Nature-inspired Method Research Articles

Optimizing Cloud Load Balancing: A Nature-Inspired Approach for Efficient Task Scheduling and Resource Optimization in Scalable Cloud Computing Environments

Cloud load balancing is a key part of making sure that tasks are scheduled and resources are used in the best way possible in scalable cloud computing settings. This study suggests a way to improve load balancing that is based on nature and uses methods as Particle Swarm Optimization (PSO) and NIVM PSO Optimized (NIVM-PSO). By acting like natural processes, these programs can adapt to changing workloads and make sure that tasks are spread out evenly across computers. The goal of the suggested model is to cut down on reaction time, make the best use of resources, and boost system performance as a whole. The results of the experiments show that when compared to standard load balancing methods, they are much better at spreading out the load, lowering delay, and increasing speed. This nature-inspired method is a strong way to handle the complexity and demands of modern cloud systems. It creates a framework that can grow and work well for future cloud computing apps.

Synthesis and Utilisation of Hybrid Metal-Carbonic Anhydrase Enzyme Carrier System for Soil Biocementation

Biocementation is an emerging nature-inspired method of producing eco-friendly cement for soil stabilization. This paper used the bovine-derived carbonic anhydrase (CA) enzyme to catalyse the bioprecipitation of CaCO3 in a fine-grained soil and thus to biocement the soil. To increase the efficiency of the CA, an innovative copper–carbonic anhydrase (CA) hybrid was fabricated. This study is a proof-of-concept of the potential application of these enzyme carriers for soil biocementation. The hybrid carriers are aimed to enhance the stability, recovery and reusability of the enzyme used in the biocementation process. The results showed that the fabricated copper phosphate-based inorganic hybrid was stable throughout the duration of the tests (2 months) and under a wide range of pH and temperatures. Its enzymatic activity was enhanced compared to the free CA enzyme and it was proved suitable for soil biocementation. This was further confirmed by the SEM analysis. Additionally, the treated soil with the formulated hybrid carrier showed improved unconfined compressive strength, especially when the carriers were implemented into the soil by mixing. The material analysis by Raman spectroscopy confirmed calcium carbonate as the primary precipitate, consistent with soil biocementation. Overall, this innovative method of delivery of enzymes with enhanced stability and activity shows promise that, upon further development, it can be successfully used to increase the efficiency and sustainability of the biocementation process.

Nature-Inspired Stalactite Nanopores for Biosensing and Energy Harvesting.

Nature provides a wide range of self-assembled structures from the nanoscale to the macroscale. Under the right thermodynamic conditions and with the appropriate material supply, structures like stalactites, icicles, and corals can grow. However, the natural growth process is time-consuming. This work demonstrates a fast, nature-inspired method for growing stalactite nanopores using heterogeneous atomic deposition of hafnium dioxide at the orifice of templated silicon nitride apertures. The stalactite nanostructures combine the benefits of reduced sensing region typically for 2-dimensional material nanopores with the asymmetric geometry of capillaries, resulting in ionic selectivity, stability, and scalability. The proposed growing method provides an adaptable nanopore platform for basic and applied nanofluidic research, including biosensing, energy science, and filtration technologies.

An enhanced grey wolf optimizer with fusion strategies for identifying the parameters of photovoltaic models

Identifying photovoltaic (PV) parameters accurately and reliably can be conducive to the effective use of solar energy. The grey wolf optimizer (GWO) that was proposed recently is an effective nature-inspired method and has become an effective way to solve PV parameter identification. However, determining PV parameters is typically regarded as a multimodal optimization, which is a challenging optimization problem; thus, the original GWO still has the problem of insufficient accuracy and reliability when identifying PV parameters. In this study, an enhanced grey wolf optimizer with fusion strategies (EGWOFS) is proposed to overcome these shortcomings. First, a modified multiple learning backtracking search algorithm (MMLBSA) is designed to ameliorate the global exploration potential of the original GWO. Second, a dynamic spiral updating position strategy (DSUPS) is constructed to promote the performance of local exploitation. Finally, the proposed EGWOFS is verified by two groups of test data, which include three types of PV test models and experimental data extracted from the manufacturer’s data sheet. Experiments show that the overall performance of the proposed EGWOFS achieves competitive or better results in terms of accuracy and reliability for most test models.

