-To cope with the increasing scale of scientific data and computational complexity of daily data, more and more cores have been integrated into GPU(Graphic Processing Units) and its working frequency is continually upgrading, which makes it being widely used in general computing for assisting CPU to accelerate program. While GPU offers powerful computing capability, the problem of the energy consumption becomes particularly prominently and it has become one of the important issues hindering development of GPU. For the purpose of solving this problem, DVFS (Dynamic Voltage Frequency Scaling) becomes an effective solution. Because the previous works only focus on single component and use linear relationship to do DVFS without considering energy saving of other units in system at software runtime, therefore we propose an energy saving model (CDVFS) of considering the characteristics of both GPU and memory at software runtime based on GA-BP (Genetic Algorithm-Back propagation) neural network to make better use of the relationship between components for energy saving. Firstly, the model assumes that functional relation between the software runtime characteristics of GPU and memory and the appropriate frequency which corresponds to the GPU and memory as nonlinear. Secondly, we extract five characteristics and use GA-BP neural network to fit the nonlinear functional relation. At last, experiments demonstrate the effectiveness of the approach and reasonableness of assumption, and also show that CDVFS can get average energy savings of 17.06% compared with previous works within acceptable performance loss.
High fail and dropout rates are the major problems in distance education. Due to a large number of online learners and limited teacher resources, it is essential to accurately identify these potential at-risk students in advance and provide timely aids, which will help to improve the educational outcome. In the online learning environment, students’ online learning behaviors can be recorded easily, with the click data being the most common one. Students’ learning behavior can reflect their learning situation and may differ among different students and periods. This paper proposed a model that uses the short-period activity characteristic and long-term changing pattern to predict the potential at-risk students. The model contains two stages: information extraction and information utilization. The first stage extracts data from the log files and organizes it in a form suitable for the model. In the second stage, according to the different characteristics of students’ short-term and long-term learning behavior, a convolution residual recurrent neural network (CRRNN) model is proposed. The convolutional neural network is used to obtain the representation of the student’s learning behavior in a certain period. Then, the residual recurrent neural network is used to get the behavior changing pattern over the periods. The experimental results indicate that the proposed model has higher performance than the three widely used baseline methods on the OULA dataset and has good practical application value for teaching and management.
The gas suspension phenomenon caused by the yield stress of the drilling fluid affects the accurate calculation of wellbore pressure after gas invasion. At present, most studies on the bubble suspension in the yield stress fluid focus on the single-bubble suspension condition and there are few studies on the gas suspension concentration. This paper carried out the GSC (gas suspension concentration) experiment in the simulated drilling fluid, xanthan solution, with different gas invasion methods. The GSC in the drilling fluid under the conditions of diffuse gas invasion and differential pressure gas invasion was simulated by using two methods of stir-depressurization and continuous ventilation. The results showed that when the size of a single bubble satisfied the single-bubble suspension condition, multiple bubbles can be suspended at the same time. The GSC is affected by the average size of the suspended bubbles, the yield stress of the drilling fluid, and the gas invasion modes. For different gas invasion modes, the empirical models of critical GSC related to the dimensionless number
Bi
are established. Compared with the experimental data, the relative error of the critical GSC in diffuse gas invasion is less than 6% and the relative error of the critical GSC in differential pressure gas invasion is less than 10%. The results of this work can provide guiding significance for accurate calculation of wellbore pressure.
In the oil industry, the drilling fluid is yield stress fluid. The gas invading the wellbore during the drilling process is distributed in the wellbore in the form of bubbles. When the buoyancy of the bubble is less than the resistance of the yield stress, the bubble will be suspended in the drilling fluid, which will lead to wellbore pressure inaccurately predicting and overflow. In this paper, the prediction model of gas limit suspension concentration under different yield stresses of drilling fluids is obtained by experiments, and the calculation method of wellbore pressure considering the influence of gas suspension under shut-in conditions is established. Based on the calculation of the basic data of a case well, the distribution of gas in different yield stress drilling fluids and the influence of gas suspension on the wellbore pressure are analyzed. The results show that with the increase of yield stress, the volume of suspended single bubbles increases, the gas suspension concentration increases, and the height at which the gas can rise is reduced. When the yield stress of drilling fluid is 2 Pa, the increment of wellhead pressure decreases by 37.1% compared with that without considering gas suspension, and when the yield stress of drilling fluid is 10Pa, the increment of wellhead pressure can decrease by 78.6%, which shows that when the yield stress of drilling fluid is different, the final stable wellhead pressure is quite different. This is of great significance for the optimization design of field overflow and kill parameters, and for the accurate calculation of wellbore pressure by considering the suspension effect of drilling fluid on the invasion gas through the shut in wellhead pressure.
Big data, cloud computing, and artificial intelligence technologies supported by heterogeneous systems are constantly changing our life and cognition of the world. At the same time, its energy consumption affects the operation cost and system reliability, and this attracts the attention of architecture designers and researchers. In order to solve the problem of energy in heterogeneous system environment, inspired by the results of 0-1 programming, a scheduling method of heuristic and greedy energy saving (HGES) approach is proposed to allocate tasks reasonably to achieve the purpose of energy saving. Firstly, all tasks are assigned to each GPU in the system, and then the tasks are divided into high-value tasks and low-value tasks by the calculated average time value and variance value of all tasks. By using the greedy method, the high-value tasks are assigned first, and then the low-value tasks are allocated. In order to verify the effectiveness and rationality of HGES, different tasks with different inputs and different comparison methods are designed and tested. The experimental results on different platforms show that the HGES has better energy saving than that of existing method and can get result faster than that of the 0-1 programming.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.