Search

Electricity demand forecasting plays a crucial role in the operation of electrical power systems because it can provide management decisions related to load switching and power grid. Thus, there have been models developed to estimate the electricity demand. However, inaccurate demand forecasting may raise the operating cost of electric power sector, which means that it would waste considerable money. In this paper, a novel modeling framework was proposed for forecasting electricity demand. Sample entropy was developed to identify the nonlinearity and uncertainty in the original time series, after that redundant noise was removed through a decomposition technique. Besides, the most optimal modes of original series and the optimal input form of the model were determined by the feature selection method. Finally, electricity demand series can be conducted forecasting through least squares support vector machine tuned by multi-objective sine cosine optimization algorithm. The case studies of Australia demonstrated that the proposed framework can ensure high accuracy and strong stability. Thus, it can be considered as a useful tool for electricity demand forecasting.

The paper is concerned with the distributed optimization problem (DOP) for a class of uncertain multi-input-multi-output (MIMO) nonlinear multi-agent systems with arbitrary relative degree. The target is to design distributed control laws such that the outputs of the agent systems converge to a consensus value and on which the sum of the local cost functions is minimized. By introducing pseudo gradient technique, internal model technique and adaptive control technique, a novel state based distributed control law is firstly constructed. An incremental type Lyapunov function based approach is presented to show that the proposed DOP is solved by the state based control law without requiring the eigenvalue information of Laplacian matrix. By further introducing distributed high-gain observer technique, an output based distributed control law is constructed and by which the DOP is solved under some mild assumption. The proposed control laws are validated on a group of Euler-Lagrange systems, a group of robot manipulators with flexible joints and a group of Chua circuit systems. The simulation results illustrate the effectiveness of the proposed methods.

The paper is concerned with the containment problem of a multi-agent system with each agent being described by an Euler–Lagrange (EL) equation with uncertain parameters. Distributed adaptive contro...

This paper is concerned with the distributed optimization problem for a class of minimum-phase nonlinear multiagent systems with second relative degree. The target is to minimize a cost function composed of a group of convex local functions of the outputs in a cooperative manner. Novel state feedback control laws are first proposed and the consensus subject to the optimization constraint is achieved when the communication graph is directed. By replacing the derivatives of the outputs in the state feedback control laws with their estimations, the output feedback control laws are constructed and proved to achieve exponential consensus under the undirected graph. The effectiveness of the proposed control laws is validated by some simulations.

Wind energy is attracting increasing attention with its sustainability and cleanliness. However, owing to the volatility and intermittency of wind speed, it is challenging to establish a scientific and reliable forecasting system. Most research has mainly been based on simple data preprocessing, single objective optimization, and point prediction, which may lead to poor forecasting performance. Hence, in this study, an innovative wind speed forecasting system is developed that incorporates effective data preprocessing and a novel algorithm. In order to alleviate the complexity and chaos of a wind speed series, a fuzzy data preprocessing scheme is designed based on “decomposition and ensemble” and a fuzzy time series. Following this, a multi-objective imperialist competitive algorithm (MOICA) is proposed and applied for optimizing an extreme learning machine (ELM), and a corresponding hybrid predictor MOICA-ELM is conducted for wind speed forecasting. For further investigation the uncertainty of wind speed, both point and interval forecasting are employed in this system. Simulation results on four wind speed datasets collected from two wind farms in China are in good accordance with the empirical data with multiple criterion and scientific evaluation; these results and show a good performance of the proposed system in terms of accuracy and stability.

A composite forecasting framework is designed and implemented successfully to estimate the prediction intervals of wind speed time series simultaneously through machine learning method embedding a newly proposed optimization method (multi-objective salp swarm algorithm). In this study, data pre-process strategy based on feature extraction is served for reducing the fluctuations of wind power generation and select appropriate input forms of wind speed datasets for the sake of improving the overall performance. Besides, fuzzy set theory selection technique is used to determine the best compromise solutions from Pareto front set deriving from the optimization phase. To test the effectiveness of the proposed composite forecasting framework, several case studies based on different time-scale wind speed datasets are conducted. The corresponding results present that the proposed framework significantly outperforms other benchmark methods, and it can provide very satisfactory results in both goals between high coverage and small width.

