In the redesign field, popularly known as optimization, such difficulties degenerate the exordium of smoothing out appraisals that performed well on benchmark cutoff focuses or essential setting-centered evaluations. To visually examine the commencement of techniques procured for smoothing out those conditions, scientists and experts felt a need to agnize the difficulties and break harmonious changes, modifications, and amendments in the evaluations to oversee such hardships. As of tardy, there has been actuating examination interest in orchestrating machine learning (ML) strategies into meta-heuristics for managing combinatorial smoothing out conditions. This joining betokens meta-heuristics towards a capable, abundant, and exuberant seek after. It also transmutes their exhibition much indistinguishably commensurate to procedure quality, cumulation rate, and energy. Since sundry getting procedures together with sundry purposes, we have incited an objective to review the early advances in utilizing ML techniques to revise meta-heuristics. To fill up this gap survey gives such an audit on the utilization of AI methods in the approach of sundry components of meta-heuristics for purposes behind computation winnows utilizing absolute execution limits. The adequacy of move and quantify is transmuted by refreshing ML evaluations using meta-heuristic redressment computations. In the review, seventeen ML-predicated evaluations we have applied for benchmarking datasets and conspicuous legitimate time tests for tasks and figures we have imparted. Pushing toward portions covers the energy-moving assessment subjects coordinating progressed ML-predicated seventeen evaluations execution and gives examiners some spellbinding pieces of erudition to utilize in their generous applications spaces of pay. This book region causes assembled well-kenned ML approaches to dissever the spam and ham comments. There may be so many obstacles in cyber security, such as Malware, Worm, viruses, SQL Injection, etc. One of them is Spam. It is a typical binary case where the output must be binary. We will examine from a large dataset through the meta-heuristic function, which one among 17 applied algorithms is the optimized one for the binary cases. 

Review for Meta-Heuristic Optimization Propels Machine Learning Computations Execution on Spam Comment Area Under Digital Security Aegis Region

The oil production process in union stations requires consuming a lot of energy, and sewage at high temperature will be produced simultaneously. Realizing the benefits of energy saving that waste heat utilization can bring to the oil field, this article first describes a novel integrated water separation and treatment process (IWSTP) with energy-saving effects. Based on the integrated process, the oilfield distributed heat station system is a good choice for utilizing waste heat from sewage. The heat pump is also considered as indispensable equipment for recovering the low-temperature waste heat of oilfield sewage. Next, a mixed integer linear programming model considering energy and technical constraints is developed to optimize the oilfield water treatment process to minimize annual total cost, which determines the selection and capacity of the required equipment. Taking an oilfield in China as an example, the validity and applicability of this model are demonstrated. The results show that the optimized scheme saves 14.08% of the economic cost compared with the traditional energy supply scheme. Finally, the impact of energy price fluctuation on the design results is analyzed. 

Integration of a novel distributed water and energy system in the oilfield

A parallel compression cycle is one efficient approach to improving the transcritical CO2 refrigeration cycle performance. This paper proposes a modified parallel compression transcritical CO2 refrigeration cycle with an ejector and a sub-cooler to further enhance the cycle performance. The thermodynamic analyses based on the energetic and exergetic analyses are conducted, and the influences of the parameters, including discharge pressure, flash pressure, gas cooler outlet temperature, and evaporation temperature, are discussed. The particle swarm optimization method is used to get the optimal discharge pressure and flash pressure and the temperature reduction in the sub-cooler with respect to the maximum COP. The performance comparisons between the conventional cycle and the modified cycle are presented. The results illustrate that the maximum improvements in COP and volumetric refrigeration capacity reach 15.8% and 17.1%. The utilization of the ejector and sub-cooler could reduce the optimal flash pressure by 16.4–33.0% and the compressor displacement by 11.4% compared with the conventional cycle. The ejector plays a dominant role in performance improvement at a high gas cooler outlet temperature. The exergy destruction analysis shows that the first-largest system exergy destruction ratio of 31.5% in the ejector-enhanced cycle is caused by the gas cooler, and its second-largest exergy destruction is generated in the two parallel compressors instead of the expansion valves in the conventional cycle. 

