Search

As a renewable and clean energy, wind energy plays an important role in easing the increasingly serious energy crisis. However, due to the strong volatility and randomness of wind speed, large-scale integration of wind energy is limited. Therefore, obtaining reliable high-quality wind speed prediction is of great importance for the planning and application of wind energy. The purpose of this study is to develop a hybrid model for short-term wind speed forecasting and quantifying its uncertainty. In this study, Minimal Gated Memory Network is proposed to reduce the training time without significantly decreasing the prediction accuracy. Furthermore, a new hybrid method combining Quantile Regression and Minimal Gated Memory Network is proposed to predict conditional quantile of wind speed. Afterwards, Kernel Density Estimation method is used to estimate wind speed probabilistic density function according to these conditional quantiles of wind speed. In order to make the model show better performance, Maximal Information Coefficient is used to select the feature variables while Genetic Algorithm is used to obtain optimal feature combinations. Finally, the performance of the proposed model is verified by seven state-of-the-art models through four cases in Inner Mongolia, China from five aspects: point prediction accuracy, interval prediction suitability, probability prediction comprehensive performance, forecast reliability and training time. The experimental results show that the proposed model is able to obtain point prediction results with high accuracy, suitable prediction interval and probability distribution function with strong reliability in a relatively short time on the prediction problems of wind speed.

In practice, the rational operation rule derived from historical information and real-time working condition can help the operators make the quasi-optimal scheduling plan of hydropower reservoirs, leading to significant improvements in the generation benefit. As an emerging artificial intelligence method, the extreme learning machine (ELM) provides a new effective tool to derivate the reservoir operation rule. However, it is difficult for the standard ELM method to avoid falling into local optima due to the random determination of both input-hidden weights and hidden bias. To enhance the ELM performance, this research develops a novel class-based evolutionary extreme learning machine (CEELM) to determine the appropriate operation rule of hydropower reservoir. In CEELM, the k-means clustering method is firstly adopted to divide all the influential factors into several disjointed sub-regions with simpler patterns; and then ELM optimized by particle swarm intelligence is applied to identify the complex input-output relationship in each cluster. The results from two reservoirs of China show that our method can obtain satisfying performance in deriving operation rules of hydropower reservoir. Thus, it can be concluded that the model’s generalization capability can be improved by isolating each subclass composed of similar dataset.

To satisfy the huge energy demand of China, a rapid development rate of hydropower system was undertaken over the past decades. Currently, thousands of hydropower reservoirs with a total installed capacity of more than 330 GW have provided approximately 20% of China’s gross electricity generation, ranked number 1 in the world. Besides, it is foreseeable that in the coming decades, the same development speed of hydropower will be maintained in order to effectively handle the increasing environment and energy problem. The dimensionality problem caused by booming system scale, unprecedented development speed and operational complexity are posing a giant challenge to the operation of large-scale hydropower system in China. Thus, after giving an overview of China’s large-scale hydropower system, this paper deeply analyses the key operation characteristics leading to the dimensionality problem and highlights the possible dimensionality reduction strategies to sharply alleviate the optimization difficulty, providing necessary technical support to achieve the goal of energy conservation and emission reduction of China. To sum up, this paper could be a good and inspiring example, contributing to the sustainable development of worldwide countries with a high proportion of hydropower integration.

Recently, the booming electricity demand and intermittent energy has sharply increased the peak shaving pressure in China. However, for a majority of regional power grids in China, the installed capacity of flexible energy (like hydropower and pumped-storage) is small and the thermal plants are asked to respond the sudden load change at peak periods. The existing method based on specialist experience and historical information may generate inferior solutions and fail to reduce the peak pressure. Thus, a practical mixed integer linear programming (MILP) model is developed for unit commitment of thermal plants with peak shaving operation aspect in regional power grid lack of flexible hydropower energy, where the goal is chosen to minimize the peak-valley difference of the residual load series obtained by subtracting all the thermal generation from the original load curve while satisfying the necessary physical constraints. The MILP model is used to the thermal system in the China’s largest regional power grid, East China Power Grid. The simulations show that the MILP model can effectively smooth the residual load curve by gathering power generation of thermal plants at peak periods. Therefore, an alternative tool is provided to alleviate the peak pressure of thermal-dominant regional power grid in China.

