


Tsinghua University won the fifth power dispatching AI application competition with perfect scores and the competition ended successfully!
The power market clearing speed has set a new record. On December 27, China Southern Power Grid’s fifth power dispatching AI application competition concluded successfully in Guangzhou. The Tsinghua University team won the championship with a perfect score. Relying on "cloud + AI" technology, the overall clearing process was controlled within 600 seconds, improving efficiency by nearly 50%.
When supply and demand are balanced, it is called clearing. With the further advancement of power market transactions, new entities such as photovoltaics, energy storage and virtual power plants have joined in. How to quickly clear electricity as a commodity has attracted much attention in the industry.
In July 2022, the southern regional power market led by China Southern Power Grid was officially launched, becoming the first regional market in the country to be put into trial operation. Currently, 160,000 trading entities conduct power spot transactions on the platform, achieving free and real-time transactions. However, due to the large scale of clearing, complex constraints, and numerous variables, the power grid faces many new challenges in terms of clearing time and operating costs with the acceleration of the marketization process and technological advancement.
On November 14, 2023, China Southern Power Grid held the 5th Power Dispatch AI Application Competition. The theme was rapid clearing of the power spot market based on artificial intelligence. This competition attracted 30 teams from the power industry across the country, including scientific research institutions, universities and Internet ecological enterprises.
Liu Yingshang, deputy chief engineer of China Southern Power Grid Corporation and secretary of the Party Committee of China Southern Power Grid General Investigation Committee, said that in recent years, general large models of artificial intelligence have continued to emerge, forming a pattern in which a hundred flowers bloom. The innovative inspiration displayed by the contestants in the competition is gradually promoting the development of the power "dispatch AI" ecosystem. China Southern Power Grid will continue to uphold technological innovation thinking, give full play to the leading role of artificial intelligence, lead industrial transformation and upgrading, give full play to the role of the national team, adhere to innovation leadership, and further promote digital transformation and digital grid construction.
According to reports, the competition environment of this competition is provided by the scheduling cloud master node and the same city node. Among the six teams that entered the finals, four teams were developed using master nodes, accounting for 66%.
Nanwang Scheduling Cloud was put into production and operation in August 2019. It is based on the Alibaba Cloud Feitian operating system. As the first large-scale industrial cloud built in the national power industry at that time, it was able to expand computing resources in seconds. In the past four years, China Southern Network Dispatching Cloud has been supporting the stable and efficient operation of more than 200 business systems of China Southern Network, and has become a solid foundation for AI innovation.
Wang Zhengcheng, a member of the Tsinghua University team, said: "The overall user experience of the Nanwang Scheduling Cloud Platform is relatively smooth. There is a big difference between development in the cloud environment and scientific research in the laboratory environment, because it is difficult for laboratory servers to be elastic. Expansion and contraction: Although the computing and storage resources currently allocated to each participating team in the South China Open are limited, if large-scale training is to be done, you can quickly apply for expansion."
In order to simulate the actual clearing problem, China Southern Power Grid provides processed power grid data of thousands of generators for 30 days. Another participant, Zeng Hongtai, believes that solving the clearing problem is actually a mixed integer linear programming problem, and the key lies in using AI to determine integer variables.
On the MindOpt Studio AI platform, researchers from Alibaba DAMO Academy have developed an auxiliary programming capability. This capability can help the Tsinghua University team save a lot of time, no longer needing to spend time reading and importing data. Instead, they can focus their efforts on algorithmic innovation.
In the end, the Tsinghua University team won the championship with two perfect scores: "time average score" and "cost average score". They successfully controlled the overall clearing time to about 600 seconds and increased the clearing efficiency by nearly 50%. This fully proves the feasibility of AI to accelerate market clearing.
At present, the national power system is transforming and developing towards a new power system. As new energy photovoltaic and wind power installations continue to increase, the future power system will become rapidly volatile. Traditional dispatching methods are difficult to adapt to the operating characteristics of new power systems in the future. Faced with this rapidly changing system, technology in the power field is moving towards the integration and development of "cloud AI".
Yin Wotao, head of the Decision Intelligence Laboratory of Alibaba Damo Academy, said that the combination of AI and mathematical solving technology is driving changes in the field of new energy power dispatching. The application of dual decision engines has greatly improved the operating efficiency and reliability of the power system, and provided new technical support for intelligent green energy management. In the future, the cloud AI model will continue to promote the power industry to develop in a green, sustainable and intelligent direction.
The China Southern Power Grid Dispatching AI Application Competition is currently the most influential and most applicable AI competition in the power industry. It is hosted by the China Southern Power Grid Power Dispatching Control Center and the China Electrical Engineering Society's Power System Automation Committee.
China Southern Power Grid has always attached great importance to the application of cloud computing and AI technology in the power industry. The past four competitions have focused on AI and revolved around topics such as load forecasting and scheduling optimization decision-making. With the innovative results of previous competitions, China Southern Power Grid has realized AI load forecasting for single-track operation of the entire network and cultivated a flexible and open new energy power forecasting value ecosystem.
The above is the detailed content of Tsinghua University won the fifth power dispatching AI application competition with perfect scores and the competition ended successfully!. For more information, please follow other related articles on the PHP Chinese website!

