Search

Tourism industry played an increasingly prominent role in the socio-economic development in China. Therefore, it is of great significance to forecast the tourism demand, to analyze the development ...

Smart Cities and Artificial Intelligence offers an intensive evaluation of how the smart city establishments are made at different scales through automated thinking headways, for instance, geospatial information, data examination, data portrayal, clever related things, and quick natural frameworks handiness. Progressing propels in electronic thinking attract us closer to making a persistent reproduced model of human-made and trademark structures, from urban regions to transportation establishments to utility frameworks. This continuous living model empowers us to all the bound to manage and improve these working structures, making them dynamically watchful. Keen Cities and Artificial Intelligence gives a multidisciplinary, joined procedure, using speculative and applied bits of information, for the evaluation of savvy city situations. This special issue shows how the mechanized and physical universes are associated inside this organic framework, and how nonstop data arrangement is changing the possibility of our urban as well as industrial condition. It gives a fresh sweeping perspective on the natural framework designing, advances, and parts that include the masterminding and execution of sharp city and industry establishments. This special issue also shows how the computerized and physical universes are connected inside this biological system, and how continuous information assortment is changing the idea of our urban and industry condition. It gives a crisp all-encompassing viewpoint on the biological system engineering, advances, and parts that involve the arranging and execution of keen city and industry foundations. After following double blind peer review for all the submitted manuscripts across the globe, and after the rigorous review process, revision and based on final recommendations of the reviewers and editorial team, finally 17 manuscripts have been accepted for publication.

The bat algorithm (BA) has fast convergence, a simple structure, and strong search ability. However, the standard BA has poor local search ability in the late evolution stage because it references the historical speed; its population diversity also declines rapidly. Moreover, since it lacks a mutation mechanism, it easily falls into local optima. To improve its performance, this paper develops a hybrid approach to improving its evolution mechanism, local search mechanism, mutation mechanism, and other mechanisms. First, the quantum computing mechanism (QCM) is used to update the searching position in the BA to improve its global convergence. Secondly, the X-condition cloud generator is used to help individuals with better fitness values to increase the rate of convergence, with the sorting of individuals after a particular number of iterations; the individuals with poor fitness values are used to implement a 3D cat mapping chaotic disturbance mechanism to increase population diversity and thereby enable the BA to jump out of a local optimum. Thus, a hybrid optimization algorithm—the chaotic cloud quantum bats algorithm (CCQBA)—is proposed. To test the performance of the proposed CCQBA, it is compared with alternative algorithms. The evaluation functions are nine classical comparative functions. The results of the comparison demonstrate that the convergent accuracy and convergent speed of the proposed CCQBA are significantly better than those of the other algorithms. Thus, the proposed CCQBA represents a better method than others for solving complex problems.

Since load forecasting plays a decisive role in the safe and stable operation of power systems, it is particularly important to explore forecasting methods accurately. In this article, the hybrid empirical mode decomposition (EMD) and support vector regression (SVR) with back‐propagation neural network (BPNN), namely the EMDHR‐SVR‐BPNN model, is proposed. Information theory is mainly used to solve the data tendency problem, and the EMD method is used to solve the data volatility problem. There is no interaction between these two methods; thus these two models can complement each other through generalized regression of orthogonal decomposition. Taking the load data from the New South Wales (NSW, Australia) market as an example, the obtained simulation results are compared with other models. It is concluded that the proposed EMDHR‐SVR‐BPNN model not only improves the forecasting accuracy but also has good fitting ability. It can reflect the changing tendency of data in a timely manner, providing a strong basis for the electricity generation of the power sector in the future, thus reducing electricity waste. The proposed EMDHR‐SVR‐BPNN model has potential for employment in mid‐short term load forecasting.