In this article, we consider the regulator design problem for a class of uncertain multi-input-multioutput (MIMO) nonlinear systems with arbitrary relative degree. The objective is to regulate the output of the nonlinear system to an optimal steady state that solves a constrained optimization problem, without computing the optimal solution in advance. By embedding saddle-point dynamics, both state and output-feedback-based regulators are proposed and the resulting closed-loop systems are modeled in standard singularly perturbed forms. By invoking the singular perturbation analysis, exponential stability is established under some regularity condition. Compared with the existing methods, the proposed regulators can deal with a class of nonlinear systems with uncertainties and arbitrary relative degree. Furthermore, the current results can include some recent works on the distributed optimization problem as special cases. Finally, the effectiveness of the proposed methods is validated through numerical simulations.

This article pays close attention to a distributed optimization problem for multiagent systems subject to exogenous disturbances. A novel distributed model reference adaptive control (D-MRAC) scheme is proposed that no explicit disturbance observer or internal model unit is involved, which not only enhances robustness but also improves transient performance. In contrast to the continuous communication that is often assumed in the existing distributed optimization works, the new method allows for more realistic scenarios in which the agents communicate with each other at discrete-time instants. It is shown by Lyapunov analysis that the concerned distributed optimization problem can be solved by the proposed D-MRAC scheme as long as the communication interval is smaller than a given threshold, which can be calculated by following the steps given in this article. Numerical simulations have shown the effectiveness of the presented method.

The paper is concerned with the distributed optimization problem for a class of higher order linear multi-agent systems. The target is to cooperatively optimize a performance function formed by a sum of convex local cost functions. To deal with the higher order dynamic, the integrator backstepping idea is introduced to break the integrator chains. Moreover, the adaptive gain technique is proposed such that the control law design can be performed in a fully distributed way, i.e., without utilizing the information of Laplacian matrix. Furthermore, the proposed scheme is applied to the control law design for the consensus of networked uncertain Euler-Lagrangian systems under optimization constraint. The effectiveness of the proposed methods is validated through some numerical simulations of a group of networked uncertain robot manipulators.

Air pollution poses a substantial threat to society and is considered one of the greatest environmental hazards for human beings. It is of great importance to develop air pollution early warning systems to alleviate the urgency and necessity of air quality monitoring and analysis. However, current early warning systems rarely focus on mining of pollutant characteristics and their corresponding scientific evaluation. In this study, we investigate an innovative hybrid air quality early warning system that comprises characteristics estimation, prediction, and evaluation. First, four different distribution functions with two estimation methods were applied for quarrying the characteristics of pollutants; Afterward, a hybrid forecasting model was proposed combined with an advanced data processing technique—a neural network and a new heuristic algorithm. For further mining the features of pollutants, two interval approaches as well as Extenics evaluation were utilized as indispensable components of the developed system. Simulation of pollutants series, including PM 2.5 , SO2, NO2, CO, and O3 are in line with lognormal distribution using certain parameters, and forecasting results are in good accordance with the empirical data using multiple criterion systems, i.e., MAE, MSE, RMSE, MAPE, MdAPE, FB, DA, and R 2 for deterministic forecasting and with IFCP and IFNAW for interval forecasting. Eight deterministic forecasting criterion for pollutants forecasting measurement indicate that the developed early warning system can achieve good performance in terms of its accuracy and effectiveness. Additionally, the positive interval forecasting results and good precision of Extenics evaluation indicate the efficiency and scalability of the designed early warning system.

