Abstract: Intelligent process management is provided. A start time is determined for an additional process to be run on a worker node within a duration of a sleep state of a task of a process already running on the worker node by adding a first defined buffer time to a determined start time of the sleep state of the task. A backfill time is determined for the additional process by subtracting a second defined buffer time from a determined end time of the sleep state of the task. A scheduling plan is generated for the additional process based on the start time and the backfill time corresponding to the additional process. The scheduling plan is executed to run the additional process on the worker node according to the start time and the backfill time corresponding to the additional process.

Abstract: Embodiments of this application provide a method and an apparatus for determining radio channel multipath information and a related device. A server obtains reference signal received powers of a plurality of downlink beams, and determines a path angle and path strength of a propagation path from an antenna in a power angular spectrum cell indicated by each power angular spectrum cell identity to a grid indicated by each grid identity, based on an association relationship between the reference signal received powers of the plurality of downlink beams and the following: a grid identity, a serving cell identity, and a power angular spectrum cell. The server can determine the radio channel multipath information based on the reference signal received powers of the plurality of downlink beams, instead of depending on map and engineering parameter information. This helps improve accuracy of the radio channel multipath information.

Abstract: A method for poetry generation includes receiving generation information indicative of a theme for the poetry generation, and determining at least a candidate piece of poetry corresponding to the generation information according to an autoregressive language model that is configured to generate elements in the candidate piece of poetry in an autoregressive manner with a plurality of regression rounds. An element in the elements is a character or a word. The autoregressive language model is configured for generating poetry in a plurality of formats, the autoregressive language model includes a plurality of processing layers connected sequentially, a processing layer in the plurality of processing layers is configured to determine attention levels for potential elements in a potential element list according to generated elements prior to a current regression round, and predict one or more additional element for the current regression round using a neural network according to the attention levels.

Abstract: Data storage of workloads is migrated from a local computing environment to a cloud computing environment. The workloads are first executed in a runtime environment that have been deployed within a first virtual machine running in the local computing environment, according to a blueprint that defines a data storage path for the workloads. The data storage of the workloads is migrated by copying contents of a first file, which corresponds to a virtual disk of the first virtual machine, to a second file, modifying the blueprint to change the data storage path to a path that specifies a file path to the second file, and deploying a runtime environment within a second virtual machine running in the cloud computing environment, according to the modified blueprint. After transitioning the data storage of the workloads in this manner, the workloads are executed in the runtime environment deployed within the second virtual machine.

Abstract: Data storage of workloads is migrated from a local computing environment to a cloud computing environment. The workloads are first executed in a runtime environment that have been deployed within a first virtual machine running in the local computing environment, according to a blueprint that defines a data storage path for the workloads. The data storage of the workloads is migrated by copying contents of a first file, which corresponds to a virtual disk of the first virtual machine, to a second file, modifying the blueprint to change the data storage path to a path that specifies a file path to the second file, and deploying a runtime environment within a second virtual machine running in the cloud computing environment, according to the modified blueprint. After transitioning the data storage of the workloads in this manner, the workloads are executed in the runtime environment deployed within the second virtual machine.

Abstract: In the field of computer vision, without sufficient labeled images, it is challenging to train an accurate model. But through visual adaptation from source to target domains, a relevant labeled dataset can help solve such problem. Many methods apply adversarial learning to diminish cross-domain distribution difference. They are able to greatly enhance the performance on target classification tasks. GAN (Generative Adversarial Networks) loss is widely used in adversarial adaptation learning methods to reduce a across-domain distribution difference. However, it becomes difficult to decline such distribution difference if generator or discriminator in GAN fails to work as expected and degrades its performance. To solve such cross-domain classification problems, an adaptation algorithm and system called as Generative Adversarial Distribution Matching (GADM) is implemented.

Abstract: To ensure photovoltaic (PV) panels at a PV plant constantly operate in an ideal state, an unsupervised system and method of intelligent performance evaluation and data-driven fault detection is used. The system and method enables engineers to check PV panels in time and implement timely maintenance. Monitored data are classified into three subsets: ideal period A, transition period S, and downturn period B. Based on A and B data, two regression prediction models are built which are tree-based and fit the non-continuous PV data well. Real-time measured power is compared with upper and lower reference baselines derived from the two predictive models, respectively. Using threshold ranges, the system and method achieves the instantaneous performance monitoring of PV power generation, and provides failure identification and operation and maintenance (O&M) suggestions to engineers.

Abstract: Systems and techniques are described for optimizing memory sharing. A described technique includes grouping virtual machines (VMs) into groups including a first group; initializing a first VM in the first group, wherein initializing the first VM includes identifying, for each of one or more first memory pages for the first VM, a respective base address for storing the first memory page using an address randomization technique, and storing, for each of the one or more first memory pages, data associating the first memory page with the respective base address for the first group, and initializing a second VM while the first VM is active, wherein initializing the second VM includes determining that the second VM is a member of the first group, and in response, storing one or more second memory pages for the second VM using the respective base addresses stored for the first group.

Abstract: Soft sensing of nonlinear and multimode industrial processes given a limited number of labeled data samples is disclosed. Methods include a semi-supervised probabilistic density-based regression approach, called Semi-supervised Weighted Gaussian Regression (SWGR). In SWGR, different weights are assigned to each training sample based on their similarities to a query sample. Then a local weighted Gaussian density is built for capturing the joint probability of historical samples around the query sample. The training process of parameters in SWGR incorporates both labeled and unlabeled data samples via a maximum likelihood estimation algorithm. In this way, the soft sensor model is able to approximate the nonlinear mechanics of input and output variables and remedy the insufficiency of labeled samples. At last, the output prediction as well as the uncertainty of prediction can be obtained by the conditional distribution.

Abstract: A continuous microwave freeze-drying device comprises a vacuum water-trapping system (1), a microwave shield plate (2), a microwave bin (6) and a freeze-drying bin (5) located in the microwave bin (6), wherein the freeze-drying bin (5) comprises an upper bin opening, a left bin wall, a right bin wall and a bottom bin wall, and the left, right and bottom bin walls are all made from nonmetal wave transmitting materials, such as polyfluortetraethylene, polyethylene, polypropylene or quartz glass. The device solves the technical problem of freeze-drying failure caused by glow discharge of microwave under freeze-drying environment.

Abstract: Systems and techniques are described for optimizing memory sharing. A described technique includes grouping virtual machines (VMs) into groups including a first group; initializing a first VM in the first group, wherein initializing the first VM includes identifying, for each of one or more first memory pages for the first VM, a respective base address for storing the first memory page using an address randomization technique, and storing, for each of the one or more first memory pages, data associating the first memory page with the respective base address for the first group, and initializing a second VM while the first VM is active, wherein initializing the second VM includes determining that the second VM is a member of the first group, and in response, storing one or more second memory pages for the second VM using the respective base addresses stored for the first group.

Abstract: A continuous microwave freeze-drying device comprises a vacuum water-trapping system (1), a microwave shield plate (2), a microwave bin (6) and a freeze-drying bin (5) located in the microwave bin (6), wherein the freeze-drying bin (5) comprises an upper bin opening, a left bin wall, a right bin wall and a bottom bin wall, and the left, right and bottom bin walls are all made from nonmetal wave transmitting materials, such as polyfluortetraethylene, polyethylene, polypropylene or quartz glass. The device solves the technical problem of freeze-drying failure caused by glow discharge of microwave under freeze-drying environment.