Thermodynamic performance evaluation of an ejector-enhanced transcritical CO2 parallel compression refrigeration cycle

With the wide application of computational fluid dynamics in various fields and the continuous growth of the complexity of the problem and the scale of the computational grid, large-scale parallel computing came into being and became an indispensable means to solve this problem. In the numerical simulation of multi-block grids, the mapping strategy from grid block to processor is an important factor affecting the efficiency of load balancing and communication overhead. The multi-level graph partitioning algorithm is an important algorithm that introduces graph network dynamic programming to solve the load-balancing problem. This paper proposed a firefly-ant compound optimization (FaCO) algorithm for the weighted fusion of two optimization rules of the firefly and ant colony algorithm. For the graph, results after multi-level graph partitioning are transformed into a traveling salesman problem (TSP). This algorithm is used to optimize the load distribution of the solution, and finally, the rough graph segmentation is projected to obtain the most original segmentation optimization results. Although firefly algorithm (FA) and ant colony optimization (ACO), as swarm intelligence algorithms, are widely used to solve TSP problems, for the problems for which swarm intelligence algorithms easily fall into local optimization and low search accuracy, the improvement of the FaCO algorithm adjusts the weight of iterative location selection and updates the location. Experimental results on publicly available datasets such as the Oliver30 dataset and the eil51 dataset demonstrated the effectiveness of the FaCO algorithm. It is also significantly better than the commonly used firefly algorithm and other algorithms in terms of the search results and efficiency and achieves better results in optimizing the load-balancing problem of parallel computing.

/pdf/load-balancing-based-on-firefly-and-ant-colony-optimization-3gz2yrij.pdf

Load Balancing Based on Firefly and Ant Colony Optimization Algorithms for Parallel Computing

With the existing power SDN network architecture, the improved switches migration algorithm is put forward. Through the advantages of the ant colony algorithm and genetic algorithm fusion, the migration process is optimized, and the fusion algorithm in switches uses the operation, such as restrictions in advance and pruning algorithm efficiency to eventually apply migration under multiple controllers to the switch. The efficiency and stability of switch migration under multicontroller are improved, and the performance of the RYU controller is compared with other algorithms. The results of the algorithm and performance comparison test show that the improved ant colony algorithm is reduced by 12.5% and 1.5%, which is a comparison of response delay; the accuracy of the migration operation of the algorithm can make full use of the resources of the controller and achieve the purpose of improving the migration efficiency and load balancing among multiple controllers.

Load Balancing of SDN Controller for Migration Optimization Based on Metaheuristics

The design parameters of heat pumps are related to each other nonlinearly or in a complicated manner; therefore, it is difficult to determine the optimal combination of design parameters, such as superheat, subcooling, and refrigerant type, analytically. To address this limitation, three representative heuristic algorithms, namely the genetic algorithm (GA), particle swarm optimization (PSO), and simulated annealing (SA), are applied to optimize a heat pump under the given process conditions. Heuristic algorithms are driven based on randomness; thus, the consistency of the calculation results and computational time represent the decision criteria for the appropriate optimizer. The GA is unsuitable as a heat pump optimizer because it requires an excessive number of iterations. In contrast, PSO and SA have a similar capability of consistency and calculation time with a rational number of iterations. In conclusion, PSO exhibits a slightly better consistency and use of computational resources; therefore, PSO is selected as the heat pump design optimization algorithm in this study. The novelty of this work lies in that the related design parameters of the heat pump are simultaneously globally optimized with minimal physical background, and the heuristic algorithm that is most applicable to heat pump design optimization is determined.

Bong Seong Oh

Papers

Application of Heuristic Algorithms for Design Optimization of Industrial Heat Pump