Wind Driven Optimization Approach based Multi-objective Optimal Power Flow and Emission Index Optimization

This paper proposes one of the optimization methods based on atmospheric motion. It is a global optimization nature-inspired method such as Wind Driven Optimization (WDO) approach to solve the Optimal Power Flow (OPF) and Emission Index (EI) in electric power systems. Our main aim is to minimize an objective function necessary for a best balance between the energy production and its consumption, which is presented as a nonlinear function, taking into account of the equality and inequality constraints. The WDO approach is nature-inspired, population based iterative heuristic optimization algorithm for multi-dimensional and multi-modal problems. WDO method have been examined and tested on the standard IEEE 30-bus system and IEEE 57-bus system with different objectives that reflect total active power generation cost, the active power losses and the emission index. The results of used method have been compared and validated with known references published recently. The results are promising and show the effectiveness and robustness of proposed approach.

Intelligent Feature Subset Selection with Machine Learning Based Detection and Mitigation of DDoS Attacks in 5G Environment

The fifth-generation (5G) technology is anticipated to permit connectivity to billions of devices, called the Internet of Things (IoT). The primary benefit of 5G is that it has maximum bandwidth and can drastically expand service beyond cell phones to standard internet service for conventionally fixed connectivity to homes, offices, factories, etc. But IoT devices will unavoidably be the primary target of diverse kinds of cyberattacks, notably distributed denial of service (DDoS) attacks. Since the conventional DDoS mitigation techniques are ineffective for 5G networks, machine learning (ML) approaches find helpful to accomplish better security. With this motivation, this study resolves the network security issues posed by network devices in the 5G networks and mitigates the harmful effects of DDoS attacks. This paper presents a new pigeon-inspired optimization-based feature selection with optimal functional link neural network (FLNN), PIOFS-OFLNN model for mitigating DDoS attacks in the 5G environment. The proposed PIOFS-OFLNN model aims to detect DDoS attacks with the inclusion of feature selection and classification processes. The proposed PIOFS-OFLNN model incorporates different techniques such as pre-processing, feature selection, classification, and parameter tuning. In addition, the PIOFS algorithm is employed to choose an optimal subset of features from the pre-processed data. Besides, the OFLNN based classification model is applied to determine DDoS attacks where the Rat Swarm Optimizer (RSO) parameter tuning takes place to adjust the parameters involved in the FLNN model optimally. FLNN is a low computational interconnectivity higher cognitive neural network. There are still no hidden layers. FLNN’s input vector is operationally enlarged to produce non-linear remedies. More details can be accessed application of Nature-Inspired Method to Odia Written by hand Number system Recognition. To validate the improved DDoS detection performance of the proposed model, a benchmark dataset is used.

Lipase immobilization on alumina membranes using a traditional and a nature-inspired method for active degradation of oil fouling

This study compared the traditional method of silanization using 3-aminopropyltriethoxysilane (APTES) with the innovative technique of polydopamine coating (PDA) for lipase immobilization on α-alumina membranes. Three lipases were tested, and Eversa Transform 2.0 (ET2) was chosen to be immobilized in the membrane due to its high hydrolytic activity towards soybean oil. Polydopamine deposition with and without glutaraldehyde activation presented the highest membrane hydrolytic activities (1553 ± 209 and 1845 ± 283 U·m−2, respectively). The membrane without activation maintained 41.1 ± 1.7 % of the free enzyme activity while the one with glutaraldehyde preserved only 23.9 ± 1.0 %. When tested in oil–water separation using a soybean oil emulsion, the membranes with ET2 immobilized by PDA showed water permeance 2-fold higher than the nonactive membranes (300 ± 12 and 156 ± 4 L·h−1·m−2·bar, respectively), showing good fouling-degrading capacity. They also presented self-cleaning properties when activated through the use of proper pH and temperature. The water permeance recovery for the control membrane was 34% while the membranes with immobilized ET2 by PDA and APTES showed recoveries of 69% and 49%, respectively. Permeance recovery for ET2 immobilized by silanization was similar to the PDA-coated membrane with no enzyme (45%).

Multi-strategy Gaussian Harris hawks optimization for fatigue life of tapered roller bearings.

Bearing is one of the most fundamental components of rotary machinery, and its fatigue life is a crucial factor in designing. The design optimization of tapered roller bearing (TRB) is a complex design problem because various arrays of designing parameters and functional requirements should be fulfilled. Since there are many design variables and nonlinear constraints, presenting an optimal design of TRBs poses some challenges for metaheuristic algorithms. The Harris hawks optimization (HHO) algorithm is a robust nature-inspired method with unique exploitation and exploration phases due to its time-varying structure. However, this metaheuristic algorithm may still converge to local optima for more challenging problems such as the design of TRBs. Therefore, this study aims to improve the accuracy and efficiency of the shortcomings of this algorithm. The performance of the proposed algorithm is first evaluated for the TRB optimization problem. The TRB optimization design has nine design variables and 26 constraints because of geometrical dimensions and strength conditions. The productivity of the proposed method is compared with diverse metaheuristic algorithms in the literature. The results demonstrate the significant development of dynamic load capacity in comparison to the standard value. Furthermore, the enhanced version of the HHO algorithm presented in this study is benchmarked with various well-known engineering problems. For supplementary materials regarding algorithms in this research, readers can refer to https://aliasgharheidari.com.

