Biao Wang

Today's Internet Services are undergoing fundamental changes and shifting to an intelligent computing era where AI is widely employed to augment services. In this context, many innovative AI algorithms, systems, and architectures are proposed, and thus the importance of benchmarking and evaluating them rises. However, modern Internet services adopt a microservice-based architecture and consist of various modules. The diversity of these modules and complexity of execution paths, the massive scale and complex hierarchy of datacenter infrastructure, the confidential issues of data sets and workloads pose great challenges to benchmarking. In this paper, we present the first industry-standard Internet service AI benchmark suite---AIBench with seventeen industry partners, including several top Internet service providers. AIBench provides a highly extensible, configurable, and flexible benchmark framework that contains loosely coupled modules. We identify sixteen prominent AI problem domains like learning to rank, each of which forms an AI component benchmark, from three most important Internet service domains: search engine, social network, and e-commerce, which is by far the most comprehensive AI benchmarking effort. On the basis of the AIBench framework, abstracting the real-world data sets and workloads from one of the top e-commerce providers, we design and implement the first end-to-end Internet service AI benchmark, which contains the primary modules in the critical paths of an industry scale application and is scalable to deploy on different cluster scales. The specifications, source code, and performance numbers are publicly available from the benchmark council web site http://www.benchcouncil.org/AIBench/index.html.

Abstract Formation pressure is the most fundamental data in oil and gas drilling and production; it has an important position in the entire cycle of oil and gas extraction. However, most current prediction methods are limited to parametric methods with fixed models; such that the accuracy does not meet requirements. This is especially true for deeper layers of marine sedimentary basins where the safety density window is extremely narrow. In this study, we propose a novel method to predict pore pressure using machine learning techniques. For the first time, the effective stress (direct output variable) was accurately predicted by a combination of four input variables (2900 sets of data, of which 90% is the training subset and 10% is the testing subset), including longitudinal velocity, porosity, mud content, and density. As such, an accurate prediction of the formation pressure was achieved based on the effective stress theorem. The performance of machine learning techniques was verified by comparing and analyzing the prediction results with traditional parametric single and multivariate models; whereby the best algorithm was chosen by structural optimization and comparative analysis of five algorithms (multilayer perceptron neural network, radial basis neural network, support vector machine, random forest, and gradient boosting machine). Compared with the methods based on parametric one‐dimensional and multivariate models, the machine learning‐based method was determined to possess high accuracy, adequate self‐adaptation, and high fault tolerance ( D 2 = 0.9981, RMSE = 0.00718 g/cm 3 ). Moreover, the multilayer perceptual neural network algorithm outperformed other machine learning algorithms in terms of goodness of fit, generalization, and prediction accuracy, with D 2 = 0.9981 and RMSE = 0.00709 g/cm 3 . The formation pressure prediction model developed in this study is not affected by the mechanical depositional environment and is applicable to sandy mudstone formations, such that it can be a useful and highly accurate alternative to the traditional formation pressure prediction methods with fixed parameter forms.

Pressure-driven water injection technology shows significant potential in addressing the key challenges of low-permeability oil reservoirs, improving water flooding development efficiency. Grounded in FDEM theory, this study establishes fluid matrix constitutive equations and employs FDEM to resolve rock stress–strain fields. A numerical simulation method for pressure-driven water injection in low-permeability reservoirs is developed to study the impact of different well pattern densities. The results indicate that the 90° horizontal well pattern using the five-spot method yields optimal outcomes, with approximately 32.32% higher cumulative liquid production than vertical well patterns. The 45° horizontal well pattern with the reversed nine-spot method also performs well, with about 30% higher cumulative liquid production than single-row vertical wells. Pressure-driven water injection improves matrix oil–water permeability and expands water flooding coverage. Based on the pressure gradient distribution driven by different well patterns, an evaluation method for the inter-well utilization capacity and its effectiveness was established. This method quantitatively assesses the reservoir depletion under various horizontal well encryption schemes. For research on timing of water injection in pressure-driven water flooding. Compared to pressure-driven water injection after 90 days, there is increased cumulative oil production after 40 days, emphasizing the importance of early pressure maintenance for higher cumulative oil production and enhanced recovery rates in low-permeability reservoir development. These findings provide crucial theoretical and practical support.

Sea surface temperature (SST) is one of the most important and widely used physical parameters for oceanography and meteorology. To obtain SST, in addition to direct measurement, remote sensing, and numerical models, a variety of data-driven models have been developed with a wealth of SST data being accumulated. As oceans are comprehensive and complex dynamic systems, the distribution and variation of SST are affected by various factors. To overcome this challenge and improve the prediction accuracy, a multi-variable long short-term memory (LSTM) model is proposed which takes wind speed and air pressure at sea level together with SST as inputs. Furthermore, two attention mechanisms are introduced to optimize the model. An interdimensional attention strategy, which is similar to the positional encoding matrix, is utilized to focus on important historical moments of multi-dimensional input; a self-attention strategy is adopted to smooth the data during the training process. Forty-three-year monthly mean SST and meteorological data from the fifth-generation ECMWF (European Centre for Medium-Range Weather Forecasts) reanalysis (ERA5) are collected to train and test the model for the sea areas around China. The performance of the model is evaluated in terms of different statistical parameters, namely the coefficient of determination, root mean squared error, mean absolute error and mean average percentage error, with a range of 0.9138–0.991, 0.3928–0.8789, 0.3213–0.6803, and 0.1067–0.2336, respectively. The prediction results indicate that it is superior to the LSTM-only model and models taking SST only as input, and confirm that our model is promising for oceanography and meteorology investigation.