Bio-Inspired Workflow Scheduling on HPC Platforms

Efficient scheduling of tasks in workflows of cloud or grid applications is a key to achieving better utilization of resources as well as timely completion of the user jobs. Many scientific applications comprise several tasks that are dependent in nature and are specified by workflow graphs. The aim of the cloud meta-scheduler is to schedule the user application tasks (and the applications) so as to optimize the resource utilization and to execute the user applications in minimum amount of time. During the past decade, there have been several attempts to use bio-inspired scheduling algorithms to obtain an optimal or near optimal schedule in order to minimize the overall schedule length and to optimize the use of resources. However, as the number of tasks increases, the solution space comprising different tasks-resource mapping sequences increases exponentially. Hence, there is a need to devise mechanisms to improvise the search strategies of the bio-inspired scheduling algorithms for better scheduling solutions in lesser number of iterations/time. The objective of the research work in this paper is to use bio-inspired bacteria foraging optimization algorithm (BFOA) along with other heuristics algorithms for better search of the scheduling solution space for multiple workflows. The idea is to first find a schedule by the heuristic algorithms such as MaxMin, MinMin, and Myopic, and use these as initial solutions (along with other randomly generated solutions) in the search space to get better solutions using BFOA. The performance of our approach with the existing approaches is compared for quality of the scheduling solutions. The results demonstrate that our hybrid approach (MinMin/Myopic with BFOA) outperforms other approaches.

A Bio-inspired trajectory planning method for robotic manipulators based on improved bacteria foraging optimization algorithm and tau theory

<abstract><p>In this paper, a novel bio-inspired trajectory planning method is proposed for robotic systems based on an improved bacteria foraging optimization algorithm (IBFOA) and an improved intrinsic Tau jerk (named Tau-J*) guidance strategy. Besides, the adaptive factor and elite-preservation strategy are employed to facilitate the IBFOA, and an improved Tau-J* with higher-order of intrinsic guidance movement is used to avoid the nonzero initial and final jerk, so as to overcome the computational burden and unsmooth trajectory problems existing in the optimization algorithm and traditional interpolation algorithm. The IBFOA is utilized to determine a small set of optimal control points, and Tau-J* is then invoked to generate smooth trajectories between the control points. Finally, the results of simulation tests demonstrate the eminent stability, optimality, and rapidity capability of the proposed bio-inspired trajectory planning method.</p></abstract>

Estimation of Minimum Energy Consumption Index in a Protected Farm Using Bacteria Foraging Optimization Algorithm

This article estimates the minimum energy consumption index in a single story protected farm which would suggest the condition of minimum energy consumption or loss condition. The analytic hierarchy process (AHP), weighted sum method (WSM) and weighted product method (WPM) are used for relative ranking of four energy consumption indicators viz., water pumping, light supplement, CO2 balancing and cooling-heating under three criteria viz., cropping area, daily crop water, and indoor environment. The minimum, maximum and average energy consumption index was predicted by the bacteria foraging optimization (BFO) algorithm and the group method of data handling (GMDH). The minimum energy consumption index (1.4174) predicted by the BFO algorithm gives higher prediction compared energy consumption index (1.114) predicted by the GMDH algorithm.

Plant Disease Detection and Classification Using Bacteria Foraging Optimization Algorithm Through Convolution Neural Network

Humans can recognize the plants infected by diseases but separated from our visual perception it is hard to recognize plant diseases. In croplands without taking the right care and prompt action, the entire field may become a region afflicted by diseases. So we identify the plant diseases ahead of time with the assistance of present-day computer technologies. An advanced model was introduced to accurately recognize and classification plant diseases. Here we proposed an approach that can use the Convolutional Neural Network (CNN) based on BFOA for distinguishing diseases in plants. The input picture for the extraction of features is divided into 3 clusters by the Euclidean distance measurement metric of the k-mean algorithm and from the ROI, parameters of the GLCM matrix are calculated in the same cluster prior to BFOA. Assigning matrix parameters as BFOA input improves the network’s accuracy and efficiency in determining. In classification, we proposed a Convolutional Neural Network (CNN) using ResNet50 as a pre-trained network in deep learning toolbox which classifies from a given dataset. The approach is more reliable as the detection and classification of plant diseases are more precise.

Parameter Optimization for Ship Antiroll Gyros

Ship antiroll gyros are a type of equipment used to reduce ships’ roll angle, and their parameters are related to the parameters of a ship and wave, which affect gyro performance. As an alternative framework, we designed a calculation method for roll reduction rate and considered random waves to establish a gyro parameter optimization model, and we then solved it through the bacteria foraging optimization algorithm (BFOA) and pattern search optimization algorithm (PSOA) to obtain optimal parameter values. Results revealed that the two methods could effectively reduce the overall mass and floor space of the antiroll gyro and improved its antirolling effect. In addition, the convergence speed and antirolling effect of the BFOA were better than that of the PSOA.

Estimation of Minimum Energy Consumption Index in a Protected Farm Using Bacteria Foraging Optimization Algorithm

This article estimates the minimum energy consumption index in a single story protected farm which would suggest the condition of minimum energy consumption or loss condition. The analytic hierarchy process (AHP), weighted sum method (WSM) and weighted product method (WPM) are used for relative ranking of four energy consumption indicators viz., water pumping, light supplement, CO2 balancing and cooling-heating under three criteria viz., cropping area, daily crop water, and indoor environment. The minimum, maximum and average energy consumption index was predicted by the bacteria foraging optimization (BFO) algorithm and the group method of data handling (GMDH). The minimum energy consumption index (1.4174) predicted by the BFO algorithm gives higher prediction compared energy consumption index (1.114) predicted by the GMDH algorithm.

NEW BACTERIA FORAGING AND PARTICLE SWARM HYBRID ALGORITHM FOR MEDICAL IMAGE COMPRESSION

For perfect diagnosis of brain tumour, it is necessary to identify tumour affected regions in the brain in MRI (Magnetic Resonance Imaging) images effectively and compression of these images for transmission over a communication channel at high speed with better visual quality to the experts. An attempt has been made in this paper for identifying tumour regions with optimal thresholds which are optimized with the proposed Hybrid Bacteria Foraging Optimization Algorithm (BFOA) and Particle Swarm Optimization (PSO) named (HBFOA-PSO) by maximizing the Renyi’s entropy and Kapur’s entropy. BFOA may be trapped into local optimal problem and delay in execution time (convergence time) because of random chemo taxis steps in the procedure of algorithm and to get global solution, a theory of swarming is commenced in the structure of HBFOA-PSO. Effectiveness of this HBFOA-PSO is evaluated on six different MRI images of brain with tumours and proved to be better in Peak Signal to Noise Ratio (PSNR), Mean Square Error (MSE) and Fitness Function.