Short-term load forecasting plays an essential role in the safe and stable operation of power systems and has always been a vital research issue of energy management. In this research, a hybrid short-load forecasting method with Variational Mode Decomposition (VMD) and Long Short-Term Memory (LSTM) networks considering relevant factors which optimized by the Bayesian Optimization Algorithm (BOA) is studied. This method firstly decomposition with VMD which is a non-recursive signal processing technology that can decompose a signal into a discrete number of modes, then, consider the relevant factors and extend to the sequence according to the coefficient of association. Specifically, for the day type and higher or lower temperature, the nonlinear mapping is used and optimized by the BOA. Finally, the subsequences are predicted by LSTM which is a special Recurrent Neural Network with memory cells and reconstructed. To validate the performance of the proposed method, two categories of contrast methods including individual methods and decomposition-based methods are demonstrated in this study. The individual methods which without decomposition processes including LSTM, Support Vector Regression, Multi-Layered Perceptron Regressor, Linear Regression, and Random Forest Regressor, and the decomposition based methods including Empirical Mode Decomposition-Long Short-Term Memory, and Ensemble Empirical Mode Decomposition-Long Short-Term Memory. The simulation results, which developed in four periods of Hubei Province, China, show that the prediction accuracy of the proposed model is significantly improved compared with the contrast methods.

In China, due to the unbalanced distribution of energy center and load center, numerous transmission projects are built to improve the national energy allocation efficiency and the external electricity is playing an increasing important role in the daily operation of receiving-end grids. The current fixed-proportion method for energy allocation is relatively simple and easy to implement, but may produce unreasonable energy injection with the features of a straight line or “anti-peak regulation” in some cases, increasing the peak operation pressure of power systems. Thus, it is of great necessity to further improve the allocation scheme of inter-regional transmitted electricity among receiving-end power grids. As a new contribution to the research field, this paper develops a mixed integer linear programming model with the goal of minimizing the weighted peak-valley difference of multiple remaining load curves to address this problem. The presented model is applied to the East China Power Grid, and the results show that the presented model can obtain satisfying results in reducing the peak loads of multiple power grids. For instance, in the long-term simulations, the presented model can make about 23.7%, 5.9%, 5.7% and 8.3% reductions in the maximum loads of Shanghai, Jiangsu, Zhejiang and Anhui, respectively. Then, it can be concluded that optimizing the allocation of inter-regional transmitted electricity will be a viable way to reduce the peak operation pressure of multiple receiving-end power grids in China.

Due to the expanding system scale and increasing operational complexity, the cascade hydropower reservoir operation balancing benefit and firm output is becoming one of the most important problems in China’s hydropower system. To handle this problem, this paper presents a parallel multi-objective particle swarm optimization where the swarm with large population size is divided into several smaller subswarms to be simultaneously optimized by different worker threads. In each subtask, the multi-objective particle swarm optimization is adopted to finish the entire evolutionary process, where the leader particles, external archive set and computational parameters are all dynamically updated. Besides, a novel constraint handling strategy is used to identify the feasible search space while the domination strategy based on constraint violation is used to enhance the convergence speed of swarm. The presented method is applied to Lancang cascade hydropower system in southwest China. The results show that PMOPSO can provide satisfying scheduling results in different cases. For the variation coefficient of generation in 30 independent runs, the presented method can bettered the serial algorithm with about 66.67% and 61.29% reductions in normal and dry years, respectively. Hence, this paper provides an effective tool for multi-objective operation of cascade hydropower system.

The power industry is playing an increasingly important role in the world economy, and insufficient power supply may lead to huge enormous economic loss throughout the world. Then, the problem of power shortage is receiving a great deal of attention from operators and managers in electrical power system. With the merits of fast startup-shutdown, hydropower is regarded as one of the most reliable renewable energy sources to smooth the electricity shortage of power grid. Thus, this paper focuses on the operation of head-sensitive hydropower system considering power shortage aspect. To effectively address this problem, a novel method based on linear programming and successive approximation is proposed, where the initial hydraulic heads of each hydroplants is generated based on the actual working condition, and then the linear programming method is used to solve the fixed-head hydropower optimization problem involving a carefully-designed min-max optimization objective, while the successive approximation strategy is employed to incrementally improve the solution's quality by dynamically updating water heads of all the hydropower plants. The simulations demonstrate that compared with the original load demand, our method can make an average of approximate 20% reduction in electricity shortage of power system, demonstrating its effectiveness and practicability.

As one of the important renewable energy, hydropower is experiencing a booming development period throughout the world in recent years. By the end of 2016, hydropower has occupied 20.1% installed capacity and 19.5% generation in China. Thus, it is of great importance to develop some effective methods to guarantee the overall generation benefit of hydropower system. As a famous optimization tool to solve this problem, the progressive optimality algorithm cannot effectively handle with large-scale hydropower system because its computational burden grows exponentially with the increasing number of hydroplants. Thus, in order to effectively alleviate the dimensionality problem, a novel method called uniform progressive optimality algorithm is introduced here. In the presented method, the complex multistage problem is firstly divided into several two-stage optimization subproblems, and then the uniform design is adopted to sample a small subset from all the possible state vectors at each subproblem, while the successive approximation strategy is adopted to gradually improve the quality of solution. The results from a real-world hydropower system of China indicate that compared with progressive optimality algorithm, the proposed method has superior performance in execution efficiency and convergence speed, which is an effective alternative method for the complex hydropower system operation problem.

