because the multi-objective differential evolution algorithm requires roughly 0.23 of simulations that is required by numerical method. Furthermore, the performance of multi-objective differential evolution algorithm is evaluated by various metrics. As a result, for the adapted load demand, the optimal configuration is 63 PV modules and 66 battery unit with maximum capacity of 500 Ah. • We optimally size standalone PV system using hybrid metaheuristic algorithm. • Multi-objective DE with hybrid multi-criteria decision making algorithms are applied. • We use analytical hierarchy process to classify system's configurations based on LLP. • The proposed sizing method is faster than numerical method by around 27 times. [ABSTRACT FROM AUTHOR]

Abstract A method of fast multi-objective optimization and decision-making support for building retrofit planning is developed, and lifecycle cost analysis method taking into account of future climate condition is used in evaluating the retrofit performance. In order to resolve the optimization problem in a fast manner with recourse to non-dominate sorting differential evolution algorithm, the simplified hourly dynamic simulation modeling tool SimBldPy is used as the simulator for objective function evaluation. Moreover, the generated non-dominated solutions are treated and rendered by a layered scheme using agglomerative hierarchical clustering technique to make it more intuitive and sense making during the decision-making process as well as to be better presented. The suggested optimization method is implemented to the retrofit planning of a campus building in UPenn with various energy conservation measures (ECM) and costs, and more than one thousand Pareto fronts are obtained and being analyzed according to the proposed decision-making framework. Twenty ECM combinations are eventually selected from all generated Pareto fronts. It is manifested that the developed decision-making support scheme shows robustness in dealing with retrofit optimization problem and is able to provide support for brainstorming and enumerating various possibilities during the decision-making process. Highlights • Lifecycle cost analysis considering future climate change impact on building retrofit. • Use paralleled NSDE and selected best crossover operator for fast optimization. • Use specifically developed energy simulator, SimBldPy, to accelerate the optimization. • Developed a decision making support scheme based on hierarchical clustering. [ABSTRACT FROM AUTHOR]

Abstract This paper proposes an improved enhanced differential evolution algorithm for implementing demand response between aggregator and consumer. The proposed algorithm utilizes a secondary population archive, which contains unfit solutions that are discarded by the primary archive of the earlier proposed enhanced differential evolution algorithm. The secondary archive initializes, mutates and recombines candidates in order to improve their fitness and then passes them back to the primary archive for possible selection. The capability of this proposed algorithm is confirmed by comparing its performance with three other well-performing evolutionary algorithms: enhanced differential evolution, multiobjective evolutionary algorithm based on dominance and decomposition, and non-dominated sorting genetic algorithm III. This is achieved by testing the algorithms' ability to optimize a multi-objective optimization problem representing a smart home with demand response aggregator. Shiftable and non-shiftable loads are considered for the smart home which model energy usage profile for a typical household in Johannesburg, South Africa. In this study, renewable sources include battery bank and rooftop photovoltaic panels. Simulation results show that the proposed algorithm is able to optimize energy usage by balancing load scheduling and contribution of renewable sources, while maximizing user comfort and minimizing peak-to-average ratio. Highlights • Evolutionary algorithms play significant role in demand response implementation. • Aggregator-consumer matching via evolutionary algorithms improves mutual benefits. • Two-archive strategy improves mutation and crossover speed in differential evolution. [ABSTRACT FROM AUTHOR]

Abstract Design study of the precooling heat exchanger specified for high speed airbreathing propulsion was carried out from the perspective of overall engine performance. The precooler proposed for the SABRE engine was adopted as the representative configuration for evaluation. Design procedure of the precooler was developed and incorporated into a cycle analysis model such that the variation in engine performance can be assessed as the design inputs is altered. By means of the differential-evolution algorithm, the design characteristics of the precooler were clarified through the idea of Pareto-Optimality. Precooler total mass and axial length, together with engine specific impulse, was included as optimization objectives on account of the results of parametric analysis. Pareto-optimal-fronts were obtained with the influence of some key design parameters such as the precooling temperature and the intake efficiency was analyzed. The results show that precooler design is a tradeoff between the optimization objectives considered. Selection of a larger precooling temperature helps to increase engine specific impulse and reduce the mass of precooler, although engine specific thrust is decreased slightly, whereas larger intake efficiency is extremely preferred for precooled cycles from not only the performance side of the engine, but more importantly, the geometry side of the precooler. Highlights • Design study of precooler is presented from the perspective of Pareto optimality. • Tradeoff feature is observed between the selected optimization objectives. • Significant increase in specific impulse can only be made within a certain range. • Adoption of larger precooling temperature benefits both the precooler and cycle. • Developing high performance intake is extremely important for precooled engines. [ABSTRACT FROM AUTHOR]

Abstract Electric power, as an efficient and clean energy, has considerable importance in industries and human lives. Electricity price is becoming increasingly crucial for balancing electricity generation and consumption. In this study, long short-term memory (LSTM) with the differential evolution (DE) algorithm, denoted as DE–LSTM, is used for electricity price prediction. Several recent studies have adopted LSTM with considerable success in certain applications, such as text recognition and speech recognition. However, problems in the application of LSTM to solving nonlinear regression and time series problems have been encountered. DE, a novel evolutionary algorithm that effectively obtains optimal solutions, is designed to identify suitable hyperparameters for LSTM. Experiments are conducted to verify the performance of the DE–LSTM model under the electricity prices in New South Wales, Germany/Austria, and France. Results indicate that the proposed DE–LSTM model outperforms existing forecasting models in terms of forecasting accuracies. Highlights • Effective Long short-term Memory (LSTM) is proposed for electricity price forecasting. • Differential evolution helps selecting suitable hyper-parameters of LSTM. • The proposed method named DE-LSTM is the best for three cases in terms of accuracy. [ABSTRACT FROM AUTHOR]