In recent years, the emergence of blockchain technology (BT) has become a unique, most disruptive, and trending technology. The decentralized database in BT emphasizes data security and privacy. Also, the consensus mechanism in it makes sure that data is secured and legitimate. Still, it raises new security issues such as majority attack and double-spending. To handle the aforementioned issues, data analytics is required on blockchain based secure data. Analytics on these data raises the importance of arisen technology Machine Learning (ML). ML involves the rational amount of data to make precise decisions. Data reliability and its sharing are very crucial in ML to improve the accuracy of results. The combination of these two technologies (ML and BT) can provide highly precise results. In this paper, we present a detailed study on ML adoption for making BT-based smart applications more resilient against attacks. There are various traditional ML techniques, for instance, Support Vector Machines (SVM), clustering, bagging, and Deep Learning (DL) algorithms such as Convolutional Neural Network (CNN) and Long short-term memory (LSTM) can be used to analyse the attacks on a blockchain-based network. Further, we include how both the technologies can be applied in several smart applications such as Unmanned Aerial Vehicle (UAV), Smart Grid (SG), healthcare, and smart cities. Then, future research issues and challenges are explored. At last, a case study is presented with a conclusion.

Accurate electric load forecasting is critical not only in preventing wasting electricity production but also in facilitating the reasonable integration of clean energy resources. Hybridizing the variational mode decomposition (VMD) method, the chaotic mapping mechanism, and improved meta-heuristic algorithm with the support vector regression (SVR) model is crucial to preventing the premature problem and providing satisfactory forecasting accuracy. To solve the boundary handling problem of the cuckoo search (CS) algorithm in the cuckoo birds' searching processes, this investigation proposes a simple method, called the out-bound-back mechanism, to help those out-bounded cuckoo birds return to their previous (the most recent iteration) optimal location. The proposed self-recurrent (SR) mechanism, inspired from the combination of Jordan's and Elman's recurrent neural networks, is used to collect comprehensive and useful information from the training and testing data. Therefore, the self-recurrent mechanism is hybridized with the SVR-based model. Ultimately, this investigation presents the VMD-SR-SVRCBCS model, by hybridizing the VMD method, the SVR model with the self-recurrent mechanism, the Tent chaotic mapping function, the out-bound-back mechanism, and the cuckoo search algorithm. Two real-world datasets are used to demonstrate that the proposed model has greater forecasting accuracy than other models.

Because of the rise in the number of cyberattacks, the devices that make up the Internet of Things (IoT) environment are experiencing increased levels of security risks. In recent years, a significant number of centralized systems have been developed to identify intrusions into the IoT environment. However, due to diverse requirements of IoT devices such as dispersion, scalability, resource restrictions, and decreased latency, these strategies were unable to achieve notable outcomes. The present paper introduces two novel metaheuristic optimization algorithms for optimizing the weights of deep learning (DL) models, use of DL may help in the detection and prevention of cyberattacks of this nature. Furthermore, two hybrid DL classifiers, i.e., convolutional neural network (CNN) + deep belief network (DBN) and bidirectional long short-term memory (Bi-LSTM) + gated recurrent network (GRU), were designed and tuned using the already proposed optimization algorithms, which results in ads to improved model accuracy. The results are evaluated against the recent approaches in the relevant field along with the hybrid DL classifier. Model performance metrics such as accuracy, rand index, f-measure, and MCC are used to draw conclusions about the model’s validity by employing two distinct datasets. Regarding all performance metrics, the proposed approach outperforms both conventional and cutting-edge methods.