Recently, with increasing attention paid to energy production and ecological protection, the hydropower reservoirs operation balancing generation benefit and ecological requirement is playing an important role in water resource and power systems. Thus, the parallel multi-objective genetic algorithm is introduced to effectively resolve this multi-objective constrained optimization problem with two competing objectives and numerous physical constraints. In the proposed method, the original large-sized swarm is decomposed into several smaller subpopulations that will be simultaneously evolved on several computing units, effectively enhancing the execution efficiency and population diversity. During the evolutionary process, the chaotic initialization method is used to enhance the quality of initial population, while the feasible space identification method and the modified domination strategy are designed to improve the feasibility of solution and convergence rate of individuals. The results from the Wu hydropower system of China show that the presented method can make full use of computationally expensive resources to improve the performance of population. For instance, compared with the traditional method, the presented method can make 69.23% and 27.44% improvements in the standard deviation of power generation and water deficit in normal year, respectively. Thus, this paper provides an effective tool to support the multi-objective operation optimization of hydropower system.

With the rapid development of cascade reservoirs, the joint operation chart of cascade reservoirs and its optimization methods have been widely researched. Aimed at the defects of the conventional two-stage Progressive Optimality Algorithm (POA) in the optimization of energy storage operation chart, this paper proposed a new multi-stage POA optimization model. It took the traditional reverse calculation result as the initial solution, and expanded the two-stage optimization mode of conventional POA to three-stage mode, four-stage mode, or higher stages mode, and implemented the iterative calculation by taking the result of lower stages POA as the input of higher stages POA, until the result converged. In addition, enumeration method was used to iterate over all the possible combinations in local optimization to improve the efficiency of local search. In order to test and verify the rationality and validity of the proposed model, two cascade reservoirs had been taken as the instances of case study, compared with conventional two-stage POA, results showed that the power generation of Li Xianjiang and Three Gorges cascade reservoirs by the proposed multi-stage POA can respectively increase by 0.055% ($32000) and 0.077% ($3900000). So the economic benefits are remarkable, and the proposed model is reasonable and effective.

With the rapid economic growth in recent years, the peak operation of hydropower system (POHS) is becoming one of the most important optimization problems in power system. However, the rapid expansion of system scale, refined management and operational constraints has greatly increased the optimization difficult of POHS. As a result, it is of great importance to develop effective methods that can ensure the computational efficiency of POHS. The progressive optimality algorithm (POA) is a commonly used technique for solving hydropower operation problem, but its execution time still grows sharply with the increasing number of hydropower plants, making it difficult to satisfy the efficiency requirement of POHS. To address this problem, a novel efficient method called parallel progressive optimality algorithm (PPOA) is presented in this paper. In PPOA, the complex problem is firstly divided into several two-stage optimization subproblems, and then the classical Fork/Join framework is used to realize parallel computation of subproblems, making a significant improvement on execution efficiency. The simulations in a real-world hydropower system demonstrate that as compared with the standard POA, PPOA can use abundant multi-core resources to reduce execution time while keeping the quality of solution, providing a new alternative to solve the complex hydropower peak operation problem.

With the rapid economic development, the demand for energy is becoming stronger in recent years. However, due to the lack of sufficient electrical capacity to satisfy the huge load demand, the problem of energy shortage is becoming an increasingly prominent issue throughout the world. With the merits of fast startup and shutdown, hydropower is often preferred to reduce the electricity shortage of power system as much as possible. Hence, this research presents an effective optimization model for the complex variable-head hydropower system operation problem considering electricity shortage objective, and then a novel quadratic programming (QP) method is developed to resolve this model. In the QP algorithm, the domain knowledge is used to estimate the initial operation condition of hydroplants from upstream to downstream, and then the nonlinear generation characteristics of hydroplants is addressed by solving a series of subproblems with dynamically updated water head, and the quality of solution is gradually improved via iterative optimization. The simulations in different scenarios indicate that the QP method can effectively achieve the goal of reducing electricity shortages of power grid, which provides a new perspective to enrich the published knowledge in the field of hydropower operation.