This paper proposes an effectively adaptive selective cuckoo search algorithm (ASCSA) for solving short-term hydrothermal scheduling problems with available water constraint, reservoir volume constraints, and transmission network constraints. The proposed ASCSA is a newly improved version of the conventional cuckoo search algorithm to enhance the solution quality and reduce the maximum number of iterations based on two new techniques including the new ratio of the difference between the fitness function values and the integration of solutions into one group. The effectiveness of ASCSA has been validated via eight hydrothermal systems, in which the last two systems consisting of the IEEE 30-bus and IEEE 118-bus systems are considered with a set of constraints in the transmission network. To investigate the performance of ASCSA, several algorithms are also implemented in the paper such as conventional cuckoo search algorithm, modified cuckoo search algorithm, particle swarm optimization, global vision of particle swarm optimization with inertia weight, differential evolution, and improved differential evolution. From result comparisons of the test systems, the proposed ASCSA method has obtained lower total costs than other methods implemented for solving the problems. Therefore, the proposed ASCSA is a very efficient and favorable method for solving the considered hydrothermal scheduling problems. [ABSTRACT FROM AUTHOR]

In this paper, a sulfur dioxide (SO 2) emission concentration real-time dynamic prediction model is proposed to achieve the control target of ultra-low SO 2 emissions and economical desulfurization system operation at a large-scale coal-fired power plant. First, a vision-expansion self-attention strategy is adopted on the Transformer algorithm structure for better time-series information feature extraction. Second, to adapt to the vision-expansion self-attention strategy, convolution and long short-term memory (LSTM) are combined to process input information position encoding, which can obtain long time-series information absolute position encoding. Then, a Convolution-LSTM VE-Transformer model is constructed by combining the above two proposed parts. The mutual information method and the differential evolution algorithm are combined to calculate correlations between variables and obtain the optimal delay time. Finally, a real-time dynamic prediction model of SO 2 is established. In this model, the structure of the input and output variables is determined by the delay time and the influence of coal quality on the SO 2 concentration. The quantitative comparison results show the superior accuracy and generalization ability of the proposed prediction model to related popular methods, indicating that the model has strong potential for use in further controller design and applications. • Transformer algorithm structure is applied to coal-fired station for the first time. • A real-time dynamic SO 2 concentration dynamic prediction model is proposed. • A vision-expansion self-attention strategy is adopted to Transformer model. • A position coding method is obtained based on combination of convolution and LSTM. • Delay time between variables is calculated by DMI and DE algorithm. [ABSTRACT FROM AUTHOR]

An optimal sizing model for a hybrid micro-grid system (HMGS) consisting of solar photovoltaic, wind turbine, diesel generator and battery is developed. A tri-objective formulation, considering techno-socio-economic factors, is proposed for finding the optimal size and configuration. Dynamic domain search is employed using a hybrid intelligent computational technique that integrated the improved particle swarm optimization (PSO) algorithm with an enhanced differential evolution (DE) model for improving the search efficiency. The idea behind the hybridization of these two popular paradigms is to deploy the higher exploration capability of the PSO during the initial search and then employ the fast convergence property of the DE to achieve an optimal solution through exploitation. A fuzzy attainment module (FAM) is appended to identify the best solution based on the highest possible attainment level for all objectives. Two power management strategies are modelled and their effect on emission curtailment is studied. Optimal sizing is analysed considering the effect of selected optimization objective(s) and multiple choices are offered to the designer based on preferences. For the selected remote island, the system with solar PV capacity 78.44 kW, wind turbine of 95 kW with a battery of 2 kW is found to be the best option. The levelized cost of energy (LCOE) is 0.0799 $/kWh, human development index (HDI) is 0.6454, unmet power is zero and the satisfaction level of all the three objectives is 72.82%. • Optimal sizing of hybrid energy system is proposed using an intelligent method. • Multi-objective problem is formulated with technical-economic and social factors. • Two battery power management strategies are employed. • Improved hybrid PSO-DE algorithm is employed for optimization. • Fuzzy attainment module is integrated to get the best attainment solution. [ABSTRACT FROM AUTHOR]

Electricity energy consumption (EEC) has great effect on the government to make reasonable energy policy and has attracted great attentions of the power generation groups with the liberalization of competition in the electricity industry. In fact, the EEC is easily affected by many factors, including the climate factor and the gross domestic product. So, the precise forecasting of electricity energy consumption is very challenging. This study aims to propose an effective and stable model named ESN - DE using an improved echo state network for forecasting electricity energy consumption. Differential evolution algorithm is used to search optimal values of the three crucial parameters of echo state network. Two comparative examples and an extended example are used to validate the applicability and accuracy of the proposed ESN - DE. Errors of the comparative examples where mean absolute percentage errors of ESN-DE are 1.516% and 0.570% respectively indicate that the ESN - DE outperforms the traditional echo state network and the existing best model. Mean absolute percentage error of ESN - DE is 2.156% for Zhengzhou City's electricity energy consumption forecasting. The proposed ESN - DE is a potential candidate for effective forecasting of electricity energy consumption because of its easy implementation and stability. [ABSTRACT FROM AUTHOR]

In the present study, the pyrolysis of biomass is proposed by one step multi reaction apparent model. It is expressed as parallel production of bio-oil, gases and charcoal. Macro TGA of Jatropha de-oiled cake is performed at temperatures ranging from 350 °C to 700 °C. The volatiles released during pyrolysis exits from the top of the reactor and are cooled in a two-stage condenser followed by an ice trap. The weight reduction variation of the biomass with time, product yield and composition of non condensable gases are measured and used to develop the apparent kinetic model. The corresponding apparent kinetic parameters are estimated by minimizing the square of the error between simulated values of residual weight fraction and experimental values using non-traditional optimization technique logarithmic differential evolution (LDE). The weight reduction with time suggests that the pyrolysis of de-oiled cake is carried out in three stages. The maximum liquid yield obtained is 31.2% at 500 °C, which further decreases with an increase in temperature. The model predicted values of residual weight fractions and yield of products are matching very well with the experimental data for all reactor temperature. [ABSTRACT FROM AUTHOR]