Accurate forecast of wind speed is the first prerequisite to supply high quality power energy to customer in a secure and economic manner. However, traditional point forecast may not be sufficiently reliable and accurate for decision-makers to perform operational strategies purely when the uncertainty level increases. For the sake of quantifying the uncertainty associated with point predictions, it is necessary to conduct interval prediction to provide reliable and accurate wind speed information. In this work, a hybrid model framework based on combinatorial modules was proposed and successfully adopted to construct the prediction intervals of the future wind speed. Feature selection methods are developed to determine the most suitable modes of original time series and the optimal input form of the model, while the optimization forecasting module is applied to model the wind speed series based on the machine learning method and the multi-objective optimization algorithm, then the compromise solution of Pareto front is chosen by “Min-max” method. Finally, the proposed combined model was investigated via the hourly wind speed data from two different periods in Penglai, China. Besides, the study’s experimental results indicated that the prediction intervals generated perform well and are satisfactory in both criterion functions of high coverage and small width through discussion among single-objective models and other multi-objective models (signal pre-processing method comparison included).

In the current paper the decentralized output regulation problem of a new class of interconnected uncertain nonlinear systems is considered. A novel decentralized high-gain input driven filter is proposed such that the output feedback based control law can be designed. Moreover, a robust multi-input changing supply function technique is presented such that the stability analysis can be performed by the non-quadratic Lyapunov functions. Therefore, the assumptions on the interconnection terms can be removed. Finally the proposed decentralized control laws are applied to the interconnected mass-spring systems immersed in the liquid and the simulation results illustrate the effectiveness of the proposed control scheme.

Portending and mastering the atmospheric quality plays a significant role in polishing up people's daily life and preventing the environment against serious pollution because air pollution has exceeded the international warning level. Since, accurate contaminants concentration forecasting and objective evaluation, which is urgent to establish an early-warning system, is a critical issue for the social community. An early-warning framework based on two modules composed of forecasting part and assessment part is proposed and successfully adopted in this paper. The forecasting part is applied to a hybrid optimization model with improved Harmony Search Algorithm with PSO strategy to forecast air contaminants concentration, while the assessment part is applied to Fuzzy Synthetic Evaluation Model with entropy weight to evaluate the air quality levels. The proposed early-warning system was investigated in three cities of Jing-Jin-Ji region of China where there exists serious air pollution for the period August 1st 2015 to September 29st 2016. The findings showed that the forecasting model is greatly superior to statistical model and other models on the urban pollutant concentration data. According to the results of air quality assessment, the evaluation model based on the entropy technique can objectively assess the atmospheric quality level.

Rolling bearings play a vital role in the overall operation of rotating machinery. In practice, many learning methods for variable-speed fault diagnosis ignore task-specific decision boundaries, making it very difficult to completely match feature distribution between different domains. Therefore, to overcome this problem, an adversarial domain adaptation of asymmetric mapping with CORAL alignment is presented. The asymmetric mapping feature extractor is able to extract more specific-domain features with obvious distinction. Meanwhile, combining the maximum classifier discrepancy of deep transfer to give an adversarial approach and taking the task-specific decision boundaries into account, class-level alignment between the features of the source domain and target domain can be attempted. To prevent degenerate learning, which is possibly caused by asymmetric mapping and adversarial learning, the model is constrained by deep CORAL alignment to extract more domain-invariant features. Experimental results show that the proposed method can solve the variable-speed (a small span of intermediate vehicle speeds) fault diagnosis problem well, with high transfer accuracy and strong generalization.

Forecasting crude oil prices is an essential research field in the international bulk commodities market. However, price movements present more complex nonlinear behavior due to an increasingly diverse range of risk factors. To achieve better accuracy, this study explores a novel multiscale hybrid paradigm to estimate crude oil prices. The method takes advantage of the variational mode decomposition method to decompose the crude oil price into several simple models, which can be explained using regular factors, irregular factors and trends. Data characteristic analysis is conducted to identify the complexity of different components of the time series. It is important for a multiscale model to select an appropriate model to produce the optimal forecasts. Thus, the final forecasted values are generated by reconstituting all these forecasting items. By investigating the West Texas Intermediate and Brent crude oil prices, this paper presents how data characteristic identification and analysis are conducted in a multiscale paradigm. The empirical analysis proves that the proposed model can achieve superior forecasting results, which indicates the effectiveness of the multiscale model at forecasting complex time series, especially crude oil prices.