With the rapid economic growth in recent years, the power demands in China keep growing and the need for reducing peak loads is becoming more prominent. With the merits of fast startup and shutdown, hydropower is often used to respond the peak load. In order to meet the practical requirement of peak operation in electrical power system, a novel min-max dynamic programming model is formulated for the peak operation of hydropower system. Then, the hybrid dynamic programming method is presented to alleviate the dimensionality problem in large-scale hydropower system, where the dynamic programming successive approximation is employed to divide the complex multi-dimensional problem into a series of small subproblems, and then the discrete differential dynamic programming is adopted to sequentially solve these subproblems. In addition, inspired by domain knowledge, the initial solution generation method and feasible space identification method are designed to promote the convergence speed of algorithm. The proposed method is used to solve the peak operation problem of a large-scale hydropower system in China. The simulations with different load demands indicate that the hybrid dynamic programming can achieve satisfactory performance in reducing peak loads of power system.

Recently, the solar photovoltaic power, a promising renewable energy, is witnessing a rapid development period. However, it is often difficult to perfectly capture the generation of solar photovoltaic plants because of various factors (like weather condition, solar radiation and human activities), increasing the operational risk and cost of power system. Hybrid energy system proves to be an effective measure to address this problem. Motivated by this practical necessity, this paper develops a novel hybrid gravitational search algorithm to solve the coordinative operation model of multiple hydropower reservoirs and solar photovoltaic power plants. In the proposed method, the gravitational search algorithm is set as the unified framework; the neighborhood search strategy is used to improve the convergence rate by considering the social information and individual experience; the adaptive mutation strategy is used to improve the population diversity by elite conservation and mutation operator; the modified elastic-ball strategy and constraint handling technique are used to enhance the solution feasibility. The simulation results of numerical functions demonstrate the superiority of the developed method in convergence rate and global search ability. The hydro–solar operation results in different cases show that compared with the traditional methods, the proposed method can yield high-quality scheduling schemes to alleviate the peak shaving pressure of power system. Thus, the novelty of this paper is to provide an effective HGSA method for solving the complex engineering optimization problem.

With the growing concerns on energy and environment, the short-term hydrothermal scheduling (SHTS) which minimizes the fuel cost and pollutant emission simultaneously is playing an increasing important role in the modern electric power system. Due to the complicated operation constraints and objectives, SHTS is classified as a multi-objective optimization problem. Thus, to efficiently resolve this problem, this paper develops a novel parallel multi-objective differential evolution (PMODE) combining the merits of parallel technology and multi-objective differential evolution. In PMODE, the population with larger size is first divided into several smaller subtasks to be concurrently executed in different computing units, and then the main thread collects the results of each subpopulation to form the final Pareto solutions set for the SHTS problem. During the evolutionary process of each subpopulation, the mutation crossover and selection operators are modified to enhance the performance of population. Besides, an external archive set is used to conserve the Pareto solutions and provide multiple evolutionary directions for individuals, while the constraint handling method is introduced to address the complicated operational constraints. The results from a mature hydrothermal system indicate that when compared with several existing methods, PMODE can obtain satisfactory solutions in both fuel cost and environmental pollutant, which is an effective tool to generate trade-off schemes for the hydrothermal scheduling problem.

As a popular optimization tool for multi-stage sequential decision problems, dynamic programming (DP) has been widely used to handle with hydropower system operation problems. However, the DP computational burden shows an exponential growth with the increasing number of hydroplants, which results in “the curse of dimensionality” and limits its application to resolve large and complex hydropower operation problem. Thus, this paper presents a novel modified DP algorithm called uniform dynamic programming (UDP) to alleviate the dimensionality problem of dynamic programming. In UDP, the uniform design is first used to construct the state variables set of each period by selecting some small but representative discrete state combinations, and then the DP recursive equation is used to find an improved solution for the next computation cycle. The UDP method is tested in the Wu River cascaded hydropower system of southwest China. The results indicate that the proposed UDP algorithm has competitive performance in computational efficiency and convergence speed, which is an effective tool for hydropower operation problem.

With the rapid economic development in recent years, the peak load demands of China are experiencing a booming period. As a regional power grid with the maximum electrical load in the world, the East China Power Grid (ECPG) is in charge of coordinating simultaneously the power generation of its own power plants to several subordinate provincial power grids. However, due to unreasonable power structure, there is a lack of flexible energy to quickly respond the peak loads of multiple power grids, which has brought a new real challenge for the dispatching center of most regional power grids in China. Hence, to meet the practical requirement of peak shaving operation in China, a novel linear programming optimization model is proposed in this paper to find out the optimal quarter-hourly generation allocation plan while satisfying a group of complex constraints. In this model, the objective is to minimize the summation of peak-valley difference of the residual load series by subtracting the total allocated generation from the original load of each power grid. This model is used to solve the day-head peak operation of 14 hydro-thermal-nuclear plants serving multiple power grids in ECPG. The results from different cases show that compared with the current method used in practical engineering, the proposed model is capable of providing results with smoother remaining load series for each power grid. Thus, this method proves to be effective technique to provide scientific decision support for large-scale generation allocation of plants serving multiple interconnected power grids in China.