Content-Centric Networking (CCN) has emerged as a potential Internet architecture that supports name-based content retrieval mechanism in contrast to the current host location-oriented IP architecture. The in-network caching capability of CCN ensures higher content availability, lesser network delay, and leads to server load reduction. It was observed that caching the contents on each intermediate node does not use the network resources efficiently. Hence, efficient content caching decisions are crucial to improve the Quality-of-Service (QoS) for the end-user devices and improved network performance. Towards this, a novel content caching scheme is proposed in this paper. The proposed scheme first clusters the network nodes based on the hop count and bandwidth parameters to reduce content redundancy and caching operations. Then, the scheme takes content placement decisions using the cluster information, content popularity, and the hop count parameters, where the caching probability improves as the content traversed toward the requester. Hence, using the proposed heuristics, the popular contents are placed near the edges of the network to achieve a high cache hit ratio. Once the cache becomes full, the scheme implements Least-Frequently-Used (LFU) replacement scheme to substitute the least accessed content in the network routers. Extensive simulations are conducted and the performance of the proposed scheme is investigated under different network parameters that demonstrate the superiority of the proposed strategy w.r.t the peer competing strategies.

Accurate electric load forecasting can provide critical support to makers of energy policy and managers of power systems. The support vector regression (SVR) model can be hybridized with novel meta-heuristic algorithms not only to identify fluctuations and the nonlinear tendencies of electric loads, but also to generate satisfactory forecasts. However, many such algorithms have numerous drawbacks, such as a low population diversity and trapping at local optima, which are problems of premature convergence. Accordingly, approaches to increase the accuracy of forecasting must be developed. In this investigation, quantum computing mechanism is used to quantamize dragonfly behaviors to enhance the searching effectiveness of the dragonfly algorithm, namely QDA. In addition, conducting the data preprocessing by the complete ensemble empirical mode decomposition adaptive noise (CEEMDAN) is useful to improve the forecasting accuracy. Thus, a new electric load forecasting model, the CEEMDAN-SVRQDA model, that combines the CEEMDAN and hybridizes the QDA with an SVR model, is proposed to provide more accurate forecasts. Two numerical examples from the Tokyo Electric Power Company (Japan) and the National Grid (UK) demonstrate that the proposed model outperforms other models.

A series of direct smelting reduction experiment has been implemented with different iron ore bases by thermogravimetric analyzers. The derivative thermogravimetric data have been obtained from these experiments. The data are then decomposed by the technology of empirical mode decomposition to receive its embedded characteristics of the power spectrum. Secondly, based on the obtained power spectrum, the energy transferring behavior for reduction process of iron oxide is analyzed and is compared with other methods (i.e., analytical reagent). Finally, the desired spectral characteristics of the power spectrum for the reduction process of Huimin iron ore can be determined. The result would play a significant role in strengthening the smelting process of Huimin iron ore.

This paper presents a model for forecasting the motion of a floating platform with satisfactory forecasting accuracy. First, owing to the complex nonlinear characteristics of a time series of floating platform motion data, a support vector regression model with a hybrid kernel function is used to simulate the motion of a floating platform. Second, the proposed chaotic efficient bat algorithm, based on the chaotic, niche search, and evolution mechanisms, is used to optimize the parameters of the hybrid kernel-based support vector regression model. Third, the ensemble empirical mode decomposition algorithm is utilized to decompose the original floating platform motion time series into a series of intrinsic mode functions and residuals. The ultimate forecasting results are obtained by summing the outputs of these functions. Subsequently, motion data for a real floating platform are used to evaluate the reliability and effectiveness of the proposed model.

A ship motion time series (SMTS) exhibits obvious periodicity under the effects of periodic wave and strong nonlinearity owing to wind, ocean currents, and the load of ship itself, which make accurate forecasting difficult. To improve forecasting accuracy, this investigation divides the SMTS into a periodic term and a nonlinear term and forecasts each term separately. First, the periodogram estimation method (PEM) is implemented to forecast the periodic term. Then, owing to the strong nonlinearity of SMTS, the LSSVR model is used to forecast the nonlinear residual term that is generated by the PEM. On account of parameters that determine the predictive accuracy of the LSSVR model, the chaotic cloud particle swarm optimization (CCPSO) algorithm is introduced to optimize the parameters of the LSSVR model. Finally, combining the PEM, LSSVR model, and CCPSO algorithm, a hybrid forecasting method for SMTS, PEM&LSSVR-CCPSO, is developed. Subsequently, SMTS data for two ships that are sailing on the ocean are used as a numerical example, and thus, the forecasting performance of the presented method is evaluated. The results of the analysis demonstrate that the proposed hybrid SMTS forecasting scheme has better forecasting performance than classical forecasting models that are considered herein.