With the increasing contribution of the power production by the photovoltaic (PV) systems to the electricity supply, the PV power forecasting becomes increasingly important. There are many factors influencing the forecasting performance, such as the air temperature, humidity, insolation, wind speed, wind direction and so on. This study proposes a Takagi-Sugeno (T-S) fuzzy model-based PV power short-term forecasting approach. First, by means of the correlation analysis, the influential factors are selected as the model inputs. Then, the fuzzy c-mean clustering algorithm and the recursive least squares method are used to identify the antecedent and the consequent parameters. The performance of the proposed forecasting approach is tested by using a large database of measurement data from the 433 kW PV array at St Lucia campus of The Queensland University of Australia. The forecasting results are compared with the support vector machine (SVM), the hybrid of empirical mode decomposition and SVM, the back propagation neural network and the recurrent neural network. The results indicate that, compared with the existing approaches, the proposed T-S fuzzy model-based forecasting approach is simpler and can forecast more accurately.

Accurate wind power and wind speed forecasting remains a critical challenge in wind power systems management. This paper proposes an ultra short-time forecasting method based on the Takagi−Sugeno (T−S) fuzzy model for wind power and wind speed. The model does not rely on a large amount of historical data and can obtain accurate forecasting results though efficient linearization. The proposed method employs meteorological measurements as input. Next, the antecedent and the consequent parameters of the forecasting model are identified by the fuzzy c-means clustering algorithm and the recursive least squares method. From these components, the T−S fuzzy model is obtained. Wind farms located in China (Shanxi Province) and in Ireland (County Kerry) are considered as cases with which to validate the proposed forecasting method. The forecasting results are compared with results from the contemporary machine learning-based models including support vector machine (SVM), the combined model of SVM and empirical mode decomposition, and back propagation neural network methods. The results show that the proposed T−S fuzzy model can effectively improve the precision of the short-term wind power forecasting.

The paper is concerned with the distributed optimization problem for a class of nonlinear multi-agent systems with second relative degrees. Unlike the existing results on control law design that rely on the high-gain or backstepping techniques, novel distributed control law is proposed such that a sum of convex local cost functions is minimized on the consensus value, where the gradients of the convex functions are locally Lipschitz. A contraction theory approach is introduced to show the incremental stability of the closed-loop system. Due to the introduction of the non-Lipschitz nonlinear gradients, the Euclidean metric is not suitable for characterizing the distance between two trajectories of a convergent system on differentiable manifolds. Motivated by this, a Finsler-Lyapunov function is constructed to invoke the Finsler distance that is shrinking along the trajectories. The effectiveness of the proposed methods is validated through some numerical simulations of a group of networked nonlinear tunnel-diode circuit systems.

Due to the mechanical equipment working under variable speed and load for a long time, the distribution of samples is different (domain shift). The general intelligent fault diagnosis method has a good diagnostic effect only on samples with the same sample distribution, but cannot correctly predict the faults of samples with domain shift in a real situation. To settle this problem, a new intelligent fault diagnosis method, domain adaptation network with double adversarial mechanism (DAN-DAM), is proposed. The DAN-DAM model is mainly composed of a feature extractor, two label classifiers and a domain discriminator. The feature extractor and the two label classifiers form the first adversarial mechanism to achieve class-level alignment. Moreover, the discrepancy between the two classifiers is measured by Wasserstein distance. Meanwhile, the feature extractor and the domain discriminator form the second adversarial mechanism to realize domain-level alignment. In addition, maximum mean discrepancy (MMD) is used to reduce the distance between the extracted features of two domains. The DAN-DAM model is verified by multiple transfer experiments on some datasets. According to the transfer experiment results, the DAN-DAM model has a good diagnosis effect for the domain shift samples. Moreover, the diagnostic accuracy is generally higher than other mainstream diagnostic methods.

