Jump to: navigation, search

Youtube search... ...Google search

AI has been applied in the telecommunications industry for over a decade, with applications focused on optimizing radio signals, power management, and network performance. AI algorithms can analyze data from network sensors to identify potential problems before they occur, allowing telecom providers to take proactive steps to fix problems and prevent outages. AI can also help to optimize network performance, improve customer service, equipment maintenance, and fraud detection. Implementing AI in telecoms also allows CSPs to proactively fix problems with communications hardware, such as cell towers. AI has the potential to simplify the task of operations by optimizing various functions that make up operations, such as field and service operations. Telecom operators can develop new revenue sources for themselves by examining market niches they haven’t previously. Some of the most promising applications of artificial intelligence and data science in telecommunications include fraud detection, customer experience improvement, and optimizing mobile tower operations.

Cognitive Radio (CR) / Software-defined radio (SDR)

Software-defined radio (SDR) is a radio communication system where components that have been traditionally implemented in hardware (e.g. mixers, filters, amplifiers, modulators/demodulators, detectors, etc.) are instead implemented by means of software on a personal computer or embedded system. Software radios have significant utility for the military and cell phone services, both of which must serve a wide variety of changing radio protocols in real time. In the long term, software-defined radios are to become the dominant technology in radio communications. SDRs, along with software defined antennas are the enablers of the cognitive radio.

GNU Radio

is a free & open-source software development toolkit that provides signal processing blocks to implement software radios. It can be used with readily-available low-cost external RF hardware to create software-defined radios, or without hardware in a simulation-like environment.

Deepwave Digital Systems

Enabling deep learning and AI at the edge of wireless systems. GPUs are extremely well suited for processes that are highly parallel. The Fast Fourier Transform (FFT) is one of the most common techniques in signal processing and happens to be a highly parallel algorithm. In this blog post the Deepwave team walks you though how to leverage the embedded GPU built into the AIR-T to perform high-speed FFTs without the computational bottleneck of a CPU and without having to experience the long development cycle associated with writing VHDL code for FPGAs. By leveraging the GPU on the AIR-T, you get the best of both worlds: fast development time and high speed processing. A familiar tool to anyone working in the wireless domain, GNU Radio allows signal processing experts to tie together blocks of functionality using an intuitive GUI. Many of the “in the weeds” details regarding the software implementation are well abstracted so the user can focus on the algorithm instead.Once an algorithm has been optimized (or a pre-trained algorithm has been downloaded by a 3rd party), the user will reference it in Deepwave’s GR-WAVELEARNER software that provides a TensorRT Inference block for GNU Radio Companion (GRC)


Software-Defined Networking (SDN)

YouTube ... Quora ... Google search ... Google News ... Bing News

Artificial Intelligence (AI) can assist Software-Defined Networking (SDN) in several ways. One of the main benefits of AI in SDN is the ability to automate network management tasks, which can help to reduce the workload on network administrators and improve network performance. AI can be used to analyze network traffic patterns and predict network failures or congestion, allowing network administrators to take proactive measures to prevent these issues from occurring. AI can also be used to optimize network traffic routing and load balancing, which can improve network performance and reduce latency.

Another way that AI can assist SDN is by enabling more intelligent network security. AI can be used to detect and respond to security threats in real-time, allowing network administrators to quickly identify and mitigate potential security breaches. AI can also be used to analyze network traffic patterns and identify anomalies that may indicate a security threat.

AI can also assist SDN in network optimization. AI algorithms can be used to optimize network traffic routing and load balancing, which can improve network performance and reduce latency. AI can also be used to optimize network resource allocation, ensuring that network resources are allocated efficiently and effectively.


Software-Defined Networking (SDN) is an approach to network management that enables dynamic, programmatically efficient network configuration in order to improve network performance and monitoring. SDN is meant to address the fact that the static architecture of traditional networks is decentralized and complex while current networks require more flexibility and easy troubleshooting. SDN suggests to centralize network intelligence in one network component by disassociating the forwarding process of network packets (data plane) from the routing process (control plane). The control plane consists of one or more controllers which are considered as the brain of SDN network. The data plane is composed of OpenFlow-enabled switches which are responsible for the packet forwarding between hosts. The communication between the control and data planes is through the OpenFlow protocol.