In this paper, we propose a memory-based global differential evolution (MGDE) algorithm and a repair technique of constraint handling for the dynamic economic dispatch problems. On the one hand, MGDE modifies the mutation of DE/best/1, and uses a memory pool to provide more candidate solutions for this operation. Moreover, it adopts a randomly generated scale factor in the modified mutation to enhance its exploration capacity. In the crossover, a dynamical crossover rate is introduced to balance MGDE's global and local search capacities. On the other hand, a repair technique is designed for handling three kinds of constraints associated with generator capacity, power balance and generating unit ramp-rate. Moreover, a commonly used penalty function method is subsequently employed to handle the possible constraint violations associated with power balance and prohibited operation zones (POZs). To judge the performance of MGDE and the efficiency of the repair technique, we have solved six well-known DED problems taken from different sources. According to the experimental results, MGDE shows a superior performance in comparison with other improved DEs which also solve these problems. In the mean time, the repair technique of constraint handling has a high efficiency in eliminating or reducing the constraint violations. [ABSTRACT FROM AUTHOR]

This paper aims to solve wind energy integrated electric power dispatch (EPD) problem from the perspectives of stochastic modelling and multiobjective optimization. At first, the competing objectives in modern electric power and energy system is analyzed and a new interval optimization model for each objective is proposed based on the uncertainties with respect to wind power. Then, a novel strength differential evolution (SDE) algorithm is developed to address the interval optimization model. The SDE adopts a population selection process based on chaotic sequence and Boltzmann distribution to balance the tradeoff between local exploitation and global exploration. Afterwards, a multiobjective EPD model is established and a novel generalized piecewise normal boundary intersection (GPNBI) method is mooted to transform multiobjective EPD into a series of single-objective sub-problems which can be effectively solved by SDE. In order to deal with the highly constrains in GPNBI, a new heuristic constraint handling strategy is proposed accordingly to accelerate the convergence speed. At last, a hyper-plane based decision-making strategy is originally developed to identify the best compromise solution in the obtained Pareto frontiers (PFs). The feasibility and effectiveness of the interval optimization model and GPNBI inspired multiobjective SDE (MOSDE) have been comprehensively evaluated on a modified IEEE 30-bus system and a 118-bus system. The statistical results confirm that the proposed interval optimization model can approximately quantify the potential uncertainty in each objective and also demonstrate that the proposed MOSDE exhibits better performance than the algorithms of the state. Therefore, it is convinced that the proposed optimization model and method have high potentials to address the practical implementation problems in electric power and energy systems with wind energy penetration. [ABSTRACT FROM AUTHOR]

In the fractional grey model, the new information priority principle has always been pursued by researchers. However, it does not mean that new information is the most important, because in reality, there are always some special moments, and the information they represent will profoundly affect the future development. That is, the most important data may be in the middle of the sequence, not the latest data. Therefore, this paper proposes a periodic variable order accumulated generating operation, which can switch the priority of new and old information with time. In terms of model structure, this paper presents a new variable coefficient whitening equation with self-adaptive structure. That is, a new fractional order grey Euler model with dynamic accumulation order (DOFGM(1,1)) is proposed in this paper. The new model combines the adjacent sequence operator, therefore the newly generated sequence is less random. By adjusting the model parameters, the structure of the model can be changed, so that the model has the features of selecting the adaptive structure. By comparison, the differential evolution algorithm is selected to optimize the hyperparameters of the model. In particular, the robustness of the model is validated by introducing perturbations to the raw data to imitate errors generated during data collection. Finally, three actual cases of China's hydropower generation, China's natural gas production and China's total primary energy production are predicted; the prediction result shows that the new model has higher prediction accuracy than the other six models. The results indicate that the proposed model benefits from its adaptive structure and produces reliable predictions. According to these prediction results, relevant suggestions on the development of China's energy are provided to decision makers. • A novel structurally adaptable grey Euler model is suggested. • A periodic variable-order accumulated generating operation is proposed. • The robustness analysis of the novel model is established. • Comparative study shows that novel model is superior to other various grey models. [ABSTRACT FROM AUTHOR]

To promote renewable energy consumption and achieve China's low-carbon energy transition, in 2019, China proposed the weight of consumption responsibility (WCR) for renewable energy in each province. This study aims to explore the micro-market behavior of new energy manufacturers in the context of WCR policy. A two-market bidding model for new energy manufacturers is first proposed, and a two-stage compound differential evolutionary game algorithm is proposed for solving the multi-party game problem. By selecting typical electricity demand scenarios, the evolution of new energy manufacturers' strategies in the electricity market and green certificate market as well as under different WCR and different thermal power unit parameters are analyzed. The research results show that when the non-hydropower WCR is relatively low, new energy manufacturers tend to adopt a low-price strategy for generation quotation and a low volume high price strategy for green certificate sales. Other conditions being unchanged, with the increase in non-hydropower WCR, all new energy manufacturers will still adopt a low-price strategy in the electricity market. New energy manufacturers with high installed capacity will increase progressively their certificate quotation. The higher output lower limit for thermal units is not conducive to electricity market bidding by new energy manufacturers. • A two-market bidding model for new energy manufacturers is established. • A two-stage compound differential evolutionary game algorithm for new energy manufacturers is proposed. • The optimal strategy of two-market bidding for new energy manufacturers is empirically analyzed. • The bidding strategies under different consumption responsibility weights are discussed. [ABSTRACT FROM AUTHOR]

