Noise Aware Scheduling in Data Centers

Spatio-temporal thermal-aware job scheduling to minimize energy consumption in virtualized heterogeneous data centers

BackgroundInformation transmission and processing in the nervous system has stochastic nature. Multiple factors contribute to neuronal trial-to-trial variability. Noise and variations are introduced by the processes at the molecular and cellular level (thermal noise, channel current noise, membrane potential variations, biochemical and diffusion noise at synapses etc). The stochastic processes are affected by different physical (temperature, electromagnetic field) and chemical (drugs) factors. The aim of this study was experimental investigation of hypotheses that increase in the noise level in the brain affects processing of visual information. Change in the noise level was introduced by an external factor producing excess noise in the brain.MethodsAn exposure to 450 MHz low-frequency modulated microwave radiation was applied to generate excess noise. Such exposure has been shown to increase diffusion, alter membrane resting potential, gating variables and intracellular Calcium efflux. Nine healthy volunteers passed the experimental protocol at the lower (without microwave) and the higher (with microwave) noise level. Two photos (visual stimuli) of unfamiliar, young male faces were presented to the subjects, one picture after another. The task was to identify later the photos from a group of six photos and to decide in which order they were presented. Each subject had a total of eight sessions at the lower and eight at the higher noise level. Each session consisted of 50 trials; altogether a subject made 800 trials, 400 at the lower and 400 at the higher noise level. Student t-test was applied for statistical evaluation of the results.ResultsCorrect recognition of both stimuli in the right order was better at the lower noise level. All the subjects under investigation showed higher numbers of right answers in trials at the lower noise level. Average number of correct answers from n=400 trials with microwave exposure was 50.3, without exposure 54.4, difference 7.5%, p<0.002. No difference between results at the lower and the higher noise level was revealed in the case of only partly correct or incorrect answers.ConclusionsOur experimental results showed that introduced excess noise reduced significantly ability of the nervous system in correct processing of visual information.

In this paper we analyze the problem of optimal task scheduling for data centers. Given the available resources and tasks, we propose a fast distributed iterative algorithm, which operates over a large scale network of nodes, and allows each of the interconnected nodes to reach agreement to an optimal solution in a finite number of time steps. More specifically, the algorithm (i) is guaranteed to converge to the exact optimal scheduling plan in a finite number of time steps and, (ii) once the goal of task scheduling is achieved, it exhibits distributed stopping capabilities (i.e., it allows the nodes to distributely determine whether they can terminate the operation of the algorithm). Furthermore, the proposed algorithm operates exclusively with quantized values (i.e., the information stored, processed and exchanged between neighboring agents is subject to deterministic uniform quantization) and relies on event-driven updates (e.g., to reduce energy consumption, communication bandwidth, network congestion, and/or processor usage). We also provide examples to illustrate the operation, performance, and potential advantages of the proposed algorithm. Finally, by using extensive empirical evaluations through simulations we show that the operation of our proposed algorithm is suitable for large scale networks such as data centers.

Communication in data centers often involves many parallel flows that all share the same performance goal. A useful abstraction, coflow, is proposed to express the communication requirements of prevalent data parallel paradigms. The multiple coflow routing and scheduling problem faces challenges when deriving a good theoretical performance ratio because coexisting coflows will compete for the same network resources such as link bandwidths. In this paper, we focus on the coflow problem in the most popular data center infrastructure: the Leaf-Spine topology. We first formulate the problem and study the path selection issue on this two-tier structure. In order to minimize the average coflow completion time (CCT), we propose a Multi- hop Coflow Routing and Scheduling strategy (MCRS) for inter-coflows and intra-coflows and prove that our method has a reasonably good competitive ratio. Extensive experiments show that MCRS outperforms other state-of- art schemes.

ABSTRACTTask scheduling algorithms for data centers must be capable of making instantaneous decisions based on the current state of the system. However, due to information limitations, these scheduling algorithms often fail to achieve optimal scheduling plans. To address the information bottleneck faced in DAG (Directed Acyclic Graph) task scheduling within data centers, this paper proposes a deep reinforcement learning scheduling model based on a DAG attention mechanism. This model utilizes the attention mechanism to capture the potential relationships between dependent tasks, thereby improving scheduling efficiency and system performance under limited information conditions. The experimental results indicate that our DAG attention mechanism can significantly reduce makespan.

