Improved Mutation-Based Particle Swarm Optimization for Load Balancing in Cloud Data Centers

Wind power ramp events increasingly affect the integration of wind power and cause more and more problems to the safety of power grid operation in recent years. Several forecasting techniques for wind power ramp events have been reported. In this paper, the statistical scenarios forecasting method is proposed for wind power ramp event probabilistic forecasting based on the probability generating model. Multi-objective fitness functions are established considering cumulative density functions and higher order moment autocorrelation functions with respect to the consistency of distribution and timing characteristics, respectively. Parameters of probability generating model are calculated by the iterative optimization using the modified genetic algorithm with multi-objective fitness functions. A number of statistical scenarios captured bands are generated accordingly. Eventually, ramp event probability characteristics are detected from scenarios captured bands to evaluate the ramp event forecasting method. A wind plant of Bonneville Power Administration with actual wind power data is selected for calculation and statistical analysis. It is shown that statistical results with multi-objective functions are more accurate than the results with single objective functions. Moreover, the statistical scenarios forecasting method can accurately estimate the characteristics of wind power ramp events. The results verify that the proposed method can guide the generation method of statistical scenarios and forecasting models for ramp events.

Load unbalancing problem is a multi-variant, multi-constraint problem that degrades performance and efficiency of computing resources. Load balancing techniques cater the solution for load unbalancing situation for two undesirable facets- overloading and under-loading. In contempt of the importance of load balancing techniques to the best of our knowledge, there is no comprehensive, extensive, systematic and hierarchical classification about the existing load balancing techniques. Further, the factors that cause load unbalancing problem are neither studied nor considered in the literature. This paper presents a detailed encyclopedic review about the load balancing techniques. The advantages and limitations of existing methods are highlighted with crucial challenges being addressed so as to develop efficient load balancing algorithms in future. The paper also suggests new insights towards load balancing in cloud computing.

Throughput maximization in a network is one of the major key challenges in wireless LANs (WLANs) and it could be achieved when the load of access points (APs) is balanced. The AP load in WLANs is very often found to be uneven. To overcome such imbalance of load, a load balancing technique have been proposed. The load balancing techniques commonly require proprietary software or hardware at the user side for controlling the user-AP association. A new load balancing technique by controlling the size of WLAN cells (i.e., AP’s coverage range), which is conceptually similar to cell breathing in cellular networks. The proposed scheme does not require any modification from the user side nor may any changes be required to the IEEE 802.11 standard [1]. It only requires the ability of dynamically changing the transmission power of the AP beacon messages. We develop a newer load balancing algorithm that will find the optimal beacon power settings which will thereon help to minimize the load of the most congested AP. The load may become shared and this may be performed with minimal delay and also maximized throughput is to be achieved. Keywords: Network throughput, Access points, WLAN, Beacon Messages, Load balancing, Throughput, Wireless LANs.

This research analyses and discusses the use of Multiobjective fitness function to evolve Finite State Automata. Such automata can describe system’s behavior mathematically in an efficient manner. However system’s behavior must highly depend on its input-output specifications. Genetic Programming is used, and the fitness function is built to guide the evolutionary process in two different cases. First case: Single point fitness function is used where the only focus is on the correctness of the evolved automata. Second case: multiobjective fitness function is used since every real-world problem involves simultaneous optimization of several incommensurable and often competing objectives. Multiobjective optimization is defined as a problem of finding a Finite State Automata which satisfies: parsimony, efficiency, and correctness. It has been presented that for large and complex problems it is necessary to divide them into sub problem(s) and simultaneously breed both sub-program(s) and a calling program.

Cloud computing is an innovative technology that mainly relies on sharing of computing resources, data as well as information over the internet. Cloud computing has been evolved from technological growth in Grid systems, Virtualization and Web2.0. Efficient Load Balancing (LB) and scheduling techniques are required for optimal utilization of computing resources and to reduce turnaround time. Load Balancing balances the load among nodes by shifting load from over-utilized node to under-utilized node. This paper presents an extensive review of different meta-heuristic techniques that are applicable in grid and cloud systems to generate optimal load balancing solution.