This paper investigates the real-time prediction of nitrogen oxides (NO x) emission by using around 17000 samples involved in a collection of three-day real data from a waste incineration power plant. To disclose the relationship between the ammonia (NH 3) ejection and NO x emission, we choose the NO x reduction from inlet to outlet rather than the NO x concentration monitored by continuous emission monitoring system (CEMS). A hybrid procedure is developed to select appropriate features from the large and unsynchronized data, with which we establish a model based on the gradient boosting decision tree (GBDT) for the prediction. Computational experiments demonstrate that, with root mean square error (RMSE) values being 1.851 and 3.593 for training and test data, respectively, GBDT outperforms its two popular counterparts, supporting vector regression (SVR) and long short-term memory (LSTM). Shapley additive explanations (SHAP) is also conducted for analysis. • NOx reduction as a proxy to disclose true relationship between NOx emission and NH 3. • The maximal information coefficient is used to eliminate redundant features. • The differential evolution is used to determine the lag-periods of selected feature. • GBDT is verified to outperform SVR and LSTM in predicting NOx emission. • SHAP is conducted to analyze the mechanism of GBDT in depth. [ABSTRACT FROM AUTHOR]

Coal fired power plants account for a large part of China's NO x emission. A precise prediction of the NO x emission can effectively improve the pollutant control level and operation ability. In this study, a novel combined model based on 1D semi-empirical model and three black box models is proposed to predicted the dynamics of NO x emission of a 350 MW circulating fluidized bed (CFB) boiler. In addition, an improved differential evolution algorithm based on non-negative constraint theory is used to determine the optimal weight coefficient of the combined model. Three different working condition datasets of the CFB boiler are acquired to evaluate the performance of combined model. The results of the experiments and discussions show that the combined model overcomes the limitation of the single model and achieves better prediction results. • A combined model based on semi-empirical model and black box models is proposed. • An improved differential evolution is applied to the combined model. • Dynamic prediction of NO x emission of CFB boiler under different operating conditions. • The proposed model performs better than single models. [ABSTRACT FROM AUTHOR]

This study proposes an effective model for enhancing the short-term wind speed forecasting performance by considering the effect of multiple meteorological factors. (a) The filter-wrapper non-dominated sorting differential evolution algorithm incorporating K -medoid clustering (FWNSDE C) is designed to select key meteorological factors and generate multiple feature subsets. For each feature subset, the hybrid deep learning model is designed: (b) singular spectrum analysis (SSA) is used to decompose the meteorological factors and construct the three-dimensional input structure; (c) convolutional long short-term memory (ConvLSTM) network is then adopted to process the sample set of three-dimensional sequence, and the final forecasting result is the average prediction of all the built ConvLSTMs. To evaluate the effectiveness of FWNSDE C -SSA-ConvLSTM, three comparative experiments on four datasets collected from the National Renewable Energy Laboratory are implemented. Experiment results show that the average mean absolute percentage error over four datasets for 1-step-ahead, 2-step-ahead, and 3-step-ahead forecasting is 1.42%, 1.99%, and 3.28%, respectively, which are much better than the predictions using feature selection benchmarks, hybrid forecasting benchmarks with different deep learning networks and data decomposition methods, and other advanced forecasting systems. Extended model discussion in terms of Friedman test and parameters sensitivity analysis further verifies the potential of proposed model. • A new multivariate wind speed forecasting model FWNSDE C -SSA-ConvLSTM is proposed. • Multi-objective feature selection approach FWNSDE C is designed to selects key meteorological factors. • Hybrid model SSA-ConvLSTM is developed to decompose meteorological factors and forecast future wind speed. • Proposed model outperforms 16 benchmarks in four wind speed datasets. [ABSTRACT FROM AUTHOR]

Short-term optimal hydrothermal scheduling plays one of the most important roles in the modern power system plan and operation. The problem aims at minimizing the total fuel cost of the thermal units while satisfying various constraints such as power balance, water balance and other constraints on thermal units as well as hydro units. Except for the above various constraints, transmission network topology and valve point effects are also introduced into the mathematical optimizing model of the short-term hydrothermal scheduling (STHS) problem. Then a small-population based parallel differential evolution approach is proposed to solve the STHS problem considering power flow constraints. In the proposed approach, a large population is divided into several subpopulations each with a small population size and several parallel running processes of one or more CPUs are performed synchronously each evolving a certain subpopulation and searching for the optimal solution independently. Two different methods are employed in the proposed parallel DE approach in order to avoid low diversity of the small population in each process. One is implemented through the small population itself and the other through the communication mechanism among different running processes. Four constraint handling rules as well as a lead operation are proposed to enhance the feasibility of solutions. Numerical results for two well-known sample test systems are presented to demonstrate the capabilities of the proposed parallel DE algorithm to generate optimal solutions of STHS problem. Two other test systems with transmission networks of standard IEEE 9-bus and IEEE 39-bus are also employed to test the effectiveness of the proposed parallel DE algorithm. The results demonstrate the superiority of the proposed algorithm. [ABSTRACT FROM AUTHOR]

With the integration of wind power and photovoltaic power, optimal operation of hydrothermal power system becomes great challenge due to its non-convex, stochastic and complex-coupled constrained characteristics. This paper extends short-term hydrothermal system optimal model into short-term hydrothermal optimal scheduling of economic emission while considering integrated intermittent energy resources (SHOSEE-IIER). For properly solving SHOSEE-IIER problem, a gradient decent based multi-objective cultural differential evolution (GD-MOCDE) is proposed to improve the optimal efficiency of SHOSEE-IIER combined with three designed knowledge structures, which mainly enhances search ability of differential evolution in the shortest way. With considering those complex-coupled and stochastic constraints, a heuristic constraint-handling measurement is utilized to tackle with them both in coarse and fine tuning way, and probability constraint-handling procedures are taken to properly handle those stochastic constraints combined with their probability density functions. Ultimately, those approaches are implemented on five test systems, which testify the optimization efficiency of proposed GD-MOCDE and constraint-handling efficiency for system load balance, water balance and stochastic constraint-handling measurements, those obtained results reveal that the proposed GD-MOCDE can properly solve the SHOSEE-IIER problem combined with those constraint-handling approaches. [ABSTRACT FROM AUTHOR]