Short-term wind speed forecasting has become an important technology to utilize sustainable energy, reduce the impact of wind power grid and improve the control of wind turbines. Current forecasting models based on individual algorithm and hybrid optimization algorithm could be applied to a variety of wind speed forecast. However, these algorithms ignored the limitation of optimizing parameter and the use of recent data, which may result in forecasting poor accuracy. In this paper, integrated approaches, combining singular spectrum analysis technique, cuckoo search algorithm (CSA) and harmony search algorithm (HSA), and back propagation neural network (BPNN), were introduced for conducting short-term wind speed forecasting. Firstly, the SSA technique is used for identifying and extracting instable components from raw wind speed signals. Then, the parameters of BPNN are employed to be optimized by the CSA/HSA, which improve precision of forecast results. Finally, the BPNN is utilized to deal with the wind speed series. The proposed hybrid model is conducted by the wind speed at three stations located in Penglai, China. Our experiment reveals that the proposed hybrid model can generate a more accurate, reliable and robust result and SSA technique is found to be superior technique to preprocess wind speed series. Furthermore, we compare to the forecast results with SSA and non SSA denoising procedure and found that hybrid model with SSA technique outperforms other prediction model.

In the current paper we consider the robust decentralized output regulation of heterogeneous uncertain linear systems with multiple leaders. A novel class of distributed observers is proposed. The states of the distributed observers synchronize to the states of their leaders, respectively. In contrast to the existing results, we consider a more general class of systems and furthermore we utilize the adaptive protocols to estimate the coupling weights between neighboring agents online. Therefore the observers and internal model based control laws can be designed in a purely distributed way, i.e., without knowledge of the associated matrix of the network topology. Finally we apply the proposed methods to solve the synchronization problem of a group of RLC networks and the simulation results show the effectiveness of the methods.

Deep learning has been widely used in intelligent fault diagnosis field in the era of industrial internet due to its excellent big data analysis ability. However, it lacks the specific attention enhancement mechanism in the training process, and is difficult to be applied to the speed transfer fault diagnosis under unbalanced training sample condition. Considering these challenges, a neural network called discrete-peak joint attention enhancement (DPJAE) convolutional model is proposed. First, the proposed discrete channel attention enhancement method is applied to enhance the characteristic discreteness of convolutional neural network channels. Then, the peak channel attention enhancement method follows, which is employed to enhance feature peaks in convolutional neural network channels. Finally, the discrete-peak joint attention enhancement method is placed in the middle of a well-designed robust CNN architecture to enhance the discreteness and peak value for channel characteristics. In order to avoid the over-fitting phenomenon of high variance in the training process of the deep network model, L 2 regularization method is introduced to regularize the weights for the front layer network. The diagnosis results on the open test dataset show that the DPJAE model not only gets high accuracy in the unbalanced training samples, but also achieves high performance in the rotating speed transfer testing samples. The proposed method is also verified on the private dataset. Compared with other diagnostic methods, the method has better diagnostic results.

The tourism industry has been integrated into the national strategic system in China. Thus, tourism demand forecasting has become a concern for the sustainable development of the tourism industry. Unfortunately, the sample size for tourism in China is always small and cannot satisfy the hypothesis test of an economic model or the data volume for a traditional time series model. In this study, a novel hybrid forecasting framework combining fuzzy time series (FTS) and an atom search optimization (ASO) algorithm is proposed for inbound tourism demand forecasting; this forecasting framework is particularly suitable for small sample sizes. Specifically, information optimization technology is applied in the FTS to improve the recognition ability of the system and effectively identify small sample information. The ASO algorithm is applied to search the optimal parameters of FTS that can further improve forecasting performance. All comparison experiments and tests verify the effectiveness and superiority of our proposed model, which provides excellent forecasting results for tourism demand and a basis for policymakers and managers to plan appropriately for the tourism market.

