Shulou(Shulou.com)06/02 Report--

AI and 5G Technology help Smart Grid meet Security Challenge

The main contents of this paper are as follows:

Smart grid technologies such as microgrids, generators and solar panels could help curb climate change and help consumers better control their energy consumption. Smart grid technology creates two-way data flow, which leads to new network security challenges. Artificial intelligence, 5G and other technologies are ready to meet these challenges, but the energy industry must continue to invest to stay ahead of cyber attacks.

For the energy industry, ensuring the security of the power grid is very important.

Nowadays, it is becoming more and more important to protect the security of networked devices, especially edge devices. However, zero-trust network security, 5G connectivity and machine learning may eventually help the "smart grid" become more resilient in the face of attacks.

While the shift to sustainable energy can help ensure a better future for the planet and reduce its carbon footprint, smart grids generate two-way risk data streams, adding complexity.

Brian Crow, vice president of analytical solutions at Sensus, said in a recent article on the role of the Internet of things in utilities that smart grid technology can balance peak demand, flatten load curves and make energy generation more efficient.

Malicious attackers can take advantage of these two-way streams.

Christine Hertzog, the main technical director of the Power Research Institute, said the marginal devices had "potential to affect the reliability of the grid." Malicious participants can target the grid and can "change the load in a dramatic way, and then you will see some problems with the reliability of the grid," she said. "

Distributed energy, smart grid acceleration

New energy and distribution # methods (including solar panels, generators and microgrids) show the prospect of curbing climate change and helping consumers better control energy consumption during peak hours.

Smart grid technology decentralizes energy transmission, enabling people to quickly connect to or disconnect from larger grids, and generate and transmit electricity locally. Unlike today's huge centralized power grids, for example, attacks or damage to microgrids will not affect the entire system. This is important in areas like California, where fires can cause spontaneous power grids to shut down.

However, the smart grid will also create unstable demand for the larger grid and provide two-way flow to the grid, thus bringing security risks. Ageing energy infrastructure exacerbates these risks.

Distributed energy production, whose components are used in smart grids, is growing. The International Energy Agency (International Energy Agency) predicts that renewable energy generation will grow by 50 per cent by 2024, with solar photovoltaic and onshore wind power accounting for the largest share of this growth.

"the world is moving towards a paradigm that relies on on-site power, whether it's solar energy, backup generators or other equipment," said Peter Asmus, chief research analyst at Navigant Research.

"the world is moving away from large, centralized resources to look more like telecommunications," Asmus said. He pointed out that although some deployments have slowed down due to the coronavirus, he expects the growth of distributed energy to accelerate in the coming years.

The edge of the grid brings complexity to the outdated power grid.

The traditional energy grid itself lags behind these modern developments. According to the U.S. Department of Energy, 70% of the grid's transmission lines and transformers have a service life of more than 25 years, and the average service life of power plants has exceeded 30 years. Some parts of the American power grid have a history of more than a hundred years.

Technologies such as Internet of things (IoT) devices, edge computing architectures and machine learning will modernize the grid. Examples include IoT-enabled backup generators that provide additional power to homes, electric vehicle charging stations or connected thermostats. These technologies are rapidly becoming the expansion of the traditional power grid.

According to the "Internet of things in the Energy Market" report, the global energy Internet of things market is expected to grow from $20.2 billion in 2020 to $35.2 billion in 2025, with a compound annual growth rate of 11.8 per cent over the forecast period.

Just as connected devices are part of this equation, so is the edge architecture.

The edge computing architecture brings computing and data closer to the devices and users that need them to reduce response time and reduce bandwidth requirements. Countless devices have emerged and reside at the edge rather than in the cloud, and traditional models require a round trip from the device to the cloud to the cloud, increasing bandwidth requirements, increasing response time, and potentially posing security concerns.

"this is what we call the edge of the grid," Hertzog said. "it's a paradigm shift." "We used to think about cyber security like the concept of a fortress: there has to be a boundary. But when you talk about the advantages of power grids and cloud-based applications, you are touting this concept."

Grid edge architecture increases the risk and complexity of power grid. Edge devices may not be patched and updated frequently, strict authentication protocols may not be applied, networks may be shared with other critical IT systems and targeted for penetration, or they may contain code that is easy and impermeable to write and become the target of malicious attackers.

Such security risks have been amplified as utilities turn to the Internet of things for better grid management and consumers take advantage of edge devices such as connected meters and home charging stations for electric vehicles. As a result, security vulnerabilities can now be two-way, so that the power grid can be infiltrated not only through its own network but also through user equipment connected to the grid.

In order to solve the security problem, enterprises are implementing a private network for the Internet of things. In a recent Omdia survey on the adoption of the Internet of things, 97% of respondents said they had considered or were using private networks to deploy the Internet of things to enhance security.

Artificial Intelligence, Zero Trust Network Security

A potential response to these risks is the emergence of machine learning and AI-enabled tools that support IT professionals. Machine learning tools can identify threats in a large number of alerts that IT professionals may receive. AI-enabled network security tools are becoming the key to edge security because humans simply cannot keep up with all the information.

"large-scale data is beyond the capacity of the human brain," Hertzog said. " "We have access to more additional information through new tools and features, but the ability to absorb and understand that information will be a huge challenge."

Companies such as State Grid Partners (National Grid Partners) have applied AI to network security monitoring and expect automation for other tasks, such as predictive maintenance and customer service.

Hertzog says artificial intelligence is crucial for authentication at the edge, which requires a zero-trust network security policy. The basic principle of zero trust is never trust, always verify.

Hertzog pointed out that this method of network security requires intelligence at the edge to achieve authentication. "We need distributed intelligence to reduce zero trust to a fine level," she said. " "artificial intelligence will participate in viewing all activities and see if there are any exceptions."

"We can get this data and provide a basis for our decisions," Hertzog said. She stressed that the real AI for this application may be far away, but automatic monitoring is already in place.

However, Hertzog also points out that decision-making can only be automated if the exported data is accurate, clean, and available.

Hertzog pointed out that poor data quality is an urgent reason for public utilities to put their work into data management to achieve network security. "Research shows that about 80 per cent of the time spent on projects involving AI is translating the data into the correct format and simply preparing to use it for AI."

Artificial intelligence will also require higher speed and network slicing, allowing the network to be partitioned to provide different levels of access to the grid to enable fine security policy settings. Such fine-grained policies are needed to protect these distributed networks.

Hertzog et al. pointed out that inevitable technologies such as 5G connectivity, a new wireless standard, can enhance zero-trust security by providing network bandwidth to achieve the speed and data strength required for edge intelligent activities.

"5G changes the rules of the game," Hertzog said. "this will support the concept of sliced networks and allow for finer definition of security policies. This has some impact on zero trust."

At the same time, Hertzog said that while 5G will enhance smart grid security, the required infrastructure will not emerge tomorrow. It will even take ten years to launch.

[recommended by editors]

The 2020 World artificial Intelligence Congress is coming! See how AI grasps the commanding heights of human language! Marginal artificial intelligence helps to enhance the advantages of the Internet of things to join the "new infrastructure"-- how does Baode empower artificial intelligence artificial intelligence, the Internet of things and big data save the honeybee industry observation: how on earth has the development of artificial intelligence in the world reached?

Https://ai.51cto.com/art/202007/621378.htm

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.