<scp>COSCO2</scp>: <scp>AI</scp>‐augmented evolutionary algorithm based workload prediction framework for sustainable cloud data centers

Karthikeyan, R.; Balamurugan, V.; Cyriac, Robin; Sundaravadivazhagan, B.

doi:10.1002/ett.4652

Cited by 11 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To ensure the long-term viability of cloud data centers, Karthikeyan et al [18] present a tree-structured tree hierarchical deep convolutional neural network (T-CNN) tuned with a sheep flock based on workload data. In the first stage, the kernel correlation technique is used to preprocess the available cloud data center historical data.…”

Section: Literature Reviewmentioning

confidence: 99%

CSO-based Efficient Resource Management for Sustainable Cloud Computing

Shanmugam,

Rajasekhar

2024

Contemp. Math.

View full text Add to dashboard Cite

The pervasive need for cloud-hosted application services has resulted from the widespread use of cloud data centers. Not only that, but there has been a dramatic increase in the resource demands of current applications, especially in data-intensive businesses. This has resulted in an increase in the number of cloud servers made available, which has increased energy usage and prompted environmental concerns. Only partially do the difficulties of scalability and adaptability in cloud resource management get addressed by conventional heuristics and reinforcement learning-based techniques. Many existing works overlook the interdependencies between host temperature, task resource usage, and scheduling decisions. Especially in contexts with fluctuating resource demands, this results in poor scalability and an upsurge in computing resource requirements. The study recommended a holistic resource management strategy based on resource scheduling for enduring cloud computing as a solution to these restrictions. Energy, thermal, and cooling models are all taken into account in the proposed model, which expresses the optimization of data center energy efficiency as a multi-objective scheduling issue. To generate optimal scheduling decisions and approximate the quality of service (QoS) for a given system state, the model employs cat-based swarm optimization as a surrogate model. Using the China Ocean Shipping Company (COSCO) framework, we conducted experiments that demonstrate cloud service orchestrator (CSO)’s superior performance compared to state-of-the-art baselines in terms of energy ingesting, makespan, and execution overhead in both simulated and real-world cloud environments.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

CSO-based Efficient Resource Management for Sustainable Cloud Computing

Shanmugam,

Rajasekhar

2024

Contemp. Math.

View full text Add to dashboard Cite

show abstract

“…Since the suggested technique calls for subterranean transmission operations, it is crucial to offer a powerful optical network-based data handling system. Thus, the General Adversarial Network (GAN), one of the most potent artificial intelligence (AI) algorithms, is integrated and adds some input noise to the data (Balamurugan et al, 2022;Karthikeyan et al, 2022;Onyema et al, 2022). The main benefit of GAN in optical communication is the ability to frame a new kind of optical vision for all kinds of energy sources.…”

Section: Optimization Algorithmmentioning

confidence: 99%

Mathematical approach of fiber optics for renewable energy sources using general adversarial networks

Hasanin

Manoharan²,

Alterazi³

et al. 2023

Front. Ecol. Evol.

View full text Add to dashboard Cite

It is significantly more challenging to extend the visibility factor to a higher depth during the development phase of a communication system for subterranean places. Even if there are numerous optical fiber systems that provide the right energy sources for intended panels, the visibility parameter is not optimized past a certain point. Therefore, the suggested method looks at the properties of a fiber optic communication system that is integrated with a certain energy source while having external panels. A regulating state is established in addition to characteristic analysis by minimizing the reflection index, and the integration of the general adversarial network (GAN) optimizes both central and layer formations in exterior panels. Thus, the suggested technique uses the external noise factor to provide relevant data to the control center via fiber optic shackles. As a result, the normalized error is smaller, boosting the suggested method's effectiveness in all subsurface areas. The created mathematical model is divided into five different situations, and the results are simulated using MATLAB to test the effectiveness of the anticipated strategy. Additionally, comparisons are done for each of the five scenarios, and it is found that the proposed fiber-optic method for energy sources is far more effective than current methodologies.

show abstract

“…At present, the urban heat island effect has become one of the common environmental problems in the world. The urban heat island phenomenon has not only brought many adverse effects to the urban environment, but also brought significant harm in aggravating climate change, increasing air pollution and affecting human health [ 5 , 6 ].…”

Section: Introductionmentioning

confidence: 99%

How to use BAPV to alleviate the urban heat island effect: An evolutionary game perspective

Fu,

Xie

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

In recent years, the phenomenon of the urban heat island caused by the rapid development of cities is very serious. To solve the problem of the urban heat island, this study proposed a PPP project consisting of the government (GOVT), photovoltaic investment company (PVIC), and residential customers (RS). Based on an evolutionary game model and combined with current policies and industry regulations in China, the evolution process and stable evolution strategies were studied. The result shows that more government subsidies, higher carbon trading prices, and feed-in tariffs will promote the development of the PPP project. For relatively suitable reference value ranges, the installation tilt angle of the BAPV system is 30°, the photovoltaic grid electricity price is 0.1096∼0.1296 $/kWh, the carbon trading is 8.92∼9.42 $/t.

show abstract

COSCO2: AI‐augmented evolutionary algorithm based workload prediction framework for sustainable cloud data centers

Cited by 11 publications

References 34 publications

CSO-based Efficient Resource Management for Sustainable Cloud Computing

CSO-based Efficient Resource Management for Sustainable Cloud Computing

Mathematical approach of fiber optics for renewable energy sources using general adversarial networks

How to use BAPV to alleviate the urban heat island effect: An evolutionary game perspective

Contact Info

Product

Resources

About