Electricity demand/load forecasting always plays a vital role in the management and operation of power systems, since it can help develop an optimal action program for power producers, end-consumers and government entities. Inaccurate prediction may cause an additional production or waste of resources due to high operational costs. This paper investigated the benefit of combining data features to produce short-term electricity demand forecast. The nature of the electricity usually presents the complex characteristic and obvious seasonal tendency. In this paper, the advantage of adaptive Fourier decomposition is firstly used to extract the fluctuation characteristics. Then, the condition of the linear and stationary sequence is satisfied and the sub-series are performed to measure and eliminate the seasonal pattern. In the process of seasonal adjustment, the average periodicity length is identified quantitatively. In addition, to realize the generalization performance on real electricity demand data, the sine cosine optimization algorithm is applied to select the penalty and kernel parameters of support vector machine. The empirical study showed that the superior property of the proposed hybrid method profits from the effect of data pretreatment and the findings prove that this hybrid modeling scheme can yield promising prediction results within acceptable computational complexity.

The paper is concerned with distributed optimal resource allocation problems on multi-agent systems that each agent has single-integrator dynamics. For the single-integrator multi-agent system, a local feasible set constraint is introduced and a distributed algorithm with projection operator is proposed. Compared with the algorithms in the existing literature on the single-integrator multi-agent systems, the proposed algorithm has simpler structure that reduces computation burden but without sacrificing the optimality. Incremental passivity theory is utilized to analyze the convergence of the algorithms. The simulation results illustrate the effectiveness of the proposed algorithms.

The photovoltaic (PV) energy, as clean and renewable energy, has become increasingly important. With energy storage system, the PV power can become schedulable and the use efficiency of PV power can be greatly improved. The tracking output is one of the running modes for energy storage to adjust the PV power generation. However, the research on the tracking output do not consider the fluctuation of PV power generation, the upper and lower limits of prediction errors, or only consider tracking the power curve. In this paper, a novel control method is proposed based on the super short-term prediction PV power and the prediction errors distribution law to obtain the charge and discharge strategy for energy storage ahead. In this control method, the objective function includes three parts, respectively the D-value between the planned output and actual output of PV power and energy storage system, the change of the state of charge (SOC) with different weight, The constraint condition considers the power demand, flexibility requirement and storage costs comprehensive. Then the prediction errors distribution law can be obtained by analyzing prediction errors of the PV power, the proper errors correction parameters can be selected according to the law to get a more accurate predication range and make the energy storage scheduling strategy more flexible. The particle swarm optimization (PSO) algorithm is used to get the optimal charge and discharge power strategy in advance. With the data collected from typical PV power station as an example, the simulation results verify the feasibility and flexibility of the proposed strategy, it also provides effective reference scheme for day-ahead control of battery energy storage systems

With the development of the times, the traditional personal credit is facing a severe test. This paper makes an exploratory study on the practical application and development of personal credit evaluation by using the MicroBlog data. According to the previous study of personal credit evaluation literature to dig out the credit-related indicators. We summed up the three major attributes of “Attributes of Demographic”, “Tweets Content”, and “User Relationship Structure”. We use support vector machine (SVM), naive Bayesian (NB), logical regression (LR) and AdaBoost classification algorithm, according to the actual problem modeling, to analysis of social network data on personal credit. Compared with other algorithms, the AUC value of AdaBoost algorithm achieves the best effect with 0.564 under the equalization setting.

Due to the convenience of the Peer to Peer (P2P) platform loan, the P2P platform is becoming more and more popular. Medical care has always been the most concerned issue. The emergence of medical P2P solves the insufficient funds problems of many people. In order to predict default customers, reduce the credit risk of credit institutions, and shorten credit approval time, this article uses historical data to establish a credit scoring model.

