WiMi Hologram Cloud Inc (WIMI)

[StockpickerCAPC]

WIMI.US develops an intelligent model LMM-VFC that supports edge migration of the virtual function chain of the next generation Internet of Things.

Source
https://finance.sina.com.cn/tech/roll/2023-03-15/doc-imykxpqz4865684.shtml

March 15, 2023

We are striding into the era of the Internet of Everything, and the development of the Internet of Things (IoT, Internet of Things) is accumulating explosive development with the advancement of science and technology and the rapid development of the Internet. The development of next-generation IoT sensing devices for the Internet of Things, along with advancements in their low-power computing capabilities and high-speed networking, has led to the introduction of edge computing.
The real-time generation of massive data will become the norm in the future society. The gradual intelligence of the equipment enables the equipment itself to have the ability to process data in real time. In the edge cloud environment, services can generate and use data locally without involving cloud computing infrastructure. Improve data processing efficiency and feedback time. WIMI (NASDAQ: WIMI) proposes to propose and evaluate an intelligent migration model based on this, which can support virtual function chains at the edge of the network based on the Internet of Things.

It is reported that WIMI (NASDAQ: WIMI) proposed an edge LMM-VFC (Virtual function chain) model, which can enable complex AI models to be executed on heterogeneous edge networks, combined with real-time QoS (Quality of Service) that triggers real-time migration. ) monitoring model, the WIMI Hologram LMM-VFC model is enhanced through the migration model.


According to the data, WIMI Holographic LMM-VFC model is a novel distributed framework, which is based on the concept of virtual function chain (VFC) of software-defined network, and supports real-time reasoning of edge AI analysis. Edge Learning Services provides support to monitor, evaluate and predict the Quality of Service (QoS) of supported services. In this model, AI analytics is decomposed into a set of virtual functions (VFs), which can be deployed on different edge devices. Using these VFs, it is possible to create a VFC that processes streaming data in a distributed manner. VFO (Virtual Function Orchestrator) is responsible for deploying VFC. VFC deploys multiple modules through the framework, optimizes design services, monitors their QoS indicators and fine-tunes their configurations to avoid failures.
More specifically, the calculation engine is responsible for proposing optimal settings for the VFC, while the edge learning service monitors the performance of edge devices and proposes possible changes. The LMM-VFC model uses this to build an intelligent model for edge migration, optimize link capabilities, and support the development of next-generation Internet of Things technologies.

In addition, WIMI's (NASDAQ: WIMI) edge LMM-VFC model supports machine learning and proposes a model based on reinforcement learning to determine the best strategy for service migration. The migration problem is usually formulated as a sequential decision problem aimed at minimizing the overall response time. The calculation migration scheme based on the reinforcement learning strategy can learn the optimal strategy of the dynamic environment in real time to ensure low computing delay.

And the WIMI holographic edge LMM-VFC model proposes a user classification mechanism based on user movement patterns to reduce decision-making complexity. A reinforcement learning-based framework is then introduced to make service migration decisions in real-time in dynamic environments. Through data-driven experiments, the efficacy of WIMI holographic edge LMM-VFC model in reducing the average delay of the system is proved. The WIMI Holographic Edge LMM-VFC model is based on the IoT mobile edge/cloud computing offloading framework for lightweight process migration. The framework does not require application binary files on the edge server, so native applications can be migrated seamlessly. The WIMI holographic edge LMM-VFC model framework shows great potential in resource-intensive IoT application processing in mobile edge/cloud computing.

In an edge cloud environment, services can generate and consume data locally without involving cloud computing infrastructure. Aiming at the problem of low computing resources of IoT nodes, WIMI proposes a virtual function chain as an intelligent distribution LMM-VFC model to maximize the use of edge computing capabilities to support demanding services. It is an intelligent migration model capable of supporting virtual function chains. According to this model, edge migration can support individual functions of the virtual function chain.
First, if a virtual function fails unexpectedly, it can be automatically repaired through cold migration.
Second, a quality-of-service monitoring model can trigger live migration, aiming to avoid overloading edge devices. An evaluation study of the proposed model demonstrates its ability to improve the robustness of edge-based services on low-power IoT devices.

The Internet of Things (IoT) is a rapidly growing field with a wide range of applications in industries such as healthcare, transportation, and agriculture. As the number of IoT devices and their associated data continues to grow, there is an increasing need for efficient and intelligent models to manage and process this data. One of the key challenges of IoT is to support edge migration of virtual function chains.

Edge migration of WIMI Holographic Edge LMM-VFC model involves moving processing tasks from centralized servers to edge devices closer to data sources, such as routers or gateways. Reduce bandwidth requirements and enable real-time processing of data. The LMM-VFC model can implement an intelligent model that supports VFC edge migration in next-generation IoT. The model will leverage machine learning to optimize VFC migration decisions based on factors such as network latency, available resources, and data privacy requirements.

WIMI's (NASDAQ: WIMI) edge LMM-VFC model can continuously monitor network conditions and data flow, and decide in real time which functions should be migrated to the edge and which functions should be kept on the centralized server. This can be achieved through a combination of rule-based and machine learning algorithms that analyze data from a variety of sources, including network performance metrics, user behavior patterns and data usage statistics.

Overall, an intelligent model that supports edge migration of virtual function chains in next-generation IoT will be a powerful tool to manage the ever-increasing volume of data generated by IoT devices. By leveraging the latest advances in artificial intelligence and machine learning, the model can help organizations optimize their data processing workflows and increase the efficiency and effectiveness of their IoT deployments.