Hazelnut tree search algorithm: a nature-inspired method for solving numerical and engineering problems

Hazelnut tree search algorithm: a nature-inspired method for solving numerical and engineering problems

Comparison of a novel dominance-based differential evolution method with the state-of-the-art methods for solving multi-objective real-valued optimization problems

Differential Evolution algorithm (DE) is a well-known nature-inspired method in evolutionary computations scope. This paper adds some new features to DE algorithm and proposes a novel method focusing on ranking technique. The proposed method is named as Dominance-Based Differential Evolution, called DBDE from this point on, which is the improved version of the standard DE algorithm. The suggested DBDE applies some changes on the selection operator of the Differential Evolution (DE) algorithm and modifies the crossover and initialization phases to improve the performance of DE. The dominance ranks are used in the selection phase of DBDE to be capable of selecting higher quality solutions. A dominance-rank for solution X is the number of solutions dominating X. Moreover, some vectors called target vectors are used through the selection process. Effectiveness and performance of the proposed DBDE method is experimentally evaluated using six well-known benchmarks, provided by CEC2009, plus two additional test problems namely Kursawe and Fonseca & Fleming. The evaluation process emphasizes on specific bi-objective real-valued optimization problems reported in literature.
 Likewise, the Inverted Generational Distance (IGD) metric is calculated for the obtained results to measure the performance of algorithms. To follow up the evaluation rules obeyed by all state-of-the-art methods, the fitness evaluation function is called 300.000 times and 30 independent runs of DBDE is carried out. Analysis of the obtained results indicates that the performance of the proposed algorithm (DBDE) in terms of convergence and robustness outperforms the majority of state-of-the-art methods reported in the literature

Finding all Pareto optimal paths by simulating ripple relay race in multi-objective networks

This paper proposes a novel nature-inspired method, so-called ripple-spreading algorithm (RSA) for multi-objective path optimization problem (MOPOP). Unlike most existing methods mainly capable of finding partial or approximated Pareto front, this paper focuses on calculating the complete Pareto front. This is achieved by taking advantage of the optimality principle in natural ripple-spreading phenomenon. Basically, the proposed RSA carries out a one-off ripple relay race in the route network, and then the complete Pareto front will be identified with guaranteed optimality by backtracking those Pareto non-dominated ripples (PNDRs) which reached the destination node. Theoretical analyses and comprehensive experiments show that all complete Pareto fronts of a one-to-all MOPOP can also be found in just a single run of ripple relay race, and the reported method can be further extended to calculate all Pareto optimal paths in dynamical networks, which have rarely been touched by existing MOPOP methods. Since many real-world application problems can be converted into MOPOP, the reported method has a great potential of applications.

Parametric Optimization for Cutting Forces and Material Removal Rate in the Turning of AISI 5140

The present paper deals with the optimization of the three components of cutting forces and the Material Removal Rate (MRR) in the turning of AISI 5140 steel. The Harmonic Artificial Bee Colony Algorithm (H-ABC), which is an improved nature-inspired method, was compared with the Harmonic Bee Algorithm (HBA) and popular methods such as Taguchi’s S/N ratio and the Response Surface Methodology (RSM) in order to achieve the optimum parameters in machining applications. The experiments were performed under dry cutting conditions using three cutting speeds, three feed rates, and two depths of cuts. Quadratic regression equations were identified as the objective function for HBA to represent the relationship between the cutting parameters and responses, i.e., the cutting forces and MRR. According to the results, the RSM (72.1%) and H-ABC (64%) algorithms provide better composite desirability compared to the other techniques, namely Taguchi (43.4%) and HBA (47.2%). While the optimum parameters found by the H-ABC algorithm are better when considering cutting forces, RSM has a higher success rate for MRR. It is worth remarking that H-ABC provides an effective solution in comparison with the frequently used methods, which is promising for the optimization of the parameters in the turning of new-generation materials in the industry. There is a contradictory situation in maximizing the MRR and minimizing the cutting power simultaneously, because the affecting parameters have a reverse effect on these two response parameters. Comparing different types of methods provides a perspective in the selection of the optimum parameter design for industrial applications of the turning processes. This study stands as the first paper representing the comparative optimization approach for cutting forces and MRR.