Wind turbine blade design is a complicated multi-objective optimization task. In this article, a novel gradient-based multi-objective evolution algorithm based on both uniform decomposition and differential evolution is proposed for the design of wind turbine blades, to overcome unsatisfactory convergence performance and diversity of solutions usually existing in conventional evolution algorithms. A uniform decomposition mechanism is developed to achieve homogeneous discretion of the objective space for the purpose of controlling population distribution. Meanwhile, a differential evolution mechanism based on neighbourhood and gradient is developed to achieve exploration-exploitation balance and enhance optimization efficiency of the algorithm proposed. Two-objective, three-objective, and four-objective optimizations for the 1.5 MW wind turbine blade designs reveal that the proposed algorithm exhibits improved distribution, convergence, and converging efficiency compared to the conventional evolution algorithms such as NSGA-II. Additionally, the improvements are more significant with more objectives involved, demonstrating that the proposed algorithm can serve as a universal, high performance algorithm for the multi-objective optimization of wind turbine blade design. [ABSTRACT FROM AUTHOR]

To achieve optimal generation from a number of mixed power plants by minimizing the operational cost while meeting the electricity demand is a challenging optimization problem. When the system involves uncertain renewable energy, the problem has become harder with its operated generators may suffer a technical problem of ramp-rate violations during the periodic implementation in subsequent days. In this paper, a scenario-based dynamic economic dispatch model is proposed for periodically implementing its resources on successive days with uncertain wind speed and load demand. A set of scenarios is generated based on realistic data to characterize the random nature of load demand and wind forecast errors. In order to solve the uncertain dispatch problems, a self-adaptive differential evolution and real-coded genetic algorithm with a new heuristic are proposed. The heuristic is used to enhance the convergence rate by ensuring feasible load allocations for a given hour under the uncertain behavior of wind speed and load demand. The proposed frameworks are successfully applied to two deterministic and uncertain DED benchmarks, and their simulation results are compared with each other and state-of-the-art algorithms which reveal that the proposed method has merit in terms of solution quality and reliability. [ABSTRACT FROM AUTHOR]

In this paper, a differential evolution based multi-objective optimization algorithm is proposed to optimally size a photovoltaic water pumping system (PVPS). Non-dominated sorting and crowding distance concepts are used to increase the elitism and diversity of the proposed algorithm. The proposed objective function is composed of technical and economic objectives. Loss of load probability is used as a technical objective, whereas life cycle cost is considered as an economic objective. The proposed PVPS is designed to provide a daily water demand of 30 m 3 with a 20 m static head and a drawdown level. The optimal configuration of the system is selected from an optimal Pareto set of configurations to achieve balance between reliability, cost, and excess water of the system. The performance of the system is tested using hourly metorological data for one year time. Results show that the loss of load probability of the proposed system is around 0.5%. The life cycle cost, water deficit, and cost of water unit of the system are 9910 USD, 55 m 3 , and 0.045 USD/m 3 , respectively. [ABSTRACT FROM AUTHOR]

In this paper, a new robust LWS (least winsorized square) estimator is proposed for dynamic state estimation of a power system. One of the main advantages of this estimator is that it has an inbuilt bad data rejection property and is less sensitive to bad data measurements. In the proposed approach, Brown's double exponential smoothing technique has been utilised for its reliable performance at the prediction step. The state estimation problem is solved as an optimisation problem using a new jDE-self adaptive differential evolution with prediction based population re-initialisation technique at the filtering step. This new stochastic search technique has been embedded with different state scenarios using the predicted state. The effectiveness of the proposed LWS technique is validated under different conditions, namely normal operation, bad data, sudden load change, and loss of transmission line conditions on three different IEEE test bus systems. The performance of the proposed approach is compared with the conventional extended Kalman filter. On the basis of various performance indices, the results thus obtained show that the proposed technique increases the accuracy and robustness of power system dynamic state estimation performance. [ABSTRACT FROM AUTHOR]

In India, power shortage is a major issue for economical growth. According to the data provided by National Load Despatch Centre, peak power shortage in Tamilnadu during the year 2014 varies between 3000 MW and 4000 MW. This power shortage can be reduced by increasing installed capacity of conventional and non-conventional energy sources. But the construction of new generation plants is cost-effective and also power generation is not assured throughout the year. This power shortage can also be minimized by implementing load management in the consumer side. This paper focuses on the reduction of peak demand by the proper operating schedule of major equipments. For this analysis, three rice industries have been considered. The major operating sections in the rice industries are pre-cleaning, soaking, pre-milling and milling. In this proposed work, to reduce the peak demand, the operating time of pre-milling section is rescheduled using the optimization techniques, DE (Differential Evolution), PSO (Particle Swarm Optimization) and ABC (Artificial Bee Colony). The rescheduled results given by DE, PSO and ABC algorithms reduce the peak demand cost of the energy consumed in three rice industries. However, the optimum scheduling obtained by ABC reduces the feeder power flow than the DE and PSO scheduling. [ABSTRACT FROM AUTHOR]

This paper proposes a new, efficient and powerful heuristic-hybrid algorithm using hybrid DE (differential evolution) and PSO (particle swarm optimization) techniques DEPSO (differential evolution particle swarm optimization) designed to solve eight optimization problems with benchmark functions and the MAED (multi-area economic dispatch), RCMAED (reserve constrained MAED) and RCMAEED (reserve constrained multi area environmental/economic dispatch) problems with reserve sharing in power system operations. The proposed hybridizing sum-local search optimizer, entitled HSLSO, is a relatively simple but powerful technique. The HSLSO algorithm is used in this study for solving different MAED problems with non-smooth cost function. The effectiveness and efficiency of the HSLSO algorithm is first tested on a number of benchmark test functions. Experimental results showe the HSLSO has a better quality solution with the ability to converge for most of the tested functions. [ABSTRACT FROM AUTHOR]