On the premise of ensuring route safety, an intelligent route planning algorithm based on multi-strategy particle swarm optimization is proposed with the lowest energy consumption as the goal. The energy consumption model is established based on airline meteorological information, and a multi-objective fitness function is constructed with energy consumption, airline smoothness and collision penalty as optimization objectives. An adaptive mean velocity updating strategy is proposed, and nonlinear inertia weight is introduced, and Tent chaotic mapping is adopted to dynamically adjust the development ability and exploration ability of the algorithm to avoid falling into local optimal solution. The strategy of updating the position of the worst particle is put forward, and the particles with the worst fitness are updated by coordinate cross, which improves the overall particle quality of the population and speeds up the efficiency of population optimization. The simulation results show that the improved multi-strategy particle swarm optimization algorithm is superior to PSO algorithm in optimization ability and convergence speed.

In Wavelength Division Multiplexing (WDM) networks, providing survivability during routing along with maintaining load balancing is a daunting task. In this paper, we propose an Ant based survivable routing and load balancing technique in WDM networks which discovers survivable and load balanced feasible paths. Ant agents are launched in the network to gather essential information such as available bandwidth, route length and number of free wavelengths. A combined feasibility value is generated from these factors for each path. While transmitting data to the destination, the source selects the path with high feasible value and low load as primary path, and other paths as backup paths. During congestion and failures, data transmission is redirected through the backup paths. Thus, our technique provides survivability and load balancing at hand efficiently. Simulation results show that our technique reduces packet drops efficiently by detecting and controlling the congestion.

In this project we have tested evolutionary process on concertina motion of snake robot. Concertina motion is a type of gait in snake in which it draws its body into sine curve then motion begins by extending its head and forward parts of the body by using frictional forces. This type of gait enable snake to move in narrow spaces. Here we have designed our snake robot in Bullet-Physics environment while Hill-Climber algorithm which is a genetic algorithm has been used to optimize the Artificial Neural Network for to give our robot the evolving capability. A multi-objective Fitness Function is designed in bullet-physics engine which reinforces learning of sinusoidal curve in snake and also reinforces forward motion in it. This multi-objective function seems to be promising as compare to single-objective as it considers the shape of the robot and takes into account the distance as well. Here in our experiment the locomotion controller quickly evolved and the desired behaviors have been obtained. Concertina motion with the proposed evolving capabilities make it a good solution for designing basic motion pattern for snake robots.

Cloud computing enables the internet based computing to everywhere. In cloud computing the task scheduling and load balancing is the important issue that must be considered in data centers. In cloud platform service providers allocate the resources based on the available resources this will increase the QoS. The process of distributing workloads is a load balancing Technique. In this paper focusing the load balancing between the virtual machine. Load balancing are different types that is network load, memory capacity, storage capacity and CPU load. Load balancing supports failover, enabling scalability and decreases costs and maximizes the resource availability. This paper presents the detailed review of load balancing with machine learning technique such as naïve bayes, random forest, Decision Tree and Support Vector Machine. By these machine learning model, SVM algorithm significantly to classify the incoming request to reduce the processing time (makespan). Also provide the moth flame optimization technique for dynamic task scheduling to make better scheduling under different load condition. We have experimented and evaluated this algorithm in a cloud simulation environment; we obtain better outcome than some other well-known algorithms. The Simulation results demonstrate that the proposed technique has a better development in terms of reducing the makespan time and load balancing.

This paper deals with the application of gray wolf optimiser (GWO) based on an artificial neural network (ANN) to optimise the coupling of the Kerman combined cycle power plant (KCCPP) with multi-effect distillation desalination (MED) unit. Thermodynamic simulation of the initial power plant has been performed in the GT Pro simulator, and an extracted steam from the steam turbine was used to supply the required energy for the desalination plant. A desalination economic evaluation program called DEEP has been applied to calculate the cost of power and freshwater production. To optimise the system, a multi-objective fitness function has been defined to reach the minimum production cost and maximum performance in the dual-purpose plant. The optimisation procedure has been performed by combining an artificial neural network along with gray wolf optimiser, and the multi-objective fitness function has been predicted by a neural network at each stage of optimisation. In this analysis, the best value of 2.286 has been found for the fitness function by the gray wolf optimiser based on an artificial neural network. This fitness value has been obtained from 89.69 US$/MWh for electric power cost, 40.78% for net electric efficiency, 1.22 US$/m3 for freshwater cost, and 14 for gain output ratio. Highlight Kerman combined cycle power plant with 1912 MWe nominal power has been modelled. A multi-effect distillation desalination plant has been coupled to the power plant to supply 50,000 m3/day of freshwater. To find the optimal design of the dual-purpose plant, an artificial neural network was connected to the gray wolf optimiser algorithm. Multi-objective optimisation has been applied to increase efficiency and reduce costs in the dual-purpose plant.

