Within the last two decades, mobile wireless technology has undergone significant evolution from 3G to 4G to the advanced use cases of 5G and Industry 4.0. As a result, the design of wireless systems has become increasingly complex. To tackle this complexity, a growing number of engineers are leveraging the power of artificial intelligence (AI) to solve the challenges introduced by these modern systems.
AI is now being used to optimize call performance, manage vehicle-to-vehicle (V2V) and vehicle-to-everything (V2X) communications between autonomous cars and their environment and enable the growth of today’s modern wireless applications. With the expansion in the number and capabilities of connected devices, AI is set to play an increasingly important role in the future of wireless technology. To ensure optimal implementation, engineers must consider the key benefits and best practices for AI in wireless systems.
The Use Cases for AI for Wireless
The evolution of mobile networks to 5G has been driven by three primary use cases; the optimization of broadband network speed and quality, the demand for ultra-reliable, low latency rate communications and time-sensitive, machine-type communications between Industry 4.0 devices.
Furthermore, the growing complexity of wireless systems can be attributed to the increasing number of devices vying for the same network resources and an expanding user base. Traditional linear design patterns that were once handled by human-based rules and data processing are no longer sufficient. By contrast, AI techniques can effectively tackle non-linear problems by automatically and efficiently extracting patterns that surpass the abilities of human-based approaches.
Integrating AI in a wireless environment enables machine learning and deep learning systems to recognize patterns within communications channels. These systems then optimize the resources given to a link in order to improve performance. As applications of a modern network compete for the same resources without the use of AI methodologies, managing these networks becomes a near-impossible task.
The sophistication of AI also enables more efficient project management through features such as reduced order modeling. By incorporating simulated environments into an algorithmic model by estimating the behavior of source environments, engineers can quickly study a system’s dominant effect using minimal computational resources. This leaves more time to explore design and carry out more iterations faster, cutting time in production cycles, along with their associated costs.
Deploying AI in Wireless Systems: Best Practice
Data quality is vital for the successful and effective deployment of AI. AI models need to be trained with a comprehensive range of data to adequately deal with real-world scenarios. By synthesizing new data based on primitives or by extracting them over the air, applications like MathWorks’ 5G Toolbox1 provide the data variability necessary for 5G network designers to train AI robustly. Failure to explore a large training data set and iterate on different algorithms based on limited data could result in a narrow local optimization instead of an overall global one, compromising the reliability of AI in real-world scenarios.
A robust approach to testing AI models in the field is similarly critical to success. If signals to test AI are captured only in a narrow and localized geography, the lack of variability in that training data may negatively impact how an engineer may approach and optimize their system design. Without comprehensive field iterations, the parameters of individual cases cannot be used to optimize AI for specific locations, which will adversely impact call performance.
Embracing Digital Transformation: The Increasing Adoption of AI Across Industries
Digital transformation has been embraced across various industries, from telecommunications to automotive applications. This, in turn, has necessitated the widescale adoption of AI and is one of the primary drivers for its application. Incorporating electronic communications sensors generates large amounts of data in applications like smart homes, telecommunication networks and autonomous vehicles that rely on connectivity. The large quantity of data generated by these applications facilitates the development of future AI techniques to accelerate the process of digital transformation, yet it also stretches the resources of the joining networks.
In telecommunications, AI is deployed at the physical layer (PHY) and in above-PHY applications. The application of AI for improving call performance between two users is referred to as operating at PHY. Applications of AI techniques to PHYs include digital predistortion, channel estimation and channel resource optimization, as well as autoencoder design that spans automatic adjustments to transceiver parameters during a call.
Channel optimization is the enhancement of the connection between two devices. This applies, principally, to the network infrastructure and the user equipment or handsets. Using AI helps to overcome signal variability in localized environments through processes such as fingerprinting and channel state information compression.
With fingerprinting, AI is used to optimize positioning and localization for wireless networks by mapping disruptions to propagation patterns in indoor environments caused by individuals entering and disrupting the environment. AI then estimates the position of the user, based on these individualized 5G signal variations. In doing so, traditional obstacles associated with localization methods using comparisons between received signal strength indication and the received signal strength in providers’ databases can be overcome. Channel state information compression, on the other hand, uses AI to compress feedback data from user equipment to a base station. This ensures that the feedback loop informing the base station’s attempt to improve call performance does not exceed the available bandwidth, leading to a dropped call.
Above-PHY uses occur primarily in resource allocation and network management applications. As the number of users and use cases on the network increase exponentially, network designers are looking to AI techniques to respond to allocation demands in real-time. Applications such as beam management, spectrum allocation and scheduling function are used to optimize the management of a core system’s resources for the competing users and use cases of the network.
In the automotive industry, using AI for wireless connectivity is making safe autonomous driving possible. Autonomous vehicles and V2V/V2X vehicular communications rely on data from multiple sources, including LiDAR, radar and wireless sensors, to interpret the environment. The hardware present in autonomous vehicles must manage data from these competing sources to function effectively. AI enables sensor fusion, which in this case means merging competing signals to enable the vehicle’s software to make sense of its location and establish how it will interact with its environment by understanding omnidirectional messages. This approach to communications allows the vehicle to establish a 360-degree field of awareness of other vehicles and potential crash threats within its proximity. Whether through informing the driver of the vehicle or driving autonomously, the utilization of AI is leading to improved road traffic safety and reducing the number of crashes at intersections.
The Increasing Importance of AI in Wireless Systems Design
As the use cases for wireless technology expand, so does the need to implement AI within those systems. From 5G to autonomous vehicles to IoT, these applications would not have the sophistication necessary to function effectively without the use of AI. AI’s place in the engineering landscape, particularly wireless system design, has been growing exponentially in recent years and this pace of change can be expected to continue and even speed up as the use cases and the number of network users expand in the modern age.
Reference
- 1.5G Toolbox, MathWorks, Web: www.mathworks.com/products/5g.html.