SD-WAN (Software-Defined Wide Area Network) is an extension of SDN that applies SDN principles to WAN connections. SD-WAN simplifies the management and operation of a WAN by decoupling the networking hardware from its control mechanism. This concept is similar to how software-defined networking implements virtualization technology to improve data center management and operation. A key application of SD-WAN is to allow companies to build higher-performance WANs using lower-cost and commercially available Internet access, enabling businesses to partially or wholly replace more expensive private WAN connection technologies such as MPLS

Machine learning solving practical problems in Communications

Machine learning has been applied to solve various practical problems in communications. Here are some examples:

  • Channel Estimation: Channel estimation is a crucial task in wireless communications, where the goal is to estimate the channel response between the transmitter and the receiver. Machine learning techniques have been used to improve the accuracy of channel estimation, especially in scenarios where the channel is time-varying and the traditional methods fail to provide accurate estimates.
  • Modulation Classification: Modulation classification is the task of identifying the modulation scheme used in a wireless transmission. Machine learning algorithms have been used to classify the modulation schemes based on the received signal, which can be useful in cognitive radio systems, where the radio can adapt its transmission parameters based on the modulation scheme used by the primary user.
  • Signal Detection: Signal detection is the task of detecting the presence of a signal in a noisy environment. Machine learning algorithms have been used to improve the detection performance, especially in scenarios where the signal-to-noise ratio is low and the traditional methods fail to provide reliable detection.
  • Resource Allocation: Resource allocation is the task of allocating the available resources, such as power and bandwidth, among the users in a wireless network. Machine learning algorithms have been used to optimize the resource allocation based on the network conditions and the user requirements, which can improve the network performance and the user experience.
  • Interference Mitigation: Interference mitigation is the task of reducing the interference caused by other users in a wireless network. Machine learning algorithms have been used to mitigate the interference by predicting the interference patterns and adapting the transmission parameters accordingly.

Physical Layer Security (PLS)

Youtube search... ...Google search

Physical layer security (PLS) has emerged as a new concept and powerful alternative that can complement and may even replace encryption-based approaches, which entail many hurdles and practical problems for future wireless systems. The basic idea of PLS is to exploit the characteristics of the wireless channel and its impairments including noise, fading, interference, dispersion, diversity, etc. in order to ensure the ability of the intended user to successfully perform data decoding while preventing eavesdroppers from doing so. Thus, the main design goal of PLS is to increase the performance difference between the link of the legitimate receiver and that of the eavesdropper by using well-designed transmission schemes. Physical Layer Security for Downlink NOMA: Requirements, Merits, Challenges, and Recommendations | H. Furqan, J. Hamamreh, and H. Arslan


Youtube search... ...Google search

Secure waveforms are designed to minimize the probability of detection by adversaries, making it difficult for them to intercept or jam the communication. AI can support secure waveforms by developing advanced techniques that can optimize the waveform parameters and minimize the probability of detection by adversaries. Artificial Intelligence (AI) can support secure waveforms in several ways:

  • Signal Processing: AI can be used to develop advanced signal processing techniques that can detect and extract weak signals from noisy environments. These techniques can help LPI/LPD waveforms to remain undetected by adversaries by minimizing the signal's footprint and reducing the probability of detection.
  • Cognitive Radio: AI can be used to develop cognitive radio systems that can adapt to the changing radio environment and optimize the waveform parameters to minimize the probability of detection. These systems can use machine learning algorithms to learn from the radio environment and adjust the waveform parameters, such as frequency, modulation, and power, to maintain LPI/LPD characteristics.
  • Machine Learning (ML): AI can be used to develop machine learning algorithms that can analyze the radio environment and predict the probability of detection. These algorithms can use various features, such as signal strength, frequency, and modulation, to predict the probability of detection and optimize the waveform parameters to maintain LPI/LPD characteristics.
  • Cybersecurity: AI can be used to develop advanced cybersecurity techniques that can detect and prevent jamming and interception attempts by adversaries. These techniques can use machine learning algorithms to analyze the radio environment and detect anomalous activities that indicate jamming or interception attempts.

