Harmony Search Research Articles

Novel Global Harmony Search Algorithm for General Linear Complementarity Problem

Linear complementarity problem (LCP) is studied. After reforming general LCP as the system of nonlinear equations by NCP-function, LCP is equivalent to solving an unconstrained optimization model, which can be solved by a recently proposed algorithm named novel global harmony search (NGHS). NGHS algorithm can overcome the disadvantage of interior-point methods. Numerical results show that the NGHS algorithm has a higher rate of convergence than the other HS variants. For LCP with a unique solution, NGHS converges to its unique solution. For LCP with multiple solutions, NGHS can find as many solutions as possible. Meanwhile, for unsolvable LCP, all algorithms are terminated on the solution with the minimum error.

MTHSA-DHEI: multitasking harmony search algorithm for detecting high-order SNP epistatic interactions

Genome-wide association studies have succeeded in identifying genetic variants associated with complex diseases, but the findings have not been well interpreted biologically. Although it is widely accepted that epistatic interactions of high-order single nucleotide polymorphisms (SNPs) [(1) Single nucleotide polymorphisms (SNP) are mainly deoxyribonucleic acid (DNA) sequence polymorphisms caused by variants at a single nucleotide at the genome level. They are the most common type of heritable variation in humans.] are important causes of complex diseases, the combinatorial explosion of millions of SNPs and multiple tests impose a large computational burden. Moreover, it is extremely challenging to correctly distinguish high-order SNP epistatic interactions from other high-order SNP combinations due to small sample sizes. In this study, a multitasking harmony search algorithm (MTHSA-DHEI) is proposed for detecting high-order epistatic interactions [(2) In classical genetics, if genes X1 and X2 are mutated and each mutation by itself produces a unique disease status (phenotype) but the mutations together cause the same disease status as the gene X1 mutation, gene X1 is epistatic and gene X2 is hypostatic, and gene X1 has an epistatic effect (main effect) on disease status. In this work, a high-order epistatic interaction occurs when two or more SNP loci have a joint influence on disease status.], with the goal of simultaneously detecting multiple types of high-order (k1-order, k2-order, …, kn-order) SNP epistatic interactions. Unified coding is adopted for multiple tasks, and four complementary association evaluation functions are employed to improve the capability of discriminating the high-order SNP epistatic interactions. We compare the proposed MTHSA-DHEI method with four excellent methods for detecting high-order SNP interactions for 8 high-orderepistatic interaction models with no marginal effect (EINMEs) and 12 epistatic interaction models with marginal effects (EIMEs) (*) and implement the MTHSA-DHEI algorithm with a real dataset: age-related macular degeneration (AMD). The experimental results indicate that MTHSA-DHEI has power and an F1-score exceeding 90% for all EIMEs and five EINMEs and reduces the computational time by more than 90%. It can efficiently perform multiple high-order detection tasks for high-order epistatic interactions and improve the discrimination ability for diverse epistasis models.

A new intelligent approach for size optimization of a renewable energy based grid connected hybrid energy system

AbstractAdopting hybrid power systems to provide access to clean, reliable, and inexpensive energy is necessary for countries like India to accomplish their goals of sustainable development. This work proposes an optimization approach for sizing a grid‐connected hybrid renewable energy system (HRES) that includes photovoltaic, biomass, biogas, and a battery. In this research, a recently developed Aquila optimization algorithm is utilized to evaluate the optimal size of HRES for a cluster of villages near Sarai Jairam, Agra district, Uttar Pradesh, India using the MATLAB software package. The goal of this optimization approach is to reduce the net present cost for HRES while satisfying the operational constraints, including the reliability of the power supply and maximum utilization of the photovoltaic, biomass, and biogas complementary properties. Initially, three HRES configurations in the off‐grid mode were optimized using the suggested Aquila optimization technique. To confirm the findings, the optimization results for the same models of off‐grid HRES were obtained using the harmony search (HS) and particle swarm optimization (PSO) algorithms. The same algorithms were also used to optimize the grid‐connected SPV/biomass/biogas with the battery model of HRES. Finally, the outcomes from the off‐grid models presented above were compared to the grid‐linked model. The grid‐connected configuration which is obtained by the Aquila optimization approach provides an optimal solution with the least net present cos t (NPC) and minimum cost of energy (COE) when compared with HS and PSO. The optimal grid‐connected HRES includes 235 kW of PV, a 10 kW biogas generator, a 64 kW biomass generator, and a 50.40 kWh battery bank. The overall net present cost and the COE are found to be $547 670 and $0.0768/kWh, respectively.

