Linkedin Twitter
  • Main
    banner logo

    smart mobility summit

    