Load balancing and task partitioning are important components of distributed computing. The optimum performance from the distributed computing system is achieved by using effective scheduling and load balancing strategy. Researchers have well explored CPU, memory, and I/O-intensive tasks scheduling, and load balancing techniques. But one of the main obstacles of the load balancing technique leads to the ignorance of applications having a mixed nature of tasks. This is because load balancing strategies developed for one kind of job nature are not effective for the other kind of job nature. We have proposed a load balancing scheme in this paper, which is known as Mixed Task Load Balancing (MTLB) for Cluster of Workstation (CW) systems. In our proposed MTLB strategy, pre-tasks are assigned to each worker by the master to eliminate the worker's idle time. A main feature of MTLB strategy is to eradicate the inevitable selection of workers. Furthermore, the proposed MTLB strategy employs Three Resources Consideration (TRC) for load balancing (CPU, Memory, and I/O). The proposed MTLB strategy has removed the overheads of previously proposed strategies. The measured results show that MTLB strategy has a significant improvement in performance.

Multi-objective cluster head using self-attention based progressive generative adversarial network for secured data aggregation

In UAV-IoT systems, trajectory planning is crucial for maintaining effective communication, coordination, and energy efficiency. This challenge is further compounded when UAVs need to coordinate with IoT devices and maintain continuous communication. Existing approaches struggle with limited scalability and inefficient energy management in UAV-supported IoT networks, leading to increased latency and reduced data throughput as network size expands. This work introduces an energy-efficient framework using a multi-objective PathFinder algorithm designed to simultaneously handle transmission coordination between drones and IoT devices. The proposed approach facilitates collaborative decision-making for route planning and resource allocation by utilizing the Collaborative Index, which measures cooperative behavior among network nodes, emphasizing key node cooperativeness parameters. Furthermore, a multi-objective fitness function was constructed for effective path planning using the Collaboration Index of nodes in the path and the QoS of the path. To validate the efficacy of the proposed model, a series of simulations were conducted focusing on key performance indicators such as energy consumption, data delay, and task completion rates against existing state-of-the-art methods.

The integration of Internet of Things (IoT) technologies into healthcare has transformed real-time monitoring and data communication. However, IoT-enabled Cognitive Radio Networks (CRNs) face persistent challenges such as high energy consumption, routing delays, and security risks. This paper proposes a novel Grey Wolf Optimization-based Multi-Adaptive Routing Protocol (GWO-MARP) that combines cluster-based routing with adaptive meta-heuristic intelligence. Unlike traditional cluster-based routing approaches that rely on static or energy-weighted selection, GWO-MARP dynamically determines cluster heads through a multi-objective fitness function that balances residual energy, lifetime, link quality, and security cost. The adaptive hunting behaviour of the GWO algorithm guides optimal path formation and ensures secure and energy-aware transmission, making the protocol distinct from existing methods. The proposed method is implemented and evaluated using MATLAB, and its performance is benchmarked against existing protocols including DA-EDC, MT-DQL, and SDL. Experimental results demonstrate significant improvements in throughput (44.30 kbps), end-to-end delay (1.175ms), packet delivery ratio (99.6%), and energy consumption (0.103J) for a network of 200 nodes. These outcomes validate the proposed protocol's capability to support robust, scalable, and energy-efficient data transmission in IoT-enabled healthcare networks.

Sampling is one of the most common and repeated tasks in a target tracking sensor network. However, tuning the sampling rate parameter can be a challenging issue considering all the sensor network restrictions. In this paper, we propose two adaptive sampling algorithms in a target tracking sensor network while considering a multi-objective fitness function. The restrictions used as objective functions are energy consumption and prediction error which provide a direct feedback to the sampling rate adaptation algorithms. We support our proposed methods with well structured experimental evaluations.