Secure Waveforms

Secure waveforms refer to communication waveforms that are designed to provide secure and resilient communication in various wireless communication systems. These waveforms are specifically designed to mitigate vulnerabilities and protect against various types of attacks, ensuring the confidentiality, integrity, and availability of transmitted data. Secure waveforms typically incorporate advanced encryption techniques, authentication mechanisms, and error correction codes to enhance the security and reliability of wireless communication. They are often used in military, defense, and critical infrastructure applications where secure and resilient communication is of utmost importance. Attributes are:

  • Confidentiality: Confidentiality ensures that the information transmitted using the waveform remains private and cannot be accessed or understood by unauthorized entities. This is achieved through encryption techniques, where the waveform data is encrypted using cryptographic algorithms. Only authorized recipients with the appropriate decryption keys can decrypt and access the original information.
  • Integrity: Integrity ensures that the waveform data remains unchanged during transmission and cannot be tampered with by unauthorized entities. To achieve integrity, secure waveforms use techniques such as message authentication codes (MACs) or digital signatures. These techniques allow the recipient to verify the integrity of the received waveform by checking the authenticity of the transmitted data.
  • Authentication: Authentication ensures that the communicating entities can verify each other's identities to establish trust and prevent unauthorized access. Secure waveforms use authentication mechanisms such as digital certificates, public-key infrastructure (PKI), or challenge-response protocols. These mechanisms allow entities to verify the identity of the sender and ensure that the received waveform is from a trusted source.
  • Anti-jamming: Anti-jamming capabilities protect the waveform from intentional interference or jamming attempts by adversaries. Secure waveforms employ techniques such as frequency hopping, spread spectrum modulation, or adaptive modulation to mitigate the effects of jamming. These techniques make it difficult for adversaries to disrupt or interfere with the transmission, ensuring reliable and secure communication. Some of the techniques used in secure waveforms to provide anti-jamming capabilities are:
    • Frequency hopping: In frequency hopping, the transmitter and receiver switch between different frequencies in a pre-determined pattern. This makes it difficult for an adversary to jam the signal as they would need to jam all the frequencies being used.
    • Spread spectrum: In spread spectrum, the signal is spread over a wide frequency band using a code. The receiver uses the same code to de-spread the signal. This makes it difficult for an adversary to jam the signal as they would need to jam the entire frequency band.
    • Adaptive power control: In adaptive power control, the transmitter adjusts its power based on the received signal strength. This helps to maintain a constant signal-to-noise ratio and makes it difficult for an adversary to jam the signal by overpowering it.
    • Directional antennas: In directional antennas, the transmitter and receiver use antennas that focus the signal in a specific direction. This makes it difficult for an adversary to jam the signal as they would need to be in the path of the signal.

Anti-Jam (AJ) & Low Probability of Intercept/Detection (LPI/ LPD) Waveforms

With MIMO arrays, radios like the StreamCaster are able to eliminate interference by directing a null toward a jammer. This happens via an optional software module called MANET-Interference Cancellation (MAN-IC). MAN-IC listens to the spatial signature of a jamming signal, then computes a set of antenna weights that null out that spatial signature. This method has proven extremely powerful, yielding as much as 30 dB of consistent suppression in field trials. The module also has the secondary benefit of improving LPI/LPD performance. By utilizing a friendly cover signal, radios can operate on the same frequencies by nulling the friendly “jamming” signal. The friendly signal overpowers the much weaker communications signals of those radios, hiding these weaker signals from the enemy.

Primary, Alternative, Contingency and Emergency (PACE) communications

Another module called MANET-Interference Avoidance (MAN-IA) enables military radios to avoid interference by hopping to a different frequency band. The system monitors multiple frequencies in different bands using the MIMO degrees of freedom available in the radios. Once the radios detect a jamming signal, each radio autonomously selects the next best channel. A regrouping algorithm ensures that all radios converge on a common frequency in less than one second.