Along with the deregulation of electric power market as well as aggregation of renewable resources, short term load forecasting (STLF) has become more and more momentous. However, it is a hard task due to various influential factors that leads to volatility and instability of the series. Therefore, this paper proposes a hybrid model which combines empirical mode decomposition (EMD), minimal redundancy maximal relevance (mRMR), general regression neural network (GRNN) with fruit fly optimization algorithm (FOA), namely EMD-mRMR-FOA-GRNN. The original load series is firstly decomposed into a quantity of intrinsic mode functions (IMFs) and a residue with different frequency so as to weaken the volatility of the series influenced by complicated factors. Then, mRMR is employed to obtain the best feature set through the correlation analysis between each IMF and the features including day types, temperature, meteorology conditions and so on. Finally, FOA is utilized to optimize the smoothing factor in GRNN. The ultimate forecasted load can be derived from the summation of the predicted results for all IMFs. To validate the proposed technique, load data in Langfang, China are provided. The results demonstrate that EMD-mRMR-FOA-GRNN is a promising approach in terms of STLF.

With the growth in food products’ usage, ensuring their quality and safety has become progressively difficult. Specifically, food traceability turns out to be a very critical task for retailers, sellers, consumers, surveillance authorities, and other stakeholders in the food supply chain system. There are requirements for food authenticity verification (correct declaration of cultivation, origin, and variety), quality checks (e.g., justification for higher prices), and preventing food products from fraudsters in the food industry. The ubiquitous and promising technology of blockchain ensures the traceability of food trade networks with high potential and handles the aforementioned issues. Blockchain makes the food industry more transparent at all levels by storing data immutably and enabling quick tracking across the stages of the food supply chain. Hence, commodities, stakeholders, and semi-finished food items can be recognized significantly faster. Motivated by these facts, in this paper, we present an in-depth survey of state-of-the-art approaches to the food industry’s security, food traceability, and food supply chain management. Further, we propose a blockchain-based secure and decentralized food industry architecture to alleviate security and privacy aspects and present a comprehensive solution taxonomy for a blockchain-based food industry. Then, a comparative analysis of existing approaches with respect to various parameters, i.e., scalability, latency, and food quality, is presented, which facilitates the end-user in selecting approaches based on the merits over other approaches. Finally, we provide insights into the open issues and research challenges with concluding remarks.

The research on the sustainability evaluation of innovation and entrepreneurship education for clean energy majors in colleges and universities can not only cultivate more and better innovative and entrepreneurial talents for the development of sustainable energy but also provide a reference for the sustainable development of innovation and entrepreneurship education for other majors. To achieve systematic and comprehensive scientific evaluation, this paper proposes an evaluation model based on SPA-VFS and Chaos bat algorithm to optimize GRNN. Firstly, the sustainability evaluation index system of innovation and entrepreneurship education for clean energy major in colleges and universities is constructed from the four aspects of the environment, investment, process, and results, and the meaning of each evaluation index is explained, Then, combined with variable fuzzy set evaluation theory (VFS) and set pair analysis theory (SPA), the classical evaluation model based on SPA-VFS is constructed, and the entropy weight method and rank method are coupled to obtain the index weight. The basic bat algorithm is improved by using Tent chaotic mapping, and the chaotic bat algorithm (CBA) is proposed. The generalized regression neural network (GRNN) model is optimized by CBA, and the intelligent evaluation model based on CBA-GRNN is obtained to realize fast real-time calculation, finally, a numerical example is used to verify the scientificity and accuracy of the model proposed in this paper. This study is conducive to a comprehensive evaluation of the sustainability of innovation and entrepreneurship education for clean energy major in colleges and universities, and is conducive to the healthy and sustainable development of innovation and entrepreneurship education for clean energy major in colleges and universities, so as to provide more innovative and entrepreneurial talents for the clean energy industry.