In recent years, with the rapid development of agricultural Internet of things, many different agricultural and sideline products can be bought easily which from different regions, but it also brings about more problems of foods safety (production and sale of fake eggs, water injection Pork, etc.). These issues affect social development and people’s health seriously. According these issues, all stages of agricultural products should be monitor and control. This paper introduces the traceability system which integrates RFID and EPC technologies, and uses ONS database to store key information. The tracing information can be queried that user login in traceability system and identify the two-dimensional code. People use the mobile scan to encrypted the QR code to get the information of agriculture and food products they need. The traceability system guarantees the safety of meat in all aspects of the supply chain. The system should be developed and promoted in society.

Subnetting has been widely used in computer networks and the Internet. The methods of subnetting are too difficult to grasp quickly for most beginners and ordinary users. With networks unreasonably parted, IP addresses will be seriously wasted. In order to save IP addresses, improve the utilization of IP addresses. In this paper, starting from the optimal network partitioning, in addition to the introduction of the average subnetting and subnetting based on Huffman coding, an improved subnetting method based on Huffman coding is also proposed. And an algorithm for the improved subnetting based on Huffman coding is implemented. The improved subnetting based on Huffman coding transforms the process of subnetting into Huffman tree structure and achieves the optimal partition of the network. Through the comparison of the IP address utilization of the three network partition methods, it can be concluded that the improved subnetting based on Huffman coding can fully improve the utilization of IP addresses and make most of the networks to be optimally partition. Improved subnetting based on Huffman coding is not only suitable for IPV4 but also for IPV6.

Reliable forecast of electricity can encourage accessible and responsible information for scholars, policymakers, end-consumers and managers of the electricity market. Numerous electricity forecasting methods have been achieved commendably, the performance of which varies depending on numerical characteristics and operational conditions. In this study, the composite forecasting concept is introduced and implemented to show the potential of forecasting performance. This modeling concept is a remarkable ability to identify and measure any seasonal relationship that exists in electricity demand data. Moreover, it is available as a toolbox in many of the programming operation research. In the module of nonlinear time series decomposition, the noise disturbance is initially considered before extracting the seasonal variation to support the condition that the linear and stationary time series should be used for the seasonality identifying method. Also, we further provide a new insight of prediction intervals estimation to better reflect the uncertainties of the underlying challenging power system plan and operation. The results show that the proposed model can generate promising forecasts compared to the other combination schemata and it can be useful for both policy-makers and public agencies to guarantee the security and regulation of the power system.

Effective forecasting of the air pollutant concentration is crucial for a robust air quality early-warning system and has both theoretical and practical significance. However, the accidental and cognitive uncertainty in the model selection or parameter setting of a single system will result in inaccurate and unstable forecasting results. Thus, in this paper, a novel fuzzy combination forecasting system based on the data preprocessing, fuzzy theory, and advanced optimization algorithm is proposed to improve the accuracy and stability of forecasting results. Based on the fuzzy theory and decorrelation maximization method, our proposed forecasting system can considering more information and maintaining the diversity of models. Moreover, Cuckoo Search algorithm applied in the system can determine the optimal weights for models aggregation. Several experiments based on PM 2.5 and PM10 datasets in three cities are analyzed and discussed to verify the excellent performance of our proposed forecasting system, and the results indicate that the forecasting system outperforms others with respect to the accuracy, stability and generalization capabilities which are the basis of a robust air quality early-warning system in practice.

Depth image based rendering (DIBR) is an important technology for virtual view synthesis in 3DTV. This paper presents a bi-directional depth image based rendering system without preprocessing depth image. An algorithm for three-dimension (3D) warping which declines exposed area is also proposed, and so is an improved merging algorithm for eliminating image ghosting. The proposed DIBR scheme can reduce computation cost compared to previous techniques. Experimental results show that edge ghosting can be completely eliminated in our method. We also demonstrate that both objective and subjective effects of the paper are better than the previous ones.

Adding element tridiagonal periodic matrices have an important effect for the algorithms of solving linear systems, computing the inverses, the triangular factorization, the boundary value problems by finite difference methods, interpolation by cubic splines, three-term difference equations and so on. In this paper, we give a fast algorithm for the Inverse Matrices of periodic adding element tridiagonal matrices.