Hybrid ant genetic algorithm for efficient task scheduling in cloud data centers

The deleterious effects of noise pollution on public health have been well documented, with traffic noise being identified as a significant contributor to stress and adverse impacts on the human body and mind. In this study, sound levels at 12 different points in Al-Oqailat Park in Buraydah, Saudi Arabia, were measured using a sound level meter (SLM), with the study’s primary objective being to conduct this measurement. The experimental results were then compared with perception measurements collected from users who frequently visited Al-Oqailat park. Sound measurements were taken in four different zones (A, B, C, and D) during rush hours between 1:30 p.m. and 5:20 p.m. It was found that noise levels at point A1 peaked at 79 dBA at 4:40 p.m., while the lowest level recorded was 41.1 dBA at point D2 at 2:35 p.m. The range of noise levels varied between 79 and 41 dBA, with a rate of decline of 48.10%. Zones A and B seemed to have the highest noise levels during rush hours, since they were located closest to King Fahd Road and Al-Adl Street, while zone D exhibited the lowest noise levels due to its location as a parking lot for Buraydah Court. An intermediate noise level was found in zone C, in the middle of Al-Oqailat park. The people perception results, completed by 84 park visitors, showed that zone A was identified as having exceptionally high noise levels compared to the other zones, with zone D having the lowest levels. These results were consistent with the experimental findings and reflected that the points along King Fahd Road and Al-Adl Street had the highest noise levels. Overall, the research highlighted the dominance of car traffic and horns as the primary sources of noise pollution in and around Al-Oqailat Park, emphasizing the significance of meticulous site selection for parks in urban areas.

Eventually-consistent federated scheduling for data center workloads

The government realizes that the development of micro and small enterprises is still hampered by financing that is more expensive than conventional financing. The potential of micro, small and medium enterprises in Indonesia is inseparable from banking support in lending to micro, small and medium enterprises. Access to Islamic banking is arguably still limited compared to conventional banking. This makes micro, small and medium enterprises players sometimes choose financing from conventional banks compared to Islamic financial institutions, this can be realized through continuous synergy between Islamic banks and Islamic cooperatives. Islamic cooperatives in various regions are financial inclusion locomotives to deepen sharia-based micro, small and medium enterprises in Malang. Sharia-based micro, small and medium enterprises are micro, small and medium enterprises that only want to be served by Islamic financial institutions. So that the need to empower sharia micro, small and medium enterprises is currently very important, through entrepreneurial orientation and financial inclusion it is expected that it will increase the empowerment of Sharia micro, small and medium enterprises based on Islamic boarding schools in the city of Malang. The research objective is to improve the role of Islamic Financial Inclusion and Entrepreneurship Orientation to empower Sharia micro, small and medium enterprises in Malang City. This study uses the path analysis model. And the type of data used are primary and secondary data taken from respondents, namely Sharia micro, small and medium enterprises and Sharia Cooperatives. Based on the results of the study it was explained that Financial Inclusion of Islamic Cooperatives did not influence the empowerment of micro, small and medium enterprises. While the entrepreneurial orientation affects the empowerment of Islamic micro, small and medium enterprises in Malang. If financial inclusion is carried out well, which is supported by high entrepreneurial orientation, this will increase the empowerment of micro, small and medium enterprises.

The study examined social media marketing strategies adopted by SMEs for their business survival in Delta State, Nigeria. The research population consists of all 3,976 registered SMEs with the Small and Medium Enterprises Development Agency of Nigeria, Delta State office (SMEDAN). Three hundred and ninety-eight (398) registered Small and Medium Enterprises in Delta State were used as sample which represents ten percent (10%) of the total number of registered SMEs which is in line with keilinger recommendation of sample study. A self structured questionnaire was used for data collection titled "Social Media and SMEs Questionnaire" (SMAPSMEQ). Data were analyzed using the descriptive and inferential statistics. The simple percentage, frequency count, mean and standard deviation were used to analyze the data received via research questions. Pearson Product Moment Correlation was used to test the three hypotheses. Findings shows that there exists a significant relationship between the impact of cause marketing strategy and customer’s loyalty among Small and Medium Enterprises, as an increase in the cause marketing strategy of SMES also leads to a corresponding increase in their customer’s loyalty and vice versa. A statistically significant relationship exist between the adoption of relationship marketing as social media marketing strategy and customer’s patronage among Small and Medium Enterprises in Delta State, which implies that maintaining a good relationship with its customers will have positive influence on the customer’s patronage, encourage mutual relationship, cheaper customer acquisition of Small and Medium Enterprises. Findings also shows that there exist a significant relationship between the adoption of scarcity marketing as social media marketing strategy and the volume of sales among Small and Medium Enterprises in Delta State, which means that if a good scarcity marketing strategy is maintained by a Small and Medium Enterprises, their volume of sales would also be positively affected. Based on the findings, it was recommended that small and Medium Scale Enterprises should give adequate attention to improving their cause, relationship and scarcity marketing strategies by setting up unit committees in their organization to see that these objectives are achieved. Small and Medium Enterprises Development Agency of Nigeria, Delta State office (SMEDAN) should continually encourage Small and Medium Scale Enterprises to uphold the use of these business strategies by using them as benchmark for raising the standard of their Enterprises across Delta State.&#x0D; Keywords: Social Media Marketing, SMEDAN, SMAPSMEQ, SMES, Strategies and Survival.