We introduce a MOO (multi-objective optimization) framework for the integration of renewable DG (distributed generation) into electric power networks. The framework searches for the optimal size and location of different DG technologies, taking into account uncertainties related to primary renewable resources availability, components failures, power demands and bulk-power supply. A non-sequential MCS-OPF (Monte Carlo simulation and optimal power flow) computational model is developed to emulate the network operation by generating random scenarios from the diverse sources of uncertainty, and assess the system performance in terms of CG (global cost). To measure uncertainty in the system performance, we introduce the DCVaR (conditional value-at-risk deviation) which, due to its axiomatic relation to the CVaR (conditional value-at-risk), allows the conjoint control of risk. A MOO strategy can, then, be adopted for the concurrent minimization of the ECG (expected global cost) and the associated deviation DCVaR ( CG ). In our work this is operatively implemented by a heuristic search engine based on differential evolution (MOO-DE). An example of application of the proposed framework is given with regards to the IEEE 30 bus test system, where in DCVaR is shown capable of enabling and controlling tradeoffs between optimal expected economic performance, uncertainty and risk. [ABSTRACT FROM AUTHOR]

The global energy crunch and rising demand for electricity make it all the more important to develop energy-efficient timetable for urban rail transit trains. Under normal circumstances, the train can operate normally according to the energy-saving timetable that has been formulated. However, trains may deviate from the original schedule and increase energy consumption due to station delays. For this, how to quickly restore the train to an efficient state and effectively transport the delayed passengers to the destination as soon as possible is a challenging problem. Therefore, this paper proposed a two-stage optimization method to solve the above problem. In the first stage, an improved differential evolution algorithm was used to optimize the energy-saving operation strategy of the train without delay, and the optimal running time-energy consumption solution set of the train in the redundant running time of each section on the entire line was obtained. Then, based on this, the second stage proposed a rapid iterative method to optimize and reschedule the timetable of the delayed train in the remaining sections, and an efficient solution was obtained. Finally, Nanning Rail Transit (NNRT) Line 5 is selected for a case study, and the proposed model and method are verified. Compared with the existing solution that temporarily shortens the running time of the next section in the delayed station, the proposed method reduces the energy consumption by 3.32% on average, and the average calculation time is about 0.36 s, which showed that the method is effective and meets the real-time requirements. [ABSTRACT FROM AUTHOR]

Wind power has been utilized well in power systems, so steady and successful wind speed forecasting is crucial to security management power grid market economy. To date, most researchers have often discounted the interpretability of prediction models, leading to obscure forecasts. This study puts forward a unique forecasting methodology that incorporates notable decomposition techniques, multifactor interpretable forecasting models, and optimization algorithms. In the proposed model, variational mode decomposition is employed to break down the raw wind speed sequence into a set of intrinsic mode functions. Adaptive differential evolution is then used for optimizing several parameters of temporal fusion transformers (TFT) to achieve satisfactory forecasting performance. TFT is a new attention-based deep learning model that puts together high-performance multi-horizon prediction and interpretable insights into temporal dynamics. Empirical studies using eight real-world 1-h wind speed data sets in Albert, Canada, and Five Points, USA demonstrate that the system using the proposed model outperforms those employing other comparable models in nearly all performance metrics. Examples of TFT's interpretable outputs are the importance ranking of the decomposed wind speed sub-sequences and meteorological data and attention analysis of different step lengths. The findings signify substantial progress for wind speed prediction and aid policymakers. • Propose a novel interpretable wind speed prediction methodology named VMD-ADE-TFT. • Impacts of influencing factors are analyzed by TFT's interpretability capability. • VMD-ADE-TFT is used to achieve better forecasting accuracy for eight cases. [ABSTRACT FROM AUTHOR]

State of health (SOH) is a crucial challenge to guarantee the reliability and safety of the electric vehicles (EVs), due to the complex aging mechanism. A novel SOH estimation method based on improved long short-term memory (LSTM) and health indicators (HIs) extraction from charging-discharging process is proposed in this paper. In order to overcome the limitation of the measurement of battery capacity in real application, some external characteristic parameters related to voltage, current and temperature are selected from charging-discharging process as HIs to describe the aging mechanism of the batteries. After that, Pearson correlation coefficient is employed to select the HIs, which have high correlations with battery capacity. And neighborhood component analysis (NCA) is used to eliminate redundant information of HIs with high correlation in order to reduce computational burden. Aiming at the problem of hyperparameter selection in LSTM models, differential evolution grey wolf optimizer (DEGWO) is proposed in this paper for hyperparameters optimization. Compared with traditional grey wolf optimizer, which is easy to fall into local optimality, DEGWO updates the population through mutation, crossover and screening operations to obtain the global optimal solution and improve the global search ability. The proposed method is verified based on the dataset of the battery from NASA and MIT. The simulations indicate that the proposed method has higher accuracy for different kinds of batteries. The estimation errors for both datasets are within 1%. Compared with other methods, the estimation evaluation indicators such as RMSE, MAE and MAPE of the proposed method are within 1%, which is much less than the estimation results obtained by other methods. And determination coefficient R2 is above 0.95, which means the proposed method has batter fitting performance. It is also indicated that the method proposed in this paper has higher accuracy, better robustness and generalization. • 15 HIs extracted from charging-discharging process are used for SOH estimation. • NCA is employed to eliminate redundant information of HIs. • A novel method DEGWO-LSTM is proposed for battery SOH estimation. • Two different battery datasets are used to verify the performance of the method. [ABSTRACT FROM AUTHOR]