With increasing attention paid to energy and environment in recent years, the hydrothermal scheduling considering economic and environmental objectives is becoming one of the most important optimization problems in power system. With two competing objectives and a set of operation constraints, the economic environmental hydrothermal scheduling problem is classified as a typical multi-objective nonlinear constrained optimization problem. Thus, in order to efficiently resolve this problem, the multi-objective quantum-behaved particle swarm optimization (MOQPSO) is presented in this paper. In MOQPSO, the elite archive set is adopted to conserve Pareto optimal solutions and provide multiple evolutionary directions for individuals, while the neighborhood searching and chaotic mutation strategies are used to enhance the search capability and diversity of population. Furthermore, a novel constraint handling method is designed to adjust the constraint violation of hydro and thermal plants, respectively. In order to verify its effectiveness, the MOQPSO is applied to a classical hydrothermal system with four hydropower plants and three thermal plants. The simulations show that the proposed method has competitive performance compared with several traditional methods.

With the fast development of hydropower in China, a group of hydropower stations has been put into operation in the past few decades and the hydropower system scale is experiencing a booming period. Hence, the “curse of dimensionality” is posing a great challenge to the optimal operation of hydropower system (OOHS) because the computational cost grows exponentially with the increasing number of plants. Discrete differential dynamic programming (DDDP) is a classical method to alleviate the dimensionality problem of dynamic programming for the OOHS, but its memory requirement and computational time still grows exponentially with the increasing number of plants. In order to improve the DDDP performance, a novel method called orthogonal discrete differential dynamic programming (ODDDP) is introduced to solve the OOHS problem. In ODDDP, orthogonal experimental design is employed to select some small but representative state combinations when constructing the corridor around the current trajectory, and then dynamic programming recursion equation is used to find an improved trajectory for the next iteration. The proposed method is applied to the optimal operation of a large-scale hydropower system in China. The results indicate that compared to the standard DDDP, ODDDP only needs about 0.37% of computing time to obtain the results with about 99.75% of generation in the hydropower system with 7 plants and 3 states per plant, providing a new effective tool for large-scale OOHS problem.

Reliable and stable hydrological prediction plays a vitally crucial role in the scientific operation of water resources system. As a famous artificial intelligence method for hydrological forecasting, extreme learning machine (ELM) has the virtues of fast training efficiency and strong generalization performance but is easily trapped into local optima because the preset computation parameters often remain unchanged in the learning process. In order to overcome this shortcoming, a practical evolutionary artificial intelligence model is developed for multiple scales nonstationary hydrological time series prediction. In the proposed method, an emerging evolutionary method called cooperation search algorithm (CSA) is used to search for the optimal input-hidden weights and hidden biases of the ELM model for the first time. The proposed method is used to forecast the runoff time series of three real-world hydrological stations in China. The experimental results show that the CSA approach can effectively determine satisfying network parameters of the ELM model, while our method can produce better results than the traditional ELM method in terms of all the performance evaluation indexes. Taking 1-step-ahead runoff forecasting at station B as an example, our method betters the ELM method with 15.76% and 42.35% improvements in both root mean squared error and mean absolute percentage error at the testing phase. Thus, a novel multiscale nonstationary hydrological prediction tool is developed to support the decision-making of water resource system.

Accurate future runoff prediction information is of great importance for the planning and management of both water resource and electric power systems. As employed to address the hydrological forecasting problem, artificial neural network (ANN) exhibits strong generalization and flexibility, but usually suffers from some shortcomings in practice, like unsatisfying learning efficiency and local convergence. The goal of this research is to develop a parallel computing and swarm intelligence based artificial neural network for multi-step-ahead hydrological time series prediction. Specially, the connection weights and biases of the ANN model are incrementally optimized via a parallelized particle swarm optimization obeying the Fork/Join framework, where the large-scale swarm is divided into a series of small and independent subswarms that will search for the optimal solution in the feasible space at the same time. The proposed method is driven to forecast the runoff time series of two real-world hydrological stations in China. The simulations indicate that the proposed method betters the conventional forecasting methods with respect to various indexes in different cases. For instance, in the 2-step-ahead case, the proposed method betters ANN with about 6.4 % improvement in the Nash-Sutcliffe efficiency value during the testing phase. Hence, the main contribution of this research is the utilization of swarm intelligence algorithm and high-performance parallel computing technique to improve the artificial intelligence model’s performances in time series forecasting.