An Efficient Metaheuristic Technique to Control the Maximum Power Point of a Partially Shaded Photovoltaic System Using Crow Search Algorithm (CSA)

The field of research in maximum power point tracking (MPPT) methods is experiencing great progress with a wide range of techniques being suggested, ranging from simple but ineffective methods to more effective but complex ones. Therefore, it is very important to propose a strategy that is both simple and effective in controlling the global maximum power point (GMPP) for a photovoltaic (PV) system under changing weather conditions, especially in partial shading cases (PSCs). This paper proposes a new design of an MPPT controller based on a metaheuristic optimization technique called Crow Search Algorithm (CSA) to attenuate the undesirable effects of partial shading on the tracking performances of standalone PV systems. CSA is a nature-inspired method based on the intelligent skills of the crow in the search process of hidden food places. CSA technique combines efficiency and simplicity using only two tuning parameters. The stability analysis of the proposed system is performed using a Lyapunov function. The simulation results for three different partial shading cases that are zero, weak and severe shading confirm the superior performance of CSA compared to PSO and P&O techniques in term of easy implementation, high efficiency and low power loss, decreasing considerably the convergence time by an average of 38.53%.

Co-eye: a multi-resolution ensemble classifier for symbolically approximated time series

Time series classification (TSC) is a challenging task that attracted many researchers in the last few years. One main challenge in TSC is the diversity of domains where time series data come from. Thus, there is no “one model that fits all” in TSC. Some algorithms are very accurate in classifying a specific type of time series when the whole series is considered, while some only target the existence/non-existence of specific patterns/shapelets. Yet other techniques focus on the frequency of occurrences of discriminating patterns/features. This paper presents a new classification technique that addresses the inherent diversity problem in TSC using a nature-inspired method. The technique is stimulated by how flies look at the world through “compound eyes” that are made up of thousands of lenses, called ommatidia. Each ommatidium is an eye with its own lens, and thousands of them together create a broad field of vision. The developed technique similarly uses different lenses and representations to look at the time series, and then combines them for broader visibility. These lenses have been created through hyper-parameterisation of symbolic representations (Piecewise Aggregate and Fourier approximations). The algorithm builds a random forest for each lens, then performs soft dynamic voting for classifying new instances using the most confident eyes, i.e., forests. We evaluate the new technique, coined Co-eye, using the recently released extended version of UCR archive, containing more than 100 datasets across a wide range of domains. The results show the benefits of bringing together different perspectives reflecting on the accuracy and robustness of Co-eye in comparison to other state-of-the-art techniques.

Statistical and Nature-Inspired Modeling of Vehicle Flows by Using Finite Mixtures of Simple Circular Normal Distributions

The representation, visualization, and modeling of traffic data is at the heart of intelligent transportation systems. Different types of traffic data exist, and novel ways of their accurate representation and modeling, which are useful for further analyses, simulations, and optimizations, are sought. In this work, location-specific traffic flows are represented by finite mixtures of circular normal (von Mises) statistical distributions. The parameters of the distributions are learned from empirical data by two variants of the expectation-maximization (EM) algorithm and by a nature-inspired method, differential evolution (DE). A proposed statistical model and a fitting strategy are evaluated on real-world data sets describing traffic flows in New York City. The experimental results show that the EM algorithm is able to find model parameters that correspond to input data and that are better than their analytic estimates, while DE evolves even more accurate models. The models based on circular distributions can be represented by circular plots as a novel type of visually appealing and easily interpretable fingerprints of the underlying traffic flow patterns.

Deep Reinforcement Learning for Cooperative Content Caching in Vehicular Edge Computing and Networks

In this article, we propose a cooperative edge caching scheme, a new paradigm to jointly optimize the content placement and content delivery in the vehicular edge computing and networks, with the aid of the flexible trilateral cooperations among a macro-cell station, roadside units, and smart vehicles. We formulate the joint optimization problem as a double time-scale Markov decision process (DTS-MDP), based on the fact that the time-scale of content timeliness changes less frequently as compared to the vehicle mobility and network states during the content delivery process. At the beginning of the large time-scale, the content placement/updating decision can be obtained according to the content popularity, vehicle driving paths, and resource availability. On the small time-scale, the joint vehicle scheduling and bandwidth allocation scheme is designed to minimize the content access cost while satisfying the constraint on content delivery latency. To solve the long-term mixed integer linear programming (LT-MILP) problem, we propose a nature-inspired method based on the deep deterministic policy gradient (DDPG) framework to obtain a suboptimal solution with a low computation complexity. The simulation results demonstrate that the proposed cooperative caching system can reduce the system cost, as well as the content delivery latency, and improve content hit ratio, as compared to the noncooperative and random edge caching schemes.

