MAG-D: A multivariate attention network based approach for cloud workload forecasting

The Coronavirus pandemic and the work-from-home have drastically changed the working style and forced us to rapidly shift towards cloud-based platforms & services for seamless functioning. The pandemic has accelerated a permanent shift in cloud migration. It is estimated that over 95% of digital workloads will reside in cloud-native platforms. Real-time workload forecasting and efficient resource management are two critical challenges for cloud service providers. As cloud workloads are highly volatile and chaotic due to their time-varying nature; thus classical machine learning-based prediction models failed to acquire accurate forecasting. Recent advances in deep learning have gained massive popularity in forecasting highly nonlinear cloud workloads; however, they failed to achieve excellent forecasting outcomes. Consequently, demands for designing more accurate forecasting algorithms exist. Therefore, in this work, we propose 'MAG-D', a Multivariate Attention and Gated recurrent unit based Deep learning approach for Cloud workload forecasting in data centers. We performed an extensive set of experiments on the Google cluster traces, and we confirm that MAG-DL exploits the long-range nonlinear dependencies of cloud workload and improves the prediction accuracy on average compared to the recent techniques applying hybrid methods using Long Short Term Memory Network (LSTM), Convolutional Neural Network (CNN), Gated Recurrent Units (GRU), and Bidirectional Long Short Term Memory Network (BiLSTM).

Energy saving potential analysis applying factory scale energy audit A case study of food production

An energy audit (EA) is a crucial step in boosting factory energy efficiency and obtaining certification for cleaner manufacturing. The results of a preliminary energy audit carried out at a sizable industrial facility in Jordan that creates some of the most well-known foods in the Middle East are presented in this study. The monthly demand of the factory for diesel ranged from 75,251.545 to 166,666.67 L. The factory energy model which is used to examine the impact of various energy-saving practices on the factory's primary energy consumption, was developed with the help of the energy audit. It has been established that optimizing the factory's energy use and the boiler systems' performance with regards to diesel consumption can withstand an expected monthly financial savings of 14205.85 Jordanian Dinar (JD). This has allowed a reduction in energy use of up to 18%. The CO₂ harmful emissions were also decreased. Additionally, it is estimated that switching from the proposed motors to energy-efficient motors will cost less overall over time, saving around 3472.314 JD/month or 0.33576/year on average. Moreover, it was discovered that a total of 772.82021 Ton CO₂/year emissions may be avoided each year.

The impact of foreign direct investment on emission reduction targets: Evidence from high- and middle-income countries

Besides bringing countries closer, the effects of globalization can help increase the production of goods and services, and foster economic growth. Foreign direct investment (FDI) is one of the processes of globalization. One aspect of globalization that has piqued the interest of economists, is the transfer of polluting industries between countries. A principal factor in this are discrepancies of environmental regulations, and these have also been instrumental in a failure to control pollution worldwide. With this impasse in mind, a Panel Autoregressive Distributed Lag was applied to evaluate the impacts of FDI on the carbon dioxide emissions of 21 countries divided by income level, for a period from 2001 to 2017. This methodology allowed the analysis of the resulting dynamics of pollution into the short-run and long-run. The characteristics of efficiency, innovation, and regulation are crucial to better understand the consequences of flows in FDI. Regulation seems to increase pollution in high-income countries, which merits further discussion. FDI decreases emissions in high-income countries, while increasing them in the short-run in middle-income countries, which supports the Pollution Haven Hypothesis. Nonetheless, the capacity of middle-income countries to absorb technology is crucial for them to benefit in the long-run. Trade openness is also highly influenced by environmental regulation in middle-income countries. Since our aim is to understand the transfer of polluting industries, an analysis of emissions from the industrial sector provided a robustness check. It also revealed that policymakers do not seem to be paying sufficient attention to innovation and controlling the environmental degradation that this sector causes.