Adaptive binary multi-objective harmony search algorithm for channel selection and cross-subject generalization in motor imagery-based BCI

Objective. Multi-channel electroencephalogram data containing redundant information and noise may result in low classification accuracy and high computational complexity, which limits the practicality of motor imagery (MI)-based brain-computer interface (BCI) systems. Therefore, channel selection can improve BCI performance and contribute to user convenience. Additionally, cross-subject generalization is a key topic in the channel selection of MI-based BCI. Approach. In this study, an adaptive binary multi-objective harmony search (ABMOHS) algorithm is proposed to select the optimal set of channels. Furthermore, a new adaptive cross-subject generalization model (ACGM) is proposed. Three public MI datasets were used to validate the effectiveness of the proposed method. Main results. The Wilcoxon signed-rank test was performed on the test accuracies, and the results indicated that the ABMOHS method significantly outperformed all channels (p< 0.001), the C3–Cz–C4 channels (p< 0.001), and 20 channels (p< 0.001) in the sensorimotor cortex. The ABMOHS algorithm based on Fisher’s linear discriminant analysis (FLDA) and support vector machine (SVM) classifiers greatly reduces the number of selected channels, especially for larger channel sizes (Dataset 2), and obtains a comparative classification performance. Although there was no significant difference in test classification performance between ABMOHS and non-dominated sorting genetic algorithm II (NSGA-II) when FLDA and SVM were used, ABMOHS required less computational time than NSGA-II. Furthermore, the number of channels obtained by ABMOHS algorithm were significantly smaller than those obtained by common spatial pattern-Rank and correlation-based channel selection algorithm. Additionally, the generalization of ACGM to untrained subjects shows that the mean test classification accuracy of ACGM created by a small sample of trained subjects is significantly better than that of Special-16 and Special-32. Significance. The proposed method can reduce the calibration time in the training phase and improve the practicability of MI-BCI.

A Hybrid Approach for Task Scheduling in the Cloud Environment

In today’s world, Cloud Computing has been considered as the best concept for the virtualization of various resources. There are various approaches that have been available for improvising the load balancing and also to improvise the job scheduling in the concept of cloud. Cloud Computing has offers the on-demand allocation of resources to users and this feature of cloud makes it a best among various technologies. Cloud computing provides great performance in less maintenance cost. So, Task scheduling has become a very important factor in enhancing the performance of resources dynamically and at low cost, which is the most crucial part of cloud computing. In other words, we can say that allocation of resources and task scheduling are the two major factors that are considered for the better performance and they must be organized precisely. The author has focused on enhancing the task scheduling process by creating a hybrid optimization algorithm and named as Cuckoo Harmony Search Algorithm (CHSA) to remove the task scheduling problem.

Short-term wind power prediction with harmony search algorithm: Belen region

Wind power is the fastest-growing technology among alternative energy production sources. Reliable forecasting of short-term wind power plays a critical role in the acquisition of most of the generated energy. In this study, short-term wind power forecast is performed using radial-based artificial neural networks, forecast error and cost to be minimized with the harmony search algorithm. Experimented results show that, we can predict wind power with fewer features and less error by using harmony search algorithm. A %7 percent improvement in RMSE rate has been achieved with the proposed method for short-term wind power prediction.

Optimal Dimensioning of Retaining Walls Using Explainable Ensemble Learning Algorithms.

