The Rise of Sensor Networks and the IoT Revolution
The rapid evolution of wireless communication technologies has propelled us from the era of 4G to 5G, supporting mobile broadband, low latency, and scalable communications. The advent of 6G brings a fundamental rethinking of the purpose of radio signals and new technologies, from communications to sensing. In this context, Integrated Sensing and Communications (ISAC) emerges as a pivotal domain of research and development in the forthcoming 6G wireless networks.
ISAC promises to usher in a new era of connectivity, where communication is not limited to data transfer but extends its reach into sensing, knowledge, intelligence, and reconfiguration, thereby connecting the physical and digital worlds. Despite the great progress on its fundamentals, ISAC has often remained at low technology readiness levels, presenting challenges and barriers that need to be surmounted.
Introducing Distributed and Intelligent Integrated Sensing and Communications (DISAC)
To unlock the full potential of ISAC, the Distributed and Intelligent Integrated Sensing and Communications (DISAC) framework for 6G represents a transformative vision for wireless communications. DISAC combines the fusion of heterogeneous and distributed sensors with a highly adaptive and efficient semantic-native approach to enable energy-efficient, high-resolution tracking of connected user equipment (UEs) and objects.
DISAC is built on several interrelated cornerstones:
-
DISAC Architecture: The foundation for both sensing and communications, offering support for intelligent operations and distributed functions. This distributed aspect enables large-scale tracking of connected UEs and passive objects, revolutionizing the fundamental fabric of wireless networks.
-
Semantic and Goal-Oriented Framework: An intelligent and parsimonious framework encompassing sensing activation, waveform design, signal processing, dedicated resource allocation, robust protocols, and semantic reasoning about multi-modal sensed information. This framework ensures exceptional sensing performance for a myriad of use cases while optimizing resource utilization.
-
Advanced High-Resolution Processing: Exploiting multi-site and multi-band processing, leveraging a combination of machine learning (ML) and model-based signal processing, to enable efficient methods that can support the goal-oriented, semantic framework while running over the DISAC architecture.
Sensor Networks is at the forefront of this transformation, exploring the boundless potential of distributed intelligence in sensor networks and IoT applications.
Unlocking the Potential of Sensor Networks through DISAC
The DISAC framework addresses the limitations of existing ISAC approaches and unlocks new possibilities for resource-efficient, accurate, and semantic network operations. By seamlessly integrating sensing with communications and harnessing the power of distributed artificial intelligence (AI), DISAC can deliver a significant impact across various use cases and industries.
Enabling Diverse IoT Applications
The DISAC vision is closely aligned with the diverse range of use cases that can be enabled by integrated sensing and 5G/6G communication technology. These use cases span a wide spectrum, from intrusion detection in smart homes to highway/railway intrusion detection, rainfall monitoring, transparent sensing, sensing for flooding, automotive maneuvering and navigation, AGV detection and tracking in factories, UAV trajectory tracing and intrusion detection, crossroads with/without obstacles, UAV and robot collision avoidance, tourist spot traffic management, sleep and health monitoring, parking space determination, seamless XR streaming, public safety, vehicle sensing for ADAS, gesture recognition, blind spot detection, and sensing and positioning in factory halls.
The digital twin use case, in particular, stands out as it subsumes many other challenging use cases as special cases, such as intrusion detection, navigation, tracking, collision avoidance, and public safety. A digital twin is a digital representation of a large-scale physical system, including factories, warehouses, buildings, or even entire cities, on a computer or cloud-based platform. This enables continuous monitoring of the system’s status and prediction of future states, facilitating maintenance and relevant decision-making.
Standardization Efforts and Ecosystem Collaboration
Several standards organizations have begun to explore and develop work on the ISAC topic in recent years, integrating AI-based approaches with varying degrees of progress. These include:
-
ETSI: Established a new industry specification group (ISG) dedicated to ISAC, with a focus on channel modeling and complementary subjects ahead of the current 3GPP scope.
-
3GPP: Completed a feasibility study on ISAC use cases and requirements and started the specification work, covering sensing operation, functional requirements, security, and secrecy aspects.
-
ITU-R WP5D: Considering ISAC as a new usage scenario to enable innovative services and solutions, where the semantic nature of DISAC is expected to play a pivotal role.
-
IEEE 802.11: The 802.11bf Task Group has already launched in 2020, defining physical and MAC modifications to enhance sensing operations of wireless local-area networks in unlicensed frequency bands.
-
AIML Standardization: Normative work has been approved for 3GPP Release 18, focusing on enhancements to data collection and signaling to support AIML-based network energy savings, load balancing, and mobility optimizations. IEEE has also formed an AIML Technical Interest Group (TIG) in 802.11 to explore several AIML use cases.
The success of the DISAC vision relies on tight coordination between ongoing ISAC and AIML standardization efforts, as the semantic nature of sensing information directly implies the need for such integration.
The DISAC Architectural Foundations
The DISAC architecture departs from the conventional cellular network architecture in several key ways to fully integrate sensing within 3GPP-compliant systems that are communications-wise optimized.