This paper develops a novel population-based evolutionary method called cooperation search algorithm (CSA) to address the complex global optimization problem. Inspired by the team cooperation behaviors in modern enterprise, the CSA method randomly generates a set of candidate solutions in the problem space, and then three operators are repeatedly executed until the stopping criterion is met: the team communication operator is used to improve the global exploration and determine the promising search area; the reflective learning operator is used to achieve a comprise between exploration and exploitation; the internal competition operator is used to choose solutions with better performances for the next cycle. Firstly, three kinds of mathematical optimization problems (including 24 famous test functions, 25 CEC2005 test problems and 30 CEC2014 test problems) are used to test the convergence speed and search accuracy of the CSA method. Then, several famous engineering optimization problems (like Gear train design, Welded beam design and Speed reducer design) are chosen to testify the engineering practicality of the CSA method. The results in different scenarios demonstrate that as compared with several existing evolutionary algorithms, the CSA method can effectively explore the decision space and produce competitive results in terms of various performance evaluation indicators. Thus, an effective tool is provided for solving the complex global optimization problems.

Accurate river flow forecasting is of great importance for the scientific management of water resources system. With the advantages of easy implementation and high flexibility, artificial neural network (ANN) has been widely employed to address the complex hydrological forecasting problem. However, the conventional ANN method often suffers from some defects in practice, like slow convergence and local minimum. In order to enhance the ANN performance, this study proposes a hybrid river flow forecasting method by integrating the novel cooperation search algorithm (CSA) into the learning process of ANN. In other words, the computational parameters of the ANN network (like threshold and linking weights) are iteratively optimized by the CSA method in the feasible state space. The proposed method is applied to the river flow data collected from two real-world hydrological stations in China. Several Quantitative indexes are chosen to compare the performance of the developed models, while the comprehensive analysis between the simulated and observed flow data are conducted. The experimental results show that in different scenarios, the hybrid method based on ANN and CSA always outperforms the control models and yields superior forecasting results during both training and testing phases. In Three Gorges Project, the presented method makes 11.10% and 5.42% improvements in the Nash–Sutcliffe efficiency and Coefficient correlation values of the standard ANN method in the testing phase. Thus, this interesting finding shows that the performance of the artificial intelligence models in river flow time series forecasting can be effectively improved by metaheuristic algorithm with outstanding global search ability.

Accurate runoff forecasting plays an important role in guaranteeing the sustainable utilization and management of water resources. Artificial intelligence methods can provide new possibilities for runoff prediction when the underlying physical relationship cannot be explicitly obtained. However, few reports evaluate the performances of various artificial intelligence methods in forecasting daily streamflow time series for sustainable water resources management by far. To refill this research gap, the potentials of five artificial intelligence methods in daily streamflow series prediction are examined, including artificial neural network (ANN), adaptive neural-based fuzzy inference system (ANFIS), extreme learning machine (ELM), Gaussian process regression (GPR) and support vector machine (SVM). Four quantitative statistical indexes are chosen as the evaluation benchmarks. The results from two huge hydropower reservoirs in China show that five artificial intelligence methods can achieve satisfying forecasting results, while the SVM, GPR and ELM methods can produce better performances than ANN and ANFIS in both training and testing phases with respective to four indexes. Thus, it is of great importance to carefully choose the appropriate forecasting models based on the actual characteristics of the studied reservoir.

Sine cosine algorithm (SCA) is an emerging meta-heuristic method for the complicated global optimization problems, but still suffers from the premature convergence problem due to the loss of swarm diversity. To improve the SCA performance, this paper develops a modified sine cosine algorithm coupled with three improvement strategies, where the quasi-opposition learning strategy is used to balance global exploration and local exploitation; the random weighting agent produced by multiple leader solutions is integrated into the agent’s evolution equation to improve the convergence rate; the adaptive mutation strategy is designed to increase the swarm diversity. The proposed method is compared with several famous evolutionary methods on 12 classical test functions, 24 CEC2005 composite functions and 30 CEC2017 benchmark functions. The results show that the proposed method outperforms several control methods in both solution quality and convergence rate. Then, the long-term operation optimization of multiple hydropower reservoirs in China is chosen to testify the engineering practicality of the developed method. The simulation results indicate that in different scenarios, the proposed method can produce satisfying scheduling schemes with better objective values compared with several existing evolutionary methods. Hence, a novel optimizer is provided to handle the complicated engineering optimization problem.

Recently, the multiple hydropower reservoirs operation optimization is attracting rising concerns from researchers and engineers since it can not only improve the utilization efficiency of water resource but also increase the generation benefit of hydropower enterprises. Mathematically, the reservoir operation problem is a typical multistage constrained optimization problem coupled with numerous decision variables and physical constraints. Sine cosine algorithm (SCA), a new swarm-based method, has the merits of clear principle and easy implementation but suffers from the premature convergence and falling into local optima. To improve the SCA performance, this paper proposes an adaptive sine cosine algorithm (ASCA) where the elite mutation strategy is used to increase the population diversity, the simplex dynamic search strategy is used to enhance the solution quality, while the neighborhood search strategy is used to improve the convergence rate. The simulations of 25 test functions show that ASCA outperforms several existing methods in both convergence rate and solution quality. The results of a real-world hydropower system in China demonstrate that ASCA betters the SCA method with obvious increase in power generation. Thus, the main contribution of this study is to provide an effective optimizer for multiple hydropower reservoirs operation.