This paper develops predictive models for optimal dimensions that minimize the construction cost associated with reinforced concrete retaining walls. Random Forest, Extreme Gradient Boosting (XGBoost), Categorical Gradient Boosting (CatBoost), and Light Gradient Boosting Machine (LightGBM) algorithms were applied to obtain the predictive models. Predictive models were trained using a comprehensive dataset, which was generated using the Harmony Search (HS) algorithm. Each data sample in this database consists of a unique combination of the soil density, friction angle, ultimate bearing pressure, surcharge, the unit cost of concrete, and six different dimensions that describe an optimal retaining wall geometry. The influence of these design features on the optimal dimensioning and their interdependence are explained and visualized using the SHapley Additive exPlanations (SHAP) algorithm. The prediction accuracy of the used ensemble learning methods is evaluated with different metrics of accuracy such as the coefficient of determination, root mean square error, and mean absolute error. Comparing predicted and actual optimal dimensions on a test set showed that an score of 0.99 could be achieved. In terms of computational speed, the LightGBM algorithm was found to be the fastest, with an average execution speed of 6.17 s for the training and testing of the model. On the other hand, the highest accuracy could be achieved by the CatBoost algorithm. The availability of open-source machine learning algorithms and high-quality datasets makes it possible for designers to supplement traditional design procedures with newly developed machine learning techniques. The novel methodology proposed in this paper aims at producing larger datasets, thereby increasing the applicability and accuracy of machine learning algorithms in relation to optimal dimensioning of structures.

Smart Hydropower Water Distribution Networks, Use of Artificial Intelligence Methods and Metaheuristic Algorithms to Generate Energy from Existing Water Supply Networks

In this paper, the possibility of installing small hydraulic turbines in existing water-supply networks, which exploit the daily pressure fluctuations in order to produce energy, is examined. For this purpose, a network of five pressure sensors is developed, which is connected to an artificial intelligence system in order to predict the daily pressure values of all nodes of the network. The sensors are placed at the critical nodes of the network. The locations of the critical nodes are implemented by applying graph theory algorithms to the water distribution network. EPANET software is used to generate the artificial intelligence training data with an appropriate external call from a Python script. Then, an improvement model is implemented using the Harmony Search Algorithm in order to calculate the daily pressure program, which can be allocated to the turbines and, consequently, the maximum energy production. The proposed methodology is applied to a benchmark water supply network and the results are presented.

Energy-Efficient Message Bundling with Delay and Synchronization Constraints in Wireless Sensor Networks.

In a wireless sensor network (WSN), reducing the energy consumption of battery-powered sensor nodes is key to extending their operating duration before battery replacement is required. Message bundling can save on the energy consumption of sensor nodes by reducing the number of message transmissions. However, bundling a large number of messages could increase not only the end-to-end delays and message transmission intervals, but also the packet error rate (PER). End-to-end delays are critical in delay-sensitive applications, such as factory monitoring and disaster prevention. Message transmission intervals affect time synchronization accuracy when bundling includes synchronization messages, while an increased PER results in more message retransmissions and, thereby, consumes more energy. To address these issues, this paper proposes an optimal message bundling scheme based on an objective function for the total energy consumption of a WSN, which also takes into account the effects of packet retransmissions and, thereby, strikes the optimal balance between the number of bundled messages and the number of retransmissions given a link quality. The proposed optimal bundling is formulated as an integer nonlinear programming problem and solved using a self-adaptive global-best harmony search (SGHS) algorithm. The experimental results, based on the Cooja emulator of Contiki-NG, demonstrate that the proposed optimal bundling scheme saves up to 51.8% and 8.8% of the total energy consumption with respect to the baseline of no bundling and the state-of-the-art integer linear programming model, respectively.

Using metaheuristics to improve the placement of multi-controllers in software-defined networking enabled clouds

SDN is a model that separates the control and the data levels in an arrangement to enhance capability to program and configure the network in a more agile and efficient manner. Multiple controller modules have been used in the SDN engineering to empower programmable and adaptable configurations such as improving scalability and reliability. The distance and time calculations and other performance measures have to be considered in solving the Multi-Controller Position Problem (MCPP). This paper investigates the use of metaheuristic algorithms to build an MCPP mathematical model. Both the symmetric Harmony Search (HS) modelling and the Particle Swarm Optimization (PSO) algorithm are considered in this respect. Thus, our hybrid approach is proposed and known as Harmony Search with Particle Swarm Optimization (HSPSO) is applied and we compared the extracted results with the state-of-the-art techniques in the previous literature. Besides the development of the mathematical model, a simulation study has been done considering the relevant parameters including the link distance description and the access time between the SDN entities. The console simulation uses NetBeans with CloudsimSDN procedure files in the SDN-based cloud environment.