Occupational Noise exposure has been linked with a range of negative health effects by various researchers. The resulting injury of occupational hearing loss is also a well recognized and global problem. To protect workers from hearing damage due to noise exposure and other related health effects, a vast store of knowledge has been accumulated till date about its nature, etiology and time course. There is still ignorance, amongst majority of people working in industries in developing and third world countries including India about ill effects of exposure to high values of noise. The study being reported here has been carried out in two textile plants located in Northern Indian state of Punjab. Equivalent sound pressure level L(eq) has been measured in various sections of these plants with the help of a Class-I type digital sound level meter. The noise spectrum has been evaluated with the help of 1/3 octave filter set. A cross sectional study involving 112 workers exposed to different levels of occupational noise has been conducted. The results of the study establish the fact that noise level in certain sections of the plants i.e Loom Shed, Spinning, Ring Frame, TFO Area is more than the acceptable limit of 90 dBA for 8 h exposure stipulated by OSHA. The noise level in other sections like carding, blow room, combing etc., although is less than 90 dB(A), but is quite higher than limits used for assessment of noise for community response. Octave band analysis of the noise shows the presence of high sound level in 4,000 Hz frequency range, which can be a major reason for causing occupational hearing loss. The results of the interview questionnaire which included a number of parameters reveal the following; (i) only 29% workers are aware about the effects of noise on health (ii) 28% workers are using ear protectors (iii) the satisfaction with the working environment is related to noise level, as workers exposed to comparatively less noise level report better satisfaction (iv) 70% of the workers reported that high noise level causes speech interference (v) 42% workers report the noise to be annoying. The study thus demonstrates the presence of gross occupational noise exposure in both the plants and the author believes that occupational noise exposure and the related effects in India is a widespread problem.

Greening cloud data centers in an economical way by energy trading with power grid

Existing flow scheduling schemes in Data Center Network (DCN) are designed mainly to minimize the flow complete time (FCT) of short flows and do not consider optimizing the FCT of latency-sensitive long flows (e.g. VR video streaming, interactive artificial intelligence questiona and the information-agnostic scheme (i.e. PIAS), which is based on the premise that flow size is not known a priori, requires a central server, causing a poor scalability in large network scales. Given the limitations of existing solutions, in this paper, we propose a distributed information-agnostic flow scheduling scheme (DIAS), which minimizes the FCT of both short flows and latency-sensitive long flows. In DIAS, packets are forwarded complying with their priorities, which are determined based on packets wait-time that is defined as staying time in end hosts' send buffers, and the longer a packet stays in a send buffer, the lower its priority. Meanwhile, instead of utilizing a central server to collect traffic load information, each switch feeds traffic load information which is used to adjust the thresholds of determining packets priority back to end hosts via ACK packets. The experimental results in ns-3 simulator show that DIAS reduces FCT by up to 54.7% and 50.1 % over DCTCP and $L^{2}\mathbf{DCT}$ , respectively. Besides, DIAS ensures a smaller FCT of latency-sensitive long flows and performs better than PIAS.

In distributed computing frameworks like MapReduce, Spark, and Dyrad, a coflow is a set of flows transferring data between two stages of a job. The job cannot start its next stage unless all flows in the coflow finish. To improve the execution performance of such a job, it is crucial to reduce the completion time of a coflow, as it can contribute more than 50 percent of the job completion time. While several coflow schedulers have been proposed, we observe that routing, as a factor greatly impacting the Coflow Completion Time (CCT), has not been well considered. In this article, we focus on the coflow scheduling problem and jointly consider routing and bandwidth allocation. We begin by providing an analytical solution to the problem of optimal bandwidth allocation with pre-determined routes. In the following, we formulate the problem of scheduling a single coflow as a Non-linear Mixed Integer Programming problem and present its relaxed convex optimization problem. We further propose two algorithms, CoRBA and its simplified version: CoRBA-fast that solve the single coflow scheduling problem with a joint consideration of routing and bandwidth allocation. Lastly, to address multiple coflows in online scheduling, we propose an online scheduler named OnCoRBA. By comparing with the start-of-the-art algorithms and schedulers via simulations, we demonstrate that CoRBA and CoRBA-fast reduce the CCT by 30-400 percent and the OnCoRBA scheduler reduces the average online CCT by 20-230 percent. In addition, CoRBA-fast can be hundreds times faster than CoRBA with around 8 percent performance degradation compared to CoRBA, which makes the use of CoRBA-fast very appropriate in practice.

This chapter contains sections titled: Introduction Related Work Intermachine Scheduling Intramachine Scheduling Evaluation Conclusion References