The unchecked internal deployment of advanced AI systems poses significant risks, according to a new report from Apollo Research. This lack of oversight, prevalent among major AI firms, allows for potential catastrophic outcomes, ranging from uncont

Traditional lie detectors are outdated. Relying on the pointer connected by the wristband, a lie detector that prints out the subject's vital signs and physical reactions is not accurate in identifying lies. This is why lie detection results are not usually adopted by the court, although it has led to many innocent people being jailed. In contrast, artificial intelligence is a powerful data engine, and its working principle is to observe all aspects. This means that scientists can apply artificial intelligence to applications seeking truth through a variety of ways. One approach is to analyze the vital sign responses of the person being interrogated like a lie detector, but with a more detailed and precise comparative analysis. Another approach is to use linguistic markup to analyze what people actually say and use logic and reasoning. As the saying goes, one lie breeds another lie, and eventually

The aerospace industry, a pioneer of innovation, is leveraging AI to tackle its most intricate challenges. Modern aviation's increasing complexity necessitates AI's automation and real-time intelligence capabilities for enhanced safety, reduced oper

The rapid development of robotics has brought us a fascinating case study. The N2 robot from Noetix weighs over 40 pounds and is 3 feet tall and is said to be able to backflip. Unitree's G1 robot weighs about twice the size of the N2 and is about 4 feet tall. There are also many smaller humanoid robots participating in the competition, and there is even a robot that is driven forward by a fan. Data interpretation The half marathon attracted more than 12,000 spectators, but only 21 humanoid robots participated. Although the government pointed out that the participating robots conducted "intensive training" before the competition, not all robots completed the entire competition. Champion - Tiangong Ult developed by Beijing Humanoid Robot Innovation Center

Artificial intelligence, in its current form, isn't truly intelligent; it's adept at mimicking and refining existing data. We're not creating artificial intelligence, but rather artificial inference—machines that process information, while humans su

A report found that an updated interface was hidden in the code for Google Photos Android version 7.26, and each time you view a photo, a row of newly detected face thumbnails are displayed at the bottom of the screen. The new facial thumbnails are missing name tags, so I suspect you need to click on them individually to see more information about each detected person. For now, this feature provides no information other than those people that Google Photos has found in your images. This feature is not available yet, so we don't know how Google will use it accurately. Google can use thumbnails to speed up finding more photos of selected people, or may be used for other purposes, such as selecting the individual to edit. Let's wait and see. As for now

Reinforcement finetuning has shaken up AI development by teaching models to adjust based on human feedback. It blends supervised learning foundations with reward-based updates to make them safer, more accurate, and genuinely help

Scientists have extensively studied human and simpler neural networks (like those in C. elegans) to understand their functionality. However, a crucial question arises: how do we adapt our own neural networks to work effectively alongside novel AI s


Hot AI Tools

Undresser.AI Undress
AI-powered app for creating realistic nude photos

AI Clothes Remover
Online AI tool for removing clothes from photos.

Undress AI Tool
Undress images for free

Clothoff.io
AI clothes remover

Video Face Swap
Swap faces in any video effortlessly with our completely free AI face swap tool!

Hot Article

Hot Tools

SecLists
SecLists is the ultimate security tester's companion. It is a collection of various types of lists that are frequently used during security assessments, all in one place. SecLists helps make security testing more efficient and productive by conveniently providing all the lists a security tester might need. List types include usernames, passwords, URLs, fuzzing payloads, sensitive data patterns, web shells, and more. The tester can simply pull this repository onto a new test machine and he will have access to every type of list he needs.

WebStorm Mac version
Useful JavaScript development tools

SublimeText3 Mac version
God-level code editing software (SublimeText3)

Dreamweaver Mac version
Visual web development tools

Atom editor mac version download
The most popular open source editor