Nature-inspired chemistry toward hierarchical superhydrophobic, antibacterial and biocompatible nanofibrous membranes for effective UV-shielding, self-cleaning and oil-water separation

Fabrication of environmental-friendly, low-cost, and free-standing superhydrophobic nanofibrous membranes with additional functionalities such as self-cleaning and UV-shielding properties is highly demanded for oil-water separation. Herein, we describe the preparation of multifunctional superhydrophobic nanofibrous membrane by using a facile and novel nature-inspired method, i.e., plant polyphenol (tannic acid) metal complex is introduced to generate rough hierarchical structures on the surface of an electrospun polyimide (PI) nanofibrous membrane, followed by modification of poly (dimethylsiloxane) (PDMS). Taking an as-prepared tannic acid − Al3+-based superhydrophobic membrane as an example, it not only exhibits anti-impact, low-adhesive and self-cleaning functions, but also presents excellent performance in the separation of various oil-water mixtures. A high flux up to 6935 l m−2 h−1 with a separation efficiency of over 99% and the oil contents in water below 5 ppm is obtained even after repeating use for twenty separation cycles. Additionally, the membrane exhibits excellent UV-shielding property, attributing to the inherent UV-absorbing ability of tannic acid. Furthermore, the membrane also possesses additional properties including antibacterial activity, good biocompatibility, robust mechanical strength, and excellent resistance to various harsh conditions. These attractive properties of the as-prepared membrane make it a promising candidate for potential applications in industrial oil-contaminated water treatments and oil-water separation.

Extracting New Dispatching Rules for Multi-objective Dynamic Flexible Job Shop Scheduling with Limited Buffer Spaces

Dispatching rules are among the most widely applied and practical methods for solving dynamic flexible job shop scheduling problems in manufacturing systems. Hence, the design of applicable and effective rules is always an important subject in the scheduling literature. The aim of this study is to propose a practical approach for extracting efficient rules for a more general type of dynamic job shop scheduling problem in which jobs arrive at the shop at different times and machine breakdowns occur stochastically. Limited-buffer conditions are also considered, increasing the problem complexity. Benchmarks are selected from the literature, with some modifications. Gene expression programming combined with a simulation model is used for the design of scheduling policies. The extracted rules are compared with several classic dispatching rules from the literature based on a multi-objective function. The new rules are found to be superior to the classic ones. They are robust and can be used for similar complex scheduling problems. The results prove the efficiency of gene expression programming as a nature-inspired method for dispatching rule extraction.

Lion Pride Optimization Algorithm: A meta-heuristic method for global optimization problems

This paper presents a new non-gradient nature-inspired method, Lion Pride Optimization Algorithm (LPOA) for solving optimal design problems. This method is inspired by the natural collective behavior of lions in their social groups lion prides. Comparative studies are carried out using fifteen mathematical examples, two benchmark structural design problems, in order to verify the effectiveness of the proposed technique. The LPOA algorithm is also compared with other algorithms for some mathematical and structural problems. The results have proven that the proposed algorithm provides desirable performance in terms of accuracy and convergence speed in all the considered problems.

An enhanced moth-flame optimizer for solving non-smooth economic dispatch problems with emissions

This paper proposes an Enhanced Moth-Flame Optimization (EMFO) algorithm for solving the non-convex economic dispatch (ED) problem with valve point effects and emissions. It determines the optimal generation schedule of generating units by minimizing both fuel cost and emission simultaneously while the system constraints are achieved. The moth-flame optimization (MFO) is a recent nature-inspired method, which is based on the navigation mechanism called transverse orientation of Moths in space. The EMFO combines the merits of the traditional MFO and levy flight by concentration the search space. The usage of Lévy-flight has the prominent properties to increase the diversity of population. The effectiveness of the proposed EMFO method is proven on using 10 benchmark functions and 3 standard test systems consisting of 6, 40 and a large scale 80 generating units with non-convex fuel cost functions. The capability of the proposed algorithm is verified also for single and multi-objective studied cases and its results are compared with several well-known previous techniques. The results confirm the high performance of the proposed EMFO method for finding the optimal economic generation scheduling at acceptable low emission levels.