Generally, the multireservoir system operation optimization (MSOO) is classified as a large-scale and multi-stage optimization problem with a set of complex constraints. Here, the goal of MSOO is chosen to determine the optimal operation policy of all the reservoirs to minimize the energy deficit of electrical system. In order to effectively resolve this problem, a hybrid quantum-behaved particle swarm optimization (HQPSO) is developed in this study. In HQPSO, the external archive set conserving the elite particles is used to provide multiple search directions for various agents; the modified evolution strategy and mutation operator are used to enhance the convergence rate of the swarm; while a practical heuristic constraint handling method is employed to address the complex physical constraints imposed on all the hydropower reservoirs. The simulations of 12 benchmark functions indicate that HQPSO can produce better results than several existing evolutionary methods. Then, two multireservoir systems are chosen to verify the performance of the proposed method. The results show that compared with the conventional methods, the HQPSO method can obtain scheduling results with better performances in reducing the energy deficits of power system. Hence, this paper provides an effective tool for the complex multireservoir system operation problem.

Accurate monthly runoff prediction plays an important role in the planning and management of water resources. However, owing to climate changes and human activities, natural runoff often contains a variety of frequency components, and existing monthly runoff estimation techniques may fail to capture potential change processes effectively. To overcome this problem, we have developed a hybrid model for monthly runoff prediction. First, observed runoff is decomposed into several subcomponents via variational mode decomposition. Second, support vector machine models based on quantum-behaved particle swarm optimization are adopted to identify the input-output relationships hidden in each subcomponent. Finally, the total output of all submodules is treated as the final forecasting result for the original runoff. Three quantitative indexes are considered to test the performance of the developed models. The monthly streamflow of two reservoirs in China’s Yangtze Valley is considered as the survey target. This area contains the world’s largest hydropower project (Three Gorges Reservoir) and the waterhead of the middle line of Asia's largest inter-basin water transfer project (Danjiangkou Reservoir). Test results indicate that the hybrid model provides better forecasting accuracy compared to several traditional methods (artificial neural networks and extreme learning machines), making it an effective tool for the scientific operation of hydropower reservoirs.

Traditional power generation operation of reservoir mainly considers the maximization of power generation and guarantees the stability of the power system. However, blindly considering power generation objectives may ignore its impact on the ecological environment and navigation. A multi-objective optimization operation model considering power generation, ecological and navigation objectives is established in this paper. In order to efficiently solve the model, a new Improved Multi-objective Moth-flame Optimization Algorithm based on R-domination (R-IMOMFO) has been proposed. In order to enhance the ability of Moth-flame Optimization Algorithm (MFO) to overcome falling into the local optimum, it is improved from three aspects: update formula, inspiration of moth linear flight path and flame population update strategy, called improved MFO (IMFO) algorithm. In order to distinguish these individuals who are not dominated by each other in Pareto domination, the R-domination is proposed in combination with reference points. To verify the performance of IMFO and R-domination separately, different evolutionary algorithms and multi-objective mechanisms are combined to generate five new algorithms. Five new algorithms and five state-of-the-art algorithms are tested on the benchmark functions and reservoir operation model. The test results show that the proposed R-IMOMFO algorithm has the ability to obtain a set of solution with good convergence and strong distribution in the optimization operation problem of cascade reservoirs. Finally, the relationships between the objectives of the operation model are explored by the set of solution obtained by R-IMOMFO and the reason for the relationships is analyzed. The operation results show that the ecological demand and navigation demand have obvious contradictory relationships.

Gravitational search algorithm (GSA) is an evolutionary algorithm developed to solve the global optimization problems, but still suffers from the premature convergence problem due to the loss of swarm diversity. In order to improve the GSA performance, this paper develops a novel multi-strategy gravitational search algorithm (MGSA) where the Levy flight strategy is adopted to increase the local search ability of the global best-known agent; and then the mutation strategy is used to improve the swarm diversity in the evolutionary process; finally, the elitism selection strategy is used to enhance the exploration ability and convergence speed of the swarm. The MGSA method is compared with several methods in 24 famous benchmark functions, and the results demonstrate the superiority of the MGSA method in both search ability and convergence rate. Next, the MGSA method is used to solve the ecological operation problem of the Wu hydropower system. The results indicate that compared with several existing methods, MGSA can obtain better scheduling schemes to make obvious reductions in the inappropriate ecological water volume in different scenarios. Thus, this paper provides a new effective tool for the complex engineering optimization problems.