On the bases of meta-heuristic optimizers and experimental datasets, the parameter extraction of the proton exchange membrane fuel cells (PEMFCs) model to reach accurate current/voltage (I/V) curves remain an active research area during these last years. In this paper, an improved hybridized optimizer is developed to accurately estimate the PEMFC model parameters namely artificial bee colony differential evolution optimizer (ABCDE). In the developed ABCDE, the double execution of the mutation strategy allows enhancing the exploitation phase and avoiding to get stuck into the local minima. To assess the proposed ABCDE based parameter's identification, a comparative study with the recently published techniques including shuffled complex evolution, artificial ecosystem-based optimizer, and enhanced Lévy flight bat algorithm is performed using five typical PEMFCs modules. In this context, the reached sum of squared errors (SSE) and the standard deviations (STD) are very competitive among the challenging methodologies. ABCDE reaches the best SSE values within interesting overall STD and CPU run time less than 3e−15 and 0.225 s, respectively, for the five cases under study. It can be confirmed that the cropped SSE values and the STD among other challenging methodologies are very competitive with the best convergence speed. The ABCDE reaches 0.011697781, 2.07916558, 0.85360752, 9.6536060e−02, and 1.42098181379214e−04 for BCS 500W, NedStack PS6, Ballard Mark V, Horizon H-12, and Modular SR-12; respectively. In addition to that, the comparison results indicate that the proposed ABCDE is successfully utilized to characterize the PEMFC's model reliably and rapidly. • A hybridized ABCDE to accurately estimate the PEMFC's parameters has been proposed and validated. • Intensive verifications of ABCDE performances are demonstrated under various experimental datasets. • Double execution of the mutation strategy is used to improve the exploration and exploitation phases. • Using five commercial PEMFC stacks, the ABCDE is investigated and compared to recent published techniques. • ABCDE outperforms the competing techniques under metrics tests. [ABSTRACT FROM AUTHOR]

Despite the continuous growth and the widespread support of renewable energy sources, solar and wind power plants pose new challenges for Transmission System Operators and Distribution System Operators. Their uncontrollability limits their applicability; therefore, to encourage their further growth, fundamental modifications are needed. The research presented in this paper focuses on the predictive control of storage-based renewable power plants, and suggests a new model for profit optimization. Profit optimization is based on electricity price prediction and effective trading strategies that match the projected electricity prices. For the electricity price prediction, a recurrent Long Short-Term Memory neural network was developed and fine-tuned. For the optimization of the electricity trading, two trading strategies, namely an adaptive gradient-descent method and a differential evolution method were developed. Both optimization techniques were tested on mathematical models of most commercially available hybrid inverter systems and one year of historical data of electricity prices. As a result, a novel model predictive control workflow and sizing guide is proposed, which may significantly increase the profit generated by the system. • Energy exchange-based predictive control for storage enhanced solar power plants. • Energy price prediction with Long Short-Term Memory-based neural network. • Gradient descent and differential evolution-based trading and control strategy. • Simulations regarding the composition of the photovoltaic power plants. • The proposed trading strategies maximize the profit and enhance grid stability. [ABSTRACT FROM AUTHOR]

The present paper deals with the parameter identification of one diode model equivalent circuit of solar cell modules from real data acquired in different temperature conditions. We termed this procedure as an optimization problem and solved it through the FSDE (Free Search Differential Evolution) algorithm as well as a novel IFSDE (Improved FSDE) approach. The IFSDE is compared with other well-known metaheuristics, namely genetic algorithms, harmony search and particle swarm optimization, showing overall better results for the proposed IFSDE approach. In particular, the IFSDE is better in escaping local optima and obtained better results. Identified results are compared with acquired data, what shows the validity of the proposed algorithm. [ABSTRACT FROM AUTHOR]

In this paper, a HADE (hybrid adaptive differential evolution) algorithm is proposed for the identification problem of PEMFC (proton exchange membrane fuel cell). Inspired by biological genetic strategy, a novel adaptive scaling factor and a dynamic crossover probability are presented to improve the adaptive and dynamic performance of differential evolution algorithm. Moreover, two kinds of neighborhood search operations based on the bee colony foraging mechanism are introduced for enhancing local search efficiency. Through testing the benchmark functions, the proposed algorithm exhibits better performance in convergent accuracy and speed. Finally, the HADE algorithm is applied to identify the nonlinear parameters of PEMFC stack model. Through experimental comparison with other identified methods, the PEMFC model based on the HADE algorithm shows better performance. [ABSTRACT FROM AUTHOR]

Estimating parameters and establishing high-accuracy and high-reliability models of photovoltaic (PV) modules by using the actual current-voltage data is important to simulate, model, and optimize the PV systems. Several meta-heuristic optimization techniques have been developed to estimate the parameters of the solar PV models. However, it is still a challenging task to accurately, reliably, and quickly estimate the unknown parameters of PV models. This paper proposes a novel hybrid seagull optimization algorithm (HSOA) for estimating the unknown parameters of PV models effectively and accurately. In proposed HSOA, the personal historical best information is embedded into position search equation to improve the solution precision. A novel nonlinear escaping energy factor based on cosine function is presented for balancing global exploration and local exploitation. The differential mutation strategy is introduced to escape from the local optima. We firstly select twelve classical benchmark test functions to investigate the feasibility of HSOA, and experimental results show that HSOA is superior to most compared methods. Then, HSOA is used for solving parameters estimation problem of three benchmark solar PV models. The comparison results demonstrate that HSOA is superior to BOA, GWO, WOA, HHO, SOA, EEGWO, and ISCA on solution quality, convergence and reliability. • A hybrid algorithm called HSOA is proposed. • HSOA is applied to estimate the unknown parameters of PV models. • A modified position updating equation is presented. • A new nonlinear escaping energy strategy is designed. • Experimental results show the competitive performance of HSOA. [ABSTRACT FROM AUTHOR]