Effects of dispatch strategies on optimum sizing of solar-diesel-battery energy storage-RO desalination hybrid scheme by efficient heuristic algorithm

Dispatch strategies on optimum sizing of hybrid renewable energy systems are crucial for attaining a cost-effective and reliable power supply. In this paper, the effects of dispatch strategies on optimum sizing of photovoltaic/energy storage/diesel/ reverse osmosis desalination hybrid scheme for supplying the electrical loads and freshwater demand of a remote region are presented. The size of the components of the hybrid scheme are optimized to minimize the total net annual cost and minimizing the system's Levelized cost of energy and to minimize the cost of the desalinated water produced, and the reliability index. For this aim, two optimal dispatch strategies, load following, and cycle charging, are designed for integrated energy systems. So an efficient heuristic algorithm, tabu search, is used for optimum sizing of the hybrid energy scheme. The results are compared with the results obtained by well-known optimization method, harmony search. In each of the strategies, the effects of reliability index and economic factors, including diesel generator initial cost, fuel cost, the O&M cost of diesel generator, initial battery cost, photovoltaic initial cost, and the interest rate, on the optimization of the hybrid energy scheme have been investigated. It showed that the tabu search algorithm has potential benefit to reduce total cost by nearly 1.8% and average simulation time by nearly 1.65% as compared to the harmony search algorithm. Also, in a specific reliability index, the cycle charging strategy has potential benefit to reduce greenhouse gas emissions by nearly 11.5% per year and the cost criteria by nearly 7.5% as compared to the load following strategy.

Design of buckling restrained steel braces using application programming interface between simulation and discrete optimization

In this study, buckling restrained braces (BRBs) are optimized through application programming interface between simulation and discrete optimization. It is aimed to maximize the energy dissipation capacity of BRBs considering the American Institute of Steel Construction (ANSI/AISC 341). Unlike other studies, BRBs modeled in the finite element packaged software are directly linked to optimization algorithms. So, the geometric and material nonlinearities are also considered. Harmony Search Algorithm (HSA), which simulates the improvisation musician performances in finding pleasing harmony, and Black Widow Optimization Algorithm (BWOA), which imitates inimitable paring attitude of black widow spiders, are taken as the optimizer tools of this study. They encoded in Microsoft Visual Basic programming language. Initially, the algorithmic performances of the HSA and BWOA are compared and evaluated on two benchmark structural engineering design problems. Afterward, two different shaped BRBs are modeled in a finite element analysis (FEA) based software, namely ANSYS Workbench. Then, the obtained simulations are integrated with the HS and BWO algorithms throughout the application programming interface without identification of complex objective function and design constraints in formulations. These are directly calculated by ANSYS Workbench over very simple formulas. So, the attained optimum designs of BRBs are investigated with a new approach. Furthermore, in order to see the supreme algorithmic performances of the HSA and BWOA, all benchmark and BRB design problems are solved so-called well-established conventional standard Genetic Algorithm (sGA). Eventually, the proposed novel design methodology gives opportunity and eases to the designers since it provides convenience in solving complicated problems having nonlinear objective function and design constraints that are tiresome to encode.

Joint optimization of space allocation and yard crane deployment in container terminal under uncertain demand

The fluctuation of container transportation volume caused by trade policy, epidemic disease and other factors has a significant impact on the terminal yard management. Especially, the decision of yard space problem and yard crane deployment problem is depending on the arriving container volume. Due to the limited space and mechanical resources of the terminal yard, the uncertain container demand will lead to the waste or shortage of yard resources. In order to improve the efficiency of yard management, this paper studies the integrated optimization of yard resources considering the impact of uncertain container demand, and a stochastic optimization model is established to improve the robustness of the daily yard management. Due to the complexity of the model, a harmony search algorithm based on two-stage decomposition strategy is designed to solve the proposed model. To accelerate the solving speed, a scoring method is developed to generate the initial space allocation plan, and a Tabu list is added to improve the solution quality. The numerical experiments are conducted to validate effectiveness and efficiency of the method.