Reliable and accurate probabilistic forecasting of wind speed is of vital importance for the utilization of wind energy and operation of power systems. In this paper, a probabilistic spatiotemporal deep learning model for wind speed forecasting is proposed. The underlying wind turbines are embedded into a grid space, which fully expresses the spatiotemporal variation process of the airflow. Thus, advanced image recognition methods can be employed to solve the spatiotemporal wind speed forecasting problem. The proposed model is based on a spatial–temporal neural network (STNN) and variational Bayesian inference. The proposed STNN combines the convolutional GRU model and 3D Convolutional Neural Network and uses an encoding-forecasting structure to generate the spatiotemporal predictions. Variational Bayesian inference is employed to obtain the approximated posterior parameter distribution of the model and determine the probability of the prediction. The proposed model is applied in two real-world case studies in United States. The experimental results demonstrate that the proposed model significantly outperforms other models in both forecast skill and forecast reliability. The uncertainty estimation is also shown and it demonstrates that the proposed model is able to provide effective uncertainty estimation in both the time level and space level.

In China, many cascade hydropower reservoirs are asked to simultaneously respond the peak loads of several interconnected power grids based on the signed agreements. However, by far, there are few reports addressing the brand-new engineering problem with huge optimization difficulty caused by multilateral generation contracts, strong hydraulic-electric relationships, load feature differences and spatial-temporal coupled constraints. Here, a three-stage hybrid method is developed to satisfy this practical requirement, where the domain knowledge is firstly used to build a virtual load curve balancing the load features and electricity contracts of multiple power grids; secondly, the dynamic programming is used to determine the scheduling process of the optimized hydroplant, while the linear programming is chosen to allocate the hydropower generation among multiple power grids; finally, the quality of solution is gradually improved via iterative search. The results in two real-world cascade hydropower systems indicate that the hybrid method can achieve satisfactory scheduling results in different cases. Thus, an effective way to reduce the optimization difficulty of the large and complex problem is to break up into a series of simple and independent subproblems to be addressed by existing mature methods.

With growing attentions paid to ecological protection in recent years, the ecological operation of cascade hydropower reservoirs is becoming an increasingly significant problem in water resource system. Mathematically, the ecological operation of cascade hydropower reservoirs is a high-dimensional, nonlinear and strong spatiotemporal coupling constrained optimization problem. To overcome the premature convergence and stagnation search of traditional methods in resolving this problem, this paper develops a novel algorithm known as simplex quantum-behaved particle swarm optimization, where the probabilistic mutation operator is performed on historical best position of some individuals, and then the simplex neighborhood search strategy based on the dynamic probability identification is used to enhance the local exploration ability of the swarm. The numerical experiments of 17 classical test functions indicate that the presented method can achieve satisfactory results in both convergence speed and global search ability. The application results from China’s Wu hydropower system indicate that our method has satisfying performance in reducing the ecological water shortage. Hence, this paper provides a novel effective tool for the complex ecological operation problem of cascade hydropower reservoirs.

Monthly streamflow prediction plays a significant role in reservoir operation and water resource management. Hence, this research tries to develop a hybrid model for accurate monthly streamflow prediction, where the ensemble empirical mode decomposition (EEMD) is firstly used to decompose the original streamflow data into a finite amount of intrinsic mode functions (IMFs) and a residue; and then the extreme learning machine (ELM) is employed to forecast each IMFs and the residue, while an improved gravitational search algorithm (IGSA) based on elitist-guide evolution strategies, selection operator and mutation operator is used to select the parameters of all the ELM models; finally, the summarized predicated results for all the subcomponents are treated as the final forecasting result. The hybrid method is applied to forecast the monthly runoff of Three Gorges in China, while four quantitative indexes are used to test the performances of the developed forecasting models. The results show that EEMD can effectively separate the internal characteristics of the original monthly runoff, and the hybrid model is able to make an obvious improvement over other models in hydrological time series prediction.

This paper presents the static magnetic and microwave characterization of hexagonal ferrite BaZn 1.1 Co 0.9 Fe 16 O 27 particles for application in a microwave absorber. The hexagonal ferrite particles have been developed through conventional ceramic processes. Ferrite particles were examined via scanning electron microscope, X-ray diffraction and vibrating sample magnetometry. The complex permeability and permittivity of ferrite-wax composites were measured over the frequency range of 2–8 GHz. The microwave intrinsic permeability and permittivity spectra have been presented, which were calculated on the basis of the measurement data of the ferrite–wax mixtures using the Bruggeman equation. The microwave absorption properties of these ferrite particles have also been discussed. The results indicate that these ferrites have good potential to be used as a broad band microwave absorber.