The escalated growth of the Internet of Things (IoT) has started to reform and reshape our lives. The deployment of a large number of objects adhered to the internet has unlocked the vision of the smart world around us, thereby paving a road towards automation and humongous data generation and collection. This automation and continuous explosion of personal and professional information to the digital world provides a potent ground to the adversaries to perform numerous cyber-attacks, thus making security in IoT a sizeable concern. Hence, timely detection and prevention of such threats are pre-requisites to prevent serious consequences. The survey conducted provides a brief insight into the technology with prime attention towards the various attacks and anomalies and their detection based on the intelligent intrusion detection system (IDS). The comprehensive look-over presented in this paper provides an in-depth analysis and assessment of diverse machine learning and deep learning-based network intrusion detection system (NIDS). Additionally, a case study of healthcare in IoT is presented. The study depicts the architecture, security, and privacy issues and application of learning paradigms in this sector. The research assessment is finally concluded by listing the results derived from the literature. Additionally, the paper discusses numerous research challenges to allow further rectifications in the approaches to deal with unusual complications.

To detect substation faults for timely repair, this paper proposes a fault detection method that is based on the time series model and the statistical process control method to analyze the regulation and characteristics of the behavior in the switching process. As the first time, this paper proposes a fault detection model using SARIMA, statistical process control (SPC) methods, and 3σ criterion to analyze the characteristics in substation’s switching process. The employed approaches are both very common tools in the statistics field, however, via effectively combining them with industrial process fault diagnosis, these common statistical tolls play excellent role to achieve rich technical contributions. Finally, for different fault samples, the proposed method improves the rate of detection by at least 9% (and up to 15%) than other methods.

The lifetime of a node in wireless sensor networks (WSN) is directly responsible for the longevity of the wireless network. The routing of packets is the most energy-consuming activity for a sensor node. Thus, finding an energy-efficient routing strategy for transmission of packets becomes of utmost importance. The opportunistic routing (OR) protocol is one of the new routing protocol that promises reliability and energy efficiency during transmission of packets in wireless sensor networks (WSN). In this paper, we propose an intelligent opportunistic routing protocol (IOP) using a machine learning technique, to select a relay node from the list of potential forwarder nodes to achieve energy efficiency and reliability in the network. The proposed approach might have applications including e-healthcare services. As the proposed method might achieve reliability in the network because it can connect several healthcare network devices in a better way and good healthcare services might be offered. In addition to this, the proposed method saves energy, therefore, it helps the remote patient to connect with healthcare services for a longer duration with the integration of IoT services.

Smart cities follow different strategies to face public health challenges associated with socio-economic objectives. Buildings play a crucial role in smart cities and are closely related to people’s health. Moreover, they are equally essential to meet sustainable objectives. People spend most of their time indoors. Therefore, indoor air quality has a critical impact on health and well-being. With the increasing population of elders, ambient-assisted living systems are required to promote occupational health and well-being. Furthermore, living environments must incorporate monitoring systems to detect unfavorable indoor quality scenarios in useful time. This paper reviews the current state of the art on indoor air quality monitoring systems based on Internet of Things and wireless sensor networks in the last five years (2014–2019). This document focuses on the architecture, microcontrollers, connectivity, and sensors used by these systems. The main contribution is to synthesize the existing body of knowledge and identify common threads and gaps that open up new significant and challenging future research directions. The results show that 57% of the indoor air quality monitoring systems are based on Arduino, 53% of the systems use Internet of Things, and WSN architectures represent 33%. The CO2 and PM monitoring sensors are the most monitored parameters in the analyzed literature, corresponding to 67% and 29%, respectively.