Comparison of Different Optimization Methods for the Microstructure of Proton Exchange Membrane Fuel Cells

Proton exchange membrane fuel cells (PEMFCs) have attracted much attention in the research and commercial sectors because they are environmental friendly and have relatively high power density compared to most other energy storage devices based on electrochemical processes. A significant part of the research on PEMFCs is related to decreasing the cost and improving the structure of PEMFCs by optimizing numerically the microstructure of these devices including the non-uniform porosity, carbon, nafion, and catalyst (i.e. platinum) distributions and the geometrical characteristics. The existing optimization techniques can generally be divided into heuristic and non-heuristic techniques. Heuristic techniques usually use stochastic approaches that search the optimization space using trial-and-error methods. Examples of such techniques include the genetic algorithm, particle swarm optimization, differential evolution, simulating annealing, harmony search, memetic algorithms, etc. These techniques can be applied to optimize a small number of design variables and often need to be used with simplified (often purely mathematic and not based on fundamental physics) models, such as compact, reduced-order models, or equivalent circuit models. On the other hand, non-heuristic techniques are deterministic and often require evaluating the gradient of the objective function. In general, these techniques have local convergence and their rate of convergence can be increased, using second-order derivatives such as the Hessian matrix, or taking advantage of the particular functional form of the objective function. Non-heuristic techniques usually require between a few tens of iterations to optimize the objective function compared to heuristic techniques which require at least tens of thousands of iterations.In this presentation we will make a thorough critical review of the different optimization methods used in the literature for PEMFCs. In additional, we will present the results of our efforts to develop a full-cell optimization algorithm for PEMFCs using the adjoint method [1-3]. The advantages and disadvantages of different methods, including the adjoint method, will be discussed in detail and examples of sample simulations results will be presented.

A novel channel selection scheme for olfactory EEG signal classification on Riemannian manifolds

Objective. The classification of olfactory-induced electroencephalogram (olfactory EEG) signals has potential applications in disease diagnosis, emotion regulation, multimedia, and so on. To achieve high-precision classification, numerous EEG channels are usually used, but this also brings problems such as information redundancy, overfitting and high computational load. Consequently, channel selection is necessary to find and use the most effective channels. Approach. In this study, we proposed a multi-strategy fusion binary harmony search (MFBHS) algorithm and combined it with the Riemannian geometry classification framework to select the optimal channel sets for olfactory EEG signal classification. MFBHS was designed by simultaneously integrating three strategies into the binary harmony search algorithm, including an opposition-based learning strategy for generating high-quality initial population, an adaptive parameter strategy for improving search capability, and a bitwise operation strategy for maintaining population diversity. It performed channel selection directly on the covariance matrix of EEG signals, and used the number of selected channels and the classification accuracy computed by a Riemannian classifier to evaluate the newly generated subset of channels. Main results. With five different classification protocols designed based on two public olfactory EEG datasets, the performance of MFBHS was evaluated and compared with some state-of-the-art algorithms. Experimental results reveal that our method can minimize the number of channels while achieving high classification accuracy compatible with using all the channels. In addition, cross-subject generalization tests of MFBHS channel selection show that subject-independent channels obtained through training can be directly used on untrained subjects without greatly compromising classification accuracy. Significance. The proposed MFBHS algorithm is a practical technique for effective use of EEG channels in olfactory recognition.

A novel PID controller for BLDCM speed control using dual fuzzy logic systems with HSA optimization

In order to enhance the speed control performance of the brushless DC motor (BLDCM), a novel proportion integration differentiation (PID) is proposed in this paper by using dual fuzzy logic systems (FLSs) with harmony search algorithm (HSA) optimization, which is called DFPID-HSA. Firstly, the FLS1 in DFPID-HSA locks the three coefficients of the PID controller in an extensive range on the basis of the system error and error change rate. Then, the FLS2 is optimized by HSA (HSA-F2) to obtain the precise correction of the three coefficients. To get the optimal global harmony better, the improved dynamic adjustment mode is used for the pitch adjustment rate (PAR) and distance bandwidth (BW) in HSA, and the triple selection method is adopted in the composition harmony section to realize the global search. Finally, DFPID-HSA provides the optimal supply control signal to BLDCM so that it can control the speed effectively. Moreover, the stability of the system is analyzed by the pole, Lyapunov, and Nyquist determination methods. And the sensitivity analysis of DFPID-HSA is carried out under the condition of different motor’s mechanical parameters to check its robustness. In addition, the superiority of DFPID-HSA is verified by MATLAB simulation and experiment platform.