Low Probability of Intercept/Detection (LPI/ LPD)

In a MANET, radios typically operate at maximum power to ensure high throughput and high network efficiency. But this produces suboptimal LPI/LPD performance since higher power is more easily detectable by adversaries. This has led to the development of a module called MANET-Power Control (MAN-PC) that minimizes the radio’s transmit power while maintaining the desired throughput. Field tests have shown a 70 percent reduction in distance to the detector before the signal is detected.


YouTube search... ...Google search

Webinar: Bringing AI research to wireless communications and sensing
AI for wireless is already here, with applications in areas such as mobility management, sensing and localization, smart signaling and interference management. Recently, Qualcomm Technologies has prototyped the AI-enabled air interface and launched the Qualcomm 5G AI Suite. These developments are possible thanks to expertise in both wireless and machine learning from over a decade of foundational research in these complementing fields. Our approach brings together the modeling flexibility and computational efficiency of machine learning and the out-of-domain generalization and interpretability of wireless domain expertise. In this webinar, Qualcomm AI Research presents an overview of state-of-the-art research at the intersection of the two fields and offers a glimpse into the future of the wireless industry.

5G-IoT-Edge-ML/AI: Technologies That Will Transform
Digi International Inc. 5G networks are being deployed, and we believe that 5G, IoT, edge compute, machine learning and artificial intelligence will combine to create the perfect technological storm – in a good way! In this video Digi engineering director Harald Remmert describes how low-cost IoT devices combined with the huge capacity of 5G will transform society, and how you can leverage 4G LTE today.

Stanford Seminar - Promise of 5G Wireless – The Journey Begins
Arogyaswami Paulraj Stanford University October 3, 2019 Professor Emeritus Arogyaswami Paulraj, Stanford University, is a pioneer of Multiple-Input Multiple-Output (MIMO) wireless communications, a technology break through that enables improved wireless performance. MIMO is now incorporated into all new wireless systems. Paulraj is the author of over 400 research papers, two text books and a co-inventor in 79 US patents. Paulraj has won over a dozen awards, notably the National Inventors Hall of Fame (USPTO), Marconi Prize and Fellowship, 2014 and the IEEE Alexander Graham Bell Medal, 2011. He is a fellow of eight scientific / engineering national academies including the US, China, India and Sweden. He is a fellow of IEEE and AAAS. In 1999, Paulraj founded Iospan Wireless Inc. – which developed and established MIMO-OFDMA wireless as the core 4G technology. Iospan was acquired in by Intel Corporation in 2003. In 2004, he co-founded Beceem Communications Inc. The company became the market leader in 4G-WiMAX semiconductor and was acquired by Broadcom Corp. in 2010. In 2014 he founded Rasa Networks to develop Machine Learning tools for WiFi Networks. The company was acquired HPE in 2016. During his 30 years in the Indian (Navy) (1961-1991), he founded three national level laboratories in India and headed one of India’s most successful military R&D projects – APSOH sonar. He received over a dozen awards (many at the national level) in India including the Padma Bhushan, Ati Vishist Seva Medal and the VASVIK Medal.

5G-IoT-Edge-ML/AI: Technologies That Will Transform
Digi International Inc. 5G networks are being deployed, and we believe that 5G, IoT, edge compute, machine learning and artificial intelligence will combine to create the perfect technological storm – in a good way! In this video Digi engineering director Harald Remmert describes how low-cost IoT devices combined with the huge capacity of 5G will transform society, and how you can leverage 4G LTE today.

5G: The perfect storm and enabler of the next wave of AI
Webinar hosted by Norwegian Cognitive Center on September 16 2020. How does 5G relate and accelerate new and emerging technologies, AI, ML and industry 4.0? 5G will come as a service offering, but it is also a technology. Both will, for a number of reasons, be disruptive and can be utilized for new and enhanced services. 5G will bring us and our IoT devices closer and more connected. It will also change the way we work, play, think and plan. Join us at this webinar to further understand the changes, enhancements and opportunities 5G will bring. Speaker: Ingebrigt Lunde is Project Manager at Nordic 5G Consortium: Ingebrigt holds a M.Sc. in Computer Science. He has previously worked with research and development for 10 years in Digital Equipment Corporation (DEC), University of Bergen, establishing commercial internet in Norway and for the last 25 years in TV 2 Norway, designing and building the IP infrastructure and production and lately new production models. He was the project manager for the groundbreaking and award nominated TV 2 Hockey national wide NDI based production network system.