As mentioned in Chap. 1, the electric load forecasting methods can be classified in three categories [1–12]

As mentioned in Chap. 2 that the traditional determination of these three parameters in an SVR model does not guarantee improved forecasting accuracy level, because of its unable to set up more suitable initial values of parameters σ, C, and e in the initial step, and unable to simultaneously consider the interaction effects among three parameters to efficiently find out the near optimal solution for large scale data set. Therefore, it is feasible to apply meta-heuristic algorithms to implement intelligent searching around the solution range to determine most appropriate parameter combination by minimizing the objective function describing the structural risk of an SVR model. This chapter will introduce more recent representative meta-heuristic algorithms (including gravitational search algorithm, GSA; cuckoo search algorithm, CSA; bat algorithm, BA; and fruit fly optimization algorithm, FOA) hybridized with the SVR forecasting model to look for the most suitable parameter combination to increase forecasting accurate level.

As indicated in Chap. 4 that hybridizing different meta-heuristic algorithms [including gravitational search algorithm (GSA), cuckoo search algorithm (CSA), bat algorithm (BA), and fruit fly optimization algorithm (FOA)] with an SVR-based electric load forecasting model can receive superior forecasting performance than other competitive forecasting models (including ARIMA, HW, GRNN, and BPNN models).

As mentioned in Chap. 1 that the methods of data pre-processing can effectively decompose the time series with non-stationary characteristics into several intrinsic mode functions, such as the decomposition methods (Huang et al. in Proc R Soc A Math Phys Eng Sci 454(1971):903–995, 1998 [1]). Huang et al. (Proc R Soc A Math Phys Eng Sci 454:903–995, 1998 [1]) proposed the empirical mode decomposition (EMD) to decompose the complex time series into several intrinsic mode functions (IMFs), which is dedicated to provide extracted components to demonstrate high accurate clustering performances, and it has also received lots of attention in relevant applications fields, such as communication, economics, engineering, and so on (Huang and Kunoth in J Comput Appl Math 240:174–183, 2013 [2, Fan et al. in Math Probl Eng 720849, 2012 3, Premanode and Toumazou in Expert Syst Appl 40:377–384, 2013 4]).

As shown in Chaps. 4 and 5 that different hybrid QCM, CMM, CGM, RLM, and SM with meta-heuristic algorithms are applied to select appropriate parameter combination of an SVR-based electric load forecasting model. These forecasting results indicate that all SVR-based hybrid models are superior to other competitive forecasting models. This chapter will introduce a novel approach, hybrid phase space reconstruction (PSR) algorithm and recurrence plot (RP) theory with bi-square kernel (BSK) function, namely PSR-BSK model, to improve the forecasting accuracy. as know that a specific state of the system can be represented by a point in the phase space and time evolution of the system creates a trajectory in the phase space. Where the phase space is a space in which all possible states of the system are represented, with each possible state corresponding to one unique point. Then, the given time series could be a projection of trajectory of the system to one coordinate of phase space. Therefore, based on the theory of time delay and embedding dimension, the phase space reconstruction (PSR) algorithm is employed to reconstruct the phase space of chaotic time series, to extract some valuable features by extending a one-dimensional time series to a high dimensional phase space. On the other hand, recurrence plot (RP) theory is a relatively new technique for the qualitative assessment of time series in a dynamical system. The fundamental assumption of RP is that there exists a realized dynamical process in an observable time series (a sequence of observations) to represent the interaction among the relevant variables over time. It has been proven mathematically that one can recreate a topologically equivalent picture of the original multidimensional system behavior by using the time series of a single observable variable. Therefore, RP reveals all of the times when the phase space trajectory of the dynamical system visits roughly the same area in the phase space, it is can graphically detect hidden patterns and structural changes in data or see similarities in patterns across the time series under study.