A parameter optimization method for an oscillating buoy-type wave energy converter (WEC) is presented from the perspective of submerged buoy volume; which affects both the power production and cost investment. The effects of submerged buoy volume on the optimal power capture are studied using the differential evolution algorithm and linear potential flow theory. The cost indictor V / P (V and P representing submerged buoy volume and power capture, respectively) is introduced to measure the cost-effectiveness of the WECs. The power capture and cost performance of the optimized WECs in regular and irregular waves are discussed. The results show that the WEC with the large power take-off (PTO) damping has good adaptability to a range of wave frequencies; however, the optimal submerged buoy volume is not cost-efficient due to the consequent relatively large cost indicators. The best choice of WEC in terms of cost-effectiveness is one designed with a large PTO damping and a buoy of slightly small non-optimal submerged volume. • A WEC optimization method by the differential evolution algorithm is proposed. • The optimal submerged buoy volume increases with the increase of PTO damping. • The WECs with large PTO damping extract high power in a wide submerged volume range. • A WEC with a large PTO and a volume slightly less than optimal volume is economical. [ABSTRACT FROM AUTHOR]

To improve the design and control of FC (fuel cell) models, it is important to extract their unknown parameters. Generally, the parameter extraction problems of FC models can be transformed as nonlinear and multi-variable optimization problems. To extract the parameters of different FC models exactly and fast, in this paper, we propose a transferred adaptive DE (differential evolution) framework, in which the successful parameters of the adaptive DE solving previous problems are properly transferred to solve new optimization problems in the similar problem-domains. Based on this framework, an improved adaptive DE method (TRADE, in short) is presented as an illustration. To verify the performance of our proposal, TRADE is used to extract the unknown parameters of two types of fuel cell models, i.e. , PEMFC (proton exchange membrane fuel cell) and SOFC (solid oxide fuel cell). The results of TRADE are also compared with those of other state-of-the-art EAs (evolutionary algorithms). Even though the modification is very simple, the results indicate that TRADE can extract the parameters of both PEMFC and SOFC models exactly and fast. Moreover, the V – I characteristics obtained by TRADE agree well with the simulated and experimental data in all cases for both types of fuel cell models. Also, it improves the performance of the original adaptive DE significantly in terms of both the quality of final solutions and the convergence speed in all cases. Additionally, TRADE is able to provide better results compared with other EAs. [ABSTRACT FROM AUTHOR]

Accurate estimation of battery actual capacity in real time is crucial for a reliable battery management system and the safety of electrical vehicles. In this paper, the battery capacity is estimated based on the battery surface temperature change under constant-current charge scenario. Firstly, the evolution of the smoothed differential thermal voltammetry (DTV) curves throughout the aging process is analyzed. Then, the change of the battery surface temperature, which is equivalent to the area under the DTV curve, over a specific voltage range is introduced as a direct feature of interest to reflect the battery actual capacity. In addition, the temperature variation transformation is utilized to reduce the influence of the initial battery inconsistency. Lastly, two battery degradation datasets are utilized to validate the proposed method. The maximum root mean-square errors of the estimation results by the reference correlation are less than 20 mAh and 60 mAh for the two employed batteries (respective nominal capacities are 740 mAh and 4800 mAh). Specifically, the mean estimation errors for the respective two batteries are reduced by approximately 24.74% and 39.60% after the temperature variation transformation. The proposed method is further compared with the existing DTV analysis method and demonstrates the superior performance. • Introduced battery surface temperature change over certain voltage range as FoI. • Determined voltage range based on differential thermal voltammetry analysis. • Utilized temperature variation transformation to reduce initial inconsistency. • Developed a capacity estimation method under constant-current charge scenario. • Validated the feasibility based on aging data from two different batteries. [ABSTRACT FROM AUTHOR]

The goal of the study was to develop an optimization methodology combining a cost model, a 2-D heat transfer model, and load variation, executable in a feasible time in a personal computer. The objective function to maximize is the annual net cash flow. For this purpose, the cogeneration plant performance is determined at different load points as a function of the condenser performance using IPSEpro process simulation software. This data is then used to implement the calculation process to obtain the objective function value. Due to the computationally heavy heat transfer model, and each objective function evaluation requiring multiple runs, one per load point, improving optimizer performance was given particular attention. A novel hybridization of cuckoo search and a greedy differential evolution strategy was created for this; the new algorithm is shown to perform better than either of its parent algorithms or other benchmarks, finding optimal solution reliably, and within approximately half the number of function evaluations as required by the parent algorithms. • Differental mutation methods e.g. cuckoo search do well in engineering optimization. • Heat exchanger optimization needs a cost model; area-based correlations inadequate. • Multiple load point power plant condenser optimization feasible in desktop PC. • Differential mutation can benefit from methods aimed at global exploration. [ABSTRACT FROM AUTHOR]

Dynamic economic dispatch with valve-point effects (DED_ vpe) is a high-dimensional constrained optimization problem with non-convex and non-smooth characteristics. Hybrid methods are one of the most advanced methods to solve the problem. However, most of these methods improve the solution accuracy at the expense of algorithm robustness. This paper proposes an adaptive hybrid backtracking search optimization algorithm (AHBSA) for solving the DED_ vpe. The core idea of AHBSA lies in designing a suitable coupling structure based on the current best individual (called optimal partial coupling). The structure hybridizes an improved BSA mutation operator and the DE/best/1 operator with equal probability. The improved BSA mutation operator uses the current best individual and the historical population to update individual position, called BSA/best/old. It is also the first research work of extending BSA to the problem. In addition, an adaptive parameter control mechanism is proposed to select an appropriate 'mixrate' value for achieving better coupling. The performance of AHBSA is validated on six DED test cases of three systems. Experimental results demonstrate that, compared with some representative methods, AHBSA not only reduces the fuel cost but also ensures the robustness of the algorithm. • A hybrid method AHBSA is proposed to solve DED problem with valve-point effects. • An optimal partial coupling structure is designed in AHBSA. • BSA is the first attempt at solving DED problem. • Results on six benchmark DED test cases show AHBSA is competitive. [ABSTRACT FROM AUTHOR]