Why China can take a lead in 5G and AI technology application
China is among the world’s first countries to apply 5G to business services. China’s telecommunications guides the global 5G-technology trend. An open China is becoming the “playground” for global AI businesses and a key landmark for a joint exploration of AI’s direction of end development. Check out this video and have a look at why China can take a lead in 5G and AI technology application. Subscribe to us on YouTube:

5G Security

YouTube search... ...Google search

Three-step approach to reach a high level of intelligent security management. How to master E2E network security when introducing 5G core | Kari-Pekka Perttula - Ericsson

  • Dynamic: Introduce automated security policy configuration and compliance monitoring
  • Cognitive: Automated threat and vulnerability detection assisted with ML /AI
  • Intelligent: Repeatable, adaptive and holistic security management with threat intelligence. This provides end-to-end visibility for business-related security risks, and actions can be directed via automated workflows to mitigate risks faster.

Threat Model: STRIDE | Wikipedia The threats are:

Rambus: What Does Security Look Like When 5G Meets AI?
Presented by Neeraj Paliwal, VP and GM of Security Business Unit, Rambus. 5G represents a revolution in mobile technology with performance that will rival that of wireline networks. 5G's Ultra-Reliable Low Latency Communication (uRLLC) links will enable a profusion of AI-powered devices from delivery drones to smart cities. Given the great value and potential risks, it is critical to protect the data, devices and infrastructure resulting from the confluence of 5G and AI. This presentation will discuss the threats to, and the security solutions that can safeguard, the emerging 5G+AI world. The Linley Spring Processor Conference featured technical presentations on AI acceleration, targeting edge, automotive, IoT, and data center. Also covered were new CPU architectures, networking, security, SoC design, and other processor-related topics.

4G to 5G Evolution: In-Depth Security Perspective
RSA Conference Anand Prasad, CISO, Rakuten Mobile Networks In this talk we will present 4G security and issues identified recently followed by in-depth explanation of security enhancements in 5G. We will also cover potential security implications from usage of technologies such as virtualization in mobile networks. Finally we will summarize 5G related security activities expected in near future.Learning Objectives:1: Get a refresher on 4G security, security issues and solutions.2: Learn in-depth regarding 5G security.3: Find out considerations for end-to-end 5G network deployment.Pre-Requisites:Attendees should have some background in mobile networks and security, especially 4G will be beneficial. It is assumed that the attendees have good knowledge of information security.

Demystifying 5G Security through Threat Modeling
Zhijun Zhang, Lead Security Architect, The World Bank Group 5G promises to bring much faster data rate and many new services. At the same time it has created a lot of concerns around security risks. This talk will walk through the new technology components in a 5G network and the new services it provides, to comprehensively analyze the risks in this ecosystem through a threat model the World Bank Group developed and to discuss the mitigating controls. Pre-Requisites: Understanding of Threat models such as STRIDE.

R&S Thirty-Five: 5G security aspects
For us, security is always an important topic. The same goes for the security in the 5G era. Today’s presentation lists a few security threats as a motivation and presents further details on the sophisticated security mechanisms used in 5G, like e.g. authentication, key derivation, subscriber privacy protection and a secure communication between network functions. With R&S Thirty-Five, you can discover more about this topic here.

5G and Security – UK5G Security Sub-Group Event Day 1
5G security event sponsored by 5G Security Sub Group UK5G, part of UK5G the national advisory body for the UK’s national 5G support programme with presentations from thought leaders on a variety of security topics from Security Assurance in a 5G World to How Colt is Addressing Security Challenges for B2B to a discussion panel on Security as a Policy. KTN exists to connect innovators with new partners and opportunities - together we can drive positive change. Find out more about KTN:

5G and Security – UK5G Security Sub-Group Event Day 2
5G security event sponsored by 5G Security Sub Group UK5G, part of UK5G the national advisory body for the UK’s national 5G support programme with presentations from thought leaders on a variety of security topics from Security Assurance in a 5G World to How Colt is Addressing Security Challenges for B2B to a discussion panel on Security as a Policy. KTN exists to connect innovators with new partners and opportunities - together we can drive positive change. Find out more about KTN:

5G Testing

YouTube search... ...Google search

Artificial Intelligence and Machine Learning for 5G Network Monitoring – COMARCH
How and why are telcos turning to artificial intelligence and machine learning to automate network management processes? Our new video and white paper answer this question. They presents a detailed view of the necessity of automation, and show which specific processes need to be addressed.