The motion of a ship, which has six degrees of freedom, is a complex nonlinear dynamic process with variable periodicity and chaotic characteristics. With the development of smart ships, modern high-precision equipment needs the help from high accuracy of ship motion (SHM) forecasting. Existing models will not easily be able to satisfy future accuracy requirements. Therefore, to improve the accuracy of SHM forecasts, by firstly determining the sequence features of SHM time series, a convolutional neural network (CNN) was used herein to extract automatically spatial feature vectors. Considering the variable-period characteristics of SHM time series, a gated recurrent unit (GRU) was used to learn the inherent time characteristics and to extract temporal feature vectors. The attention mechanism (AM) was developed to control the effect of feature vectors on the output to solve the problem of the contribution of feature vectors. Integrating the above methods, an SHM hybrid forecasting model, the SHM CNN-GRU-AM (SHM-CG it is referred to as GCWOA-SHM-C&G&A. Finally, ship heave and pitch time series data are used to analyze an example to test the forecasting effectiveness of SHM-C&G&A and the optimization performance of GCWOA. The experimental results reveal that the proposed SHM-C&G&A model is more robust that the other models that are considered in this paper, and exhibits better nonlinear characteristics. The proposed GCWOA yields a better combination of hyperparameters than contrast algorithms in the forecasting process.

Short term load forecasting (STLF) is an important issue for an electricity power system, to enhance its management efficiency and reduce its operational costs. However, STLF is affected by lots of exogenous factors, it demonstrates complicate characteristics, particularly, the multi-dimensional nonlinearity. Therefore, it is desired to extract some valuable features embedded in the time series, to demonstrate the relationships of the nonlinearity, eventually, to improve the forecasting accuracy. Due to the superiorities of phase space reconstruction (PSR) algorithm in reconstructing the phase space of time series, and of bi-square kernel (BSK) regression model in simultaneously considering original spectral signature and spatial information, this paper proposes a novel electricity load forecasting model by hybridizing PSR algorithm with BSK regression model, namely PSR-BSK model. The electricity load data can be sufficiently reconstructed by PSR algorithm to extract the evolutionary trends of the electricity power system and the embedded valuable features information to improve the reliability of the forecasting performances. The BSK model reasonably illustrates the spatial structures among regression points and their neighbor points to receive the rules of rotation rules and disturbance in each dimension. Eventually, the proposed PSR-BSK model including multi-dimensional regression is successfully established. The short term load data from the New South Wales (NSW, Australia) market and the New York Independent System Operator (NYISO, USA) are employed to illustrate the forecasting performances with different alternative forecasting models. The results demonstrate that, in these two employed numerical examples, the proposed PSR-BSK models all significantly receive the smallest forecasting errors in terms of MAPE (less than 2.20%), RMSE (less than 30.0), and MAE (less than 2.30), and the shortest running time (less than 400 s) than other forecasting models.

This paper develops a novel short-term load forecasting model that hybridizes several machine learning methods, such as support vector regression (SVR), grey catastrophe (GC (1,1)), and random forest (RF) modeling. The modeling process is based on the minimization of both SVR and risk. GC is used to process and extract catastrophe points in the long term to reduce randomness. RF is used to optimize forecasting performance by exploiting its superior optimization capability. The proposed SVR-GC-RF model has higher forecasting accuracy (MAPE values are 6.35% and 6.21%, respectively) using electric loads from Australian-Energy-Market-Operator; it can provide analytical support to forecast electricity consumption accurately.

In this study, the degree of grayness of images of various types of cloud, collected from the Kunming Province (China) area, was statistically analyzed as part of a new weather recognition method to recognize weather patterns more accurately. The results reveal that the differences of the results of gray degree-based factor analysis vary remarkably with weather conditions. The image factor is the main factor in recognition, and the statistical factor is the reference factor. The recognition accurate level can be improved by up to 95.3% using the proposed approach. The proposed gray degree-based method outperforms wild line spread function and outdoor images support vector machine methods. The gray-scale method is easier to implement, timely, reliable, and accurate.