Modelling and comparative dynamic analysis due to demagnetization of a torque controlled permanent magnet synchronous motor drive for energy-efficient electric vehicle

In this paper modelling and comparative dynamic analysis of a field oriented controlled permanent magnet synchronous motor (PMSM) torque drive employing a hysteresis current controller and a PWM (Pulse Width Modulation) operated current controller is presented. To illustrate the proposed concept in this torque controlled drive, torque and mutual flux linkages are applied as external inputs and speed of the machine is kept fixed. Moreover the magnitude of torque angle as well as stator current reference is controlled through the proposed machine dynamics. In fact a computation based on demagnetization of direct axis current to achieve the flux weakening in this proposed drive for current compensation is also introduced. To achieve the faster computation and accuracy Euler's integration technique is used to solve the proposed complex dynamics of the permanent magnet synchronous machine. In a hysteresis current, controllers with a large hysteresis band current ripple and the torque pulsations are prominent at higher carrier frequency of the inverter. Additionally, a relationship with the magnitude of torque pulsations, PWM carrier frequency and the hysteresis window size is also achieved through various case-studies. Furthermore, the presence of current ripple and the pulsations generate some noise as well as vibration in a typical electric propulsion system. Afterwards a PWM current controller with identical operating conditions is proposed for such reduction of torque pulsation as well as ripples in the current waveform. Finally various feasible results are presented through MATLAB simulation and necessary hardware implementation to justify the comparative assessment of the proposed controllers for dynamic performance analysis in energy-efficient electric vehicles.

Data in brief on CO2 absorption-desorption of aqueous-based amino acid solvents with phase change behaviour

The data presented in this paper are related to the published research article “Development of aqueous-based phase change amino acid solvents for energy-efficient CO₂ capture: The role of antisolvent” [1]. The raw and analyzed data include the equilibrium and kinetics of CO₂ absorption, the density and concentration of different CO₂-containing species at upper and lower liquid phases, and particle size distribution of solid particles precipitated during CO₂ absorption of aqueous and aqueous-based amino acid solvents. In addition, the SEM images of solid precipitates at the end of CO₂ absorption are presented. The detailed values of this phase change amino acid solvent are crucial for large-scale implementation of CO₂ capture systems with phase change behavior.

Plasmonic Glasses and Films Based on Alternative Inexpensive Materials for Blocking Infrared Radiation

The need for energy-saving materials is pressing. This Letter reports on the design of energy-saving glasses and films based on plasmonic nanocrystals that efficiently block infrared radiation. Designing such plasmonic composite glasses is nontrivial and requires taking full advantage of both material and geometrical properties of the nanoparticles. We compute the performance of solar plasmonic glasses incorporating a transparent matrix and specially shaped nanocrystals. This performance depends on the shape and material of such nanocrystals. Glasses designed with plasmonic nanoshells are shown to exhibit overall better performances as compared to nanorods and nanocups. Simultaneously, scalable synthesis of plasmonic nanoshells and nanocups is technologically feasible using gas-phase fabrication methods. The computational simulations were performed for noble metals (gold and silver) as well as for alternative plasmonic materials (aluminum, copper, and titanium nitride). Inexpensive plasmonic materials (silver, copper, aluminum, and titanium nitride) show an overall good performance in terms of the commonly used figures of merit of industrial glass windows. Together with numerical data for specific materials, this study includes a set of general rules for designing efficient plasmonic IR-blocking media. The plasmonic glasses proposed herein are good candidates for the creation of cheap optical media, to be used in energy-saving windows in warm climates' housing or temperature-sensitive infrastructure.

Hydrothermal treatment coupled with mechanical expression at increased temperature for excess sludge dewatering: influence of operating conditions and the process energetics

Dewatering is very important for excess sludge treatment and disposal. Hydrothermal treatment coupled with mechanical expression is a novel technology, in which a conventional pressure dewatering is combined with hydrothermal effect to realize an improved liquid/solids separation with low energy consumption. In this study, the process was performed by way of that the excess sludge was hydrothermally treated first and then the mechanical expression was employed immediately at increased temperature in two separate cells respectively. The results demonstrated that the mechanical expression employed at increased temperature showed a significant advantage than that at room temperature, given a further reduction of 19-47% of the moisture content. The dewatering process at room temperature was mostly depended on the effect of mechanical expression. Hydrothermal process, more importantly than mechanical effect at increased temperatures, seemed to govern the extent to which the dewatering process occurred. The dewatering began to show a positive effect when the temperature was exceeded the threshold temperature (between 120 and 150 °C). The residence time of 30 min promoted a substantial conversion in the sludge surface properties. After dewatering at temperatures of 180-210 °C, the moisture content decreased from 52 to 20% and the corresponding total water removal as filtrate was between 81 and 93%. It was observed that the moisture content of filter cake correlated with surface charge (Rp = -0.93, p < 0.05) and relative hydrophobicity (Rp = -0.99, p < 0.05). The calculated energy balance suggested that no additional external energy input is needed to support the dewatering process for excess sludge. The dewatering process needs an obviously lower energy input compared to thermal drying and electro-dewatering to produce a higher solids content cake.