5G Life Cycle Automation with AI-Based Continuous Testing
B-Yond and Keysight Technologies discuss 5G Life Cycle Automation with AI-Based Continuous Testing and Validation. Key insights about how to enable full end to end life cycle automation and testing, with a practical example of a customer deployment for 5G.

Virtualization - Dynamic Spectrum Sharing (DSS)

Youtube search... ...Google search ...Google News

Spectrum Sharing utilizes virtualization to partition optical spectrum

R&S Thirty-Five: Introduction to 5G Dynamic Spectrum Sharing
5G and LTE cooperating and sharing the same frequency. Is this possible and what are the technology settings and adjustments to make this real? Check out our today´s webcast and find out what Andreas Rößler, Technology Manager at Rohde & Schwarz thinks about it!

Understanding Dynamic Spectrum Sharing (DSS)
Keysight EEsof EDA This video introduces dynamic spectrum sharing also known as LTE 5G coexistence and looks at the techniques adapted by 5G NR in order to coexist with LTE. There is a demo of verifying a DSS implementation using Keysight’s PathWave Signal Generation (N7631C, N7624C) and PathWave Vector Signal Analysis (89600 VSA) software.

Stanford Seminar - The Future of Wireless Communications Hint: It's not a linear amplifier
EE380: Computer Systems Colloquium Seminar Speaker: Douglas Kirkpatrick is the co-founder and CEO of Eridan Communications ...The future of wireless communications will demand leaps in spectrum efficiency, bandwidth efficiency, and power efficiency for successful technology deployments. Key applications that will fundamentally change how we interact with wireless systems and the demands we place on wireless technologies include Dynamic Spectrum Access Networks, massive MIMO, and the evasive unicorn of the "universal handset". While each of these breakthrough "system" capabilities make simultaneous demands of spectrum efficiency, bandwidth efficiency, and power efficiency, the current suite of legacy technologies forces system designers to make undesirable trade-offs because of the limitations of linear amplifier technology. ...Dr. Kirkpatrick was a Program Manager and Chief Scientist at the Defense Advanced Research Projects Agency (DARPA). While he was at DARPA he started and managed programs that, among other things, developed and deployed the first LED flashlights, started and validated the DOD path to bio-renewable jet fuel, developed and demonstrated ultra-high efficiency solar cells, developed and demonstrated full 3d dynamic holographic displays, and developed and demonstrated portable tools for the rapid de-novo synthesis of DNA up to 10,000 base pairs long. In addition to his DARPA role he was simultaneously the Senior Technologist for Technology Productization for the Undersecretary for Acquisition, Technology, and Logistics in the Department of Defense... Dr. Kirkpatrick is a Fellow of the American Physics Society, a Member of the IEEE, and a Member of the Materials Research Society. Dr. Kirkpatrick holds a BS degree in Physics and Mathematics (1980) from the College of William and Mary and a Ph.D. in Physics from M.I.T. (1988).

5G & Spectrum Sharing Panel, Mobile World Congress LA 2019
Industry and government leaders discuss the SC2 Championship, how this relates to other spectrum sharing efforts being pursued by industry leaders and regulators, and look forward to the future of 5G and Spectrum Sharing technologies. Moderator: John Chapin, SC2 Subject Matter Expert Panelists: - Paul Tilghman, SC2 Program Manager, DARPA - Ali Kyayrallah, Engineering Director, Ericsson Research - John Smee - VP of Engineering, Qualcomm Research - Julius Knapp - Chief, Office of Engineering and Technology, FCC - Fred Moorefield - Acting Deputy CIO - C4IIC, DoD