A research project at Waseda University in Japan has offered a way to use artificial intelligence (AI) to predict wireless conditions in advance and proactively adjust transmission settings for more reliable video delivery.
Explaining the rationale for the study, the research team at Waseda – led by Jiro Katto and PhD candidate Kasidis Arunruangsirilert – say they have developed a lightweight AI model that predicts wireless conditions before they deteriorate, adjusting transmission settings accordingly.
Outlining the background of their work, the researchers noted that cable television (CATV) remains a cornerstone of how national broadcasts and emergency information reach thousands of households. Yet they suggested that since many older buildings were not built with fibre optics in mind, retrofitting them with the necessary wiring for CATV is too costly or impractical, leaving residents unable to access broadcast services.
The emerging candidate technology to address this is 5G multicast and broadcast services (MBS), a 3GPP-standardised technology introduced in Release 17 that enables native point-to-multipoint data delivery over 5G new radio (NR) networks. It uses 5G wireless signals to deliver the same television stream to many households simultaneously. By making efficient use of the limited radio spectrum, it offers a realistic path to modernising CATV infrastructure.
However, the researchers stressed that 5G multicast broadcasting has a fundamental limitation. Ordinary 5G connections on smartphones are two-way, so when a data packet fails to arrive, the receiving device can simply request retransmission. Multicast broadcasting may not support such return channels, which means lost data packets cannot be resent, causing the video stream to freeze momentarily.
The research team believes conventional 5G communication protocols, designed around retransmission requests and maximising speed, are not built to handle situations where retransmission is limited.
The AI model they created is designed to predict wireless conditions in advance and proactively adjust transmission settings, enabling stable, real-time video delivery via 5G broadcasting. In addition to improving quality of service in general, the researchers claimed that their approach could help enable more reliable delivery of high-definition television over local 5G networks, particularly where installing fibre-optic cables is impractical, and bridge information gaps in underserved areas.
The AI model was trained using approximately 26 million measurements collected every 0.5 milliseconds from a commercial 5G network, enabling it to capture rapid fluctuations in radio conditions that coarse datasets miss. It relied on information already collected by smartphones during standard operation, and is compact enough to run in real time on consumer devices without requiring specialised hardware.
Tests on a real-world commercial 5G network showed that the AI model selected an error-free transmission setting for approximately 87% of video segments, compared with only 32% for a conventional speed-oriented approach. The model also operated in less than 0.07 milliseconds on smartphone chipsets released from 2020 onward, introducing no perceptible delay to viewers.
“Our study stands as a practical example of AI-native wireless communication, in which AI takes on decision-making responsibilities in next-generation networks, and represents a meaningful step toward the long-sought convergence of broadcasting and broadband on a single, spectrally efficient wireless platform,” said the research team.
Beyond improving television services, the researchers believe the same approach could benefit many forms of one-way wireless communication where retransmission is impossible, including satellite communications, autonomous vehicles, scientific exploration and industrial systems.
“Our study stands as a practical example of AI-native wireless communication, in which AI takes on decision-making responsibilities in next-generation networks, and represents a meaningful step toward the long-sought convergence of broadcasting and broadband on a single, spectrally efficient wireless platform,” said Katto.