Distributed Intelligent Signal Processing
The DISAC architecture supports distributed intelligent signal processing at the sensing receive nodes, enabling only higher-level sensing information to be sent to the fusion center. This involves defining new network functions, protocols, and interfaces to support distributed functions across many nodes, including synchronization, calibration, and AI modules for both the semantic layer and the radio layer.
Heterogeneous Capabilities and Load Balancing
The DISAC architecture must support a variety of heterogeneous capabilities and be able to balance the load based on instructions from the semantic layer. This is crucial to optimally perform local processing and hierarchical fusion of information, considering the diverse energy budgets and computation constraints of different types of nodes.
Integrating Multi-Functional Reconfigurable Intelligent Surfaces (RIS)
The design and integration of multi-functional RISs that can be used for both improving communications and sensing, as well as assisting in network deployment optimization and resource allocation, constitute critical DISAC aspects. RISs with signal reception capabilities can act as Sensor Receive Nodes (SRNs) with limited local processing capabilities.
Semantic Information Exchange and New Protocols
The DISAC architecture needs to support semantic information exchange between different network functions, implying the introduction of new protocols and network functions that include semantic extraction, semantic composition, and semantic instruction. These functions must also interact with the radio layer through operator functions that control network nodes.
Innovations in DISAC Signal Processing and Resource Allocation
The DISAC physical layer involves four key components of classical signal processing: waveform optimization, channel parameter estimation, detection, data association, and estimation, and tracking of UEs and objects over time. However, the DISAC vision requires revisiting these processes to tailor them to instantaneous application needs, leading to a more parsimonious ISAC operation.
Semantic-Aware Signal Shaping and Processing
The use of semantic-aware encoding/decoding over multiple frequency bands can increase the performance and robustness of sensing and communications. Flexible coordination among transmitted waveforms, based on OFDM or even learned from scratch, can provide improved efficiency, resilience, and robustness against interference and hardware distortion.
On the receiver-side processing, a combination of ML (e.g., for imaging and extended target processing) and model-based methods (e.g., for deciding which sensors to activate and when) is foreseen to address the challenge of resolution requirements in all sensing applications.
Distributed Aperture and High-Resolution Processing
The distributed aperture provided by the DISAC system can attain high resolution on the order of the wavelength, while suppressing sidelobes through the random placement of the many distributed receivers. Realizing and harnessing this resolution, however, is challenging, requiring extreme calibration of the infrastructure, both in terms of static (AP locations) and dynamic (time, frequency, and phase synchronization) aspects.
Sensing-Aided Communications
The DISAC paradigm envisions the optimization of large-scale and distributed communication provisioning with location and more generally, context information becoming available from the distributed processing of data gathered from multi-modal sensory devices integrated within the wireless network infrastructure. This paves the way for more efficient, context-aware, and environmentally sustainable communication networks.
Adaptive and Goal-Oriented Resource Allocation
Efficient resource allocation schemes within DISAC must be inherently goal-oriented, exploiting contextual information to strike a balance in the time, frequency, and energy resources allocated for sensing and communications. This dynamic adjustment to varying network conditions and user requirements is crucial, especially considering the heterogeneous nature of future wireless networks.
Incorporating advanced signal processing methods and the novel semantic domain within DISAC, the resulting adaptive resource allocation strategies will ensure that both sensing data and communication signals are processed and transmitted efficiently, prioritizing critical information for respective transmission.
Challenges and the Way Forward
While many of DISAC’s building blocks have been and are being studied in isolation, bringing them together requires facing several challenges that can be tackled with a broad view encompassing stakeholders from industry and academia covering the entire 6G value chain.
Designing the Semantic Framework
Designing and executing the semantic framework is a formidable challenge, as it significantly departs from the standard approach and architecture for ISAC, requiring extensive study in the coming years.
Distributed ISAC Signal Processing and Fusion
The distributed approach for ISAC will require new ways of shaping the wireless signal, processing it, and fusing the resulting information with external sensors, considering this information over extended space and time. Computational and communication constraints are expected to be the main bottlenecks, requiring lightweight processing methods.
Hardware Integration and Demonstration
The development of new hardware components that can operate in different frequency ranges while supporting DISAC in distributed settings is a challenge. These hardware components must be designed to work together seamlessly and provide interfaces to existing systems.
Standardization and Coordination
Studies on waveforms and distributed architectures, including the definition of new functional elements, protocols, and interfaces, are needed for discussion in standards development organizations (SDOs). Specific metrics, KPIs, and KVIs applicable to DISAC must be developed, as well as suitable channel models to evaluate performance in the relevant use cases. Coordination between ISAC and AI activities in SDOs is also necessary to support the semantic framework.
As the industry and research community continue to explore the boundaries of sensor networks and IoT, the DISAC framework stands out as a transformative vision that can unlock the true potential of distributed intelligence, revolutionizing how we perceive, interact, and harness the power of the physical and digital worlds. By seamlessly integrating sensing, communications, and AI, Sensor Networks is at the forefront of this exciting future, driving innovation and shaping the next generation of ubiquitous, intelligent, and adaptive sensor-driven ecosystems.