A hyper-heuristic inspired approach for automatic failure prediction in the context of industry 4.0

In the era of technological advances and Industry 4.0, massive data collection and analysis is a common approach followed by many industries and companies worldwide. One of the most important uses of data mining and Machine Learning techniques is to predict possible breaks or failures in industrial processes or machinery. This research designs and develops a hyper-heuristic inspired methodology to autonomously identify significant parameters of the time series that characterize the behaviour of relevant process variables enabling the prediction of failures. The proposed hyper-heuristic inspired approach is based on the combination of an optimization process performed by a meta-heuristic algorithm (Harmony Search) and feature based statistical methods for anomaly detection. It demonstrates its adaptability to different failure cases without expert domain knowledge and the capability of autonomously identifying most relevant parameters of the time series to detect the abnormal behaviour prior to the final failure. The proposed solution is validated against a real database of a cold stamping process yielding satisfactory results respect to a novel AUC_ROC based metric, named AUC_MOD, and other conventional metrics, i.e., Specificity, Sensitivity and False Positive Rate.

MRI-BRAIN TUMOR CLASSIFICATION USING K-MEANS CLUSTERING AND ENHANCED HARMONY FEATURE SELECTION

This study introduces an enhanced feature selection method that is efficient in differentiating the malignant tumor patients from the benign patients by using K-Means clustering method combined with enhanced harmony search algorithm. The start of malignant tumor is caused by gene mutation process, it is very vital to identify and classify the presence or absence of the malignant tumor through analyzing the gene information. The planned methodology composed of four steps. The first step is to preprocess the original data by using min-max normalization. In the next step, generalized fisher score is used to find and eliminate the redundant data to confine the significant candidate genes. Selection of representative gene from each cluster is done by the K-Means clustering technique in the next phase. In the final phase the vital features for classification are selected by enhanced harmony search algorithm. The selected gene combination through this method for feature selection is then applied to the classification model and verified by means of 5-fold cross validation method. The projected model obtained a classification accuracy of up to 96.67%. Additionally, on comparing the projected method with other methods, the projected method performs well in classifying malignant tumor. This new method performs well in classification of brain tumors to malignant or benign. The projected model cannot be restricted only with the classification of brain tumors, but can also be used for other gene-related diseases effectively.

Review on the parameter settings in harmony search algorithm applied to combinatorial optimization problems

Harmony search algorithm (HSA) is relatively considered as one of the most recent metaheuristic algorithms. HSA is a modern - nature algorithm that simulates the musicians’ natural process of musical improvisation to enhance their instrument’s note to find a state of pleasant (harmony) according to aesthetic standards. Lots of variants of HSA have been suggested to tackle combinatorial optimization problems. They range from hybridizing some components of other metaheuristic approaches (to improve the HSA) to taking some concepts of HSA and utilizing them to improve other metaheuristic methods. This stud y reviews research pertaining to parameter settings of HSA and its applications to efficiently solve hard combinatorial optimization problems.

Optimal day‐ahead scheduling in micro‐grid with renewable based DGs and smart charging station of EVs using an enhanced manta‐ray foraging optimisation

Micro-grids (MGs) are small parts of the electrical power system that work along with the electric system or autonomously based on environmental or economic conditions. The renewable-based distributed generators (RDGs) and electric vehicle charging stations (EVCSs) are wildly incorporated in MGs. Optimal day-ahead scheduling of the MG is ahead corner of energy management for cost reduction. In addition, solving the economic load dispatch and day-ahead scheduling of the MG is a complex optimisation problem, especially considering the RDGs, EVCS, and uncertainties in the electrical system. This paper aims to optimise the day-ahead scheduling of the MG with and without a smart charging strategy for electric vehicles. An enhanced manta-ray foraging optimisation (EMRFO) algorithm is proposed to solve this optimisation problem. EMRFO depends upon boosting population diversity and the searching ability of the standard MRFO using strategies. The proposed strategies are based on quasi-oppositional-based learning and local chaotic mutation. The studied MG consists of wind turbines, fuel cells, and diesel generators. The day-ahead scheduling of the MG is solved with and without considering the uncertainties of the load demand and the wind speed. The proposed algorithm for day-ahead scheduling of the MG is compared to well-known algorithms such as anti lion optimisation, particle swarm optimisation, whale optimisation algorithm, sine cosine algorithm, and harmony search algorithm. The simulation results demonstrate that the proposed algorithm is superior to these algorithms for solving the optimisation problem. The results show that the generation cost is reduced considerably from 77,745.61 $ to 76,984.2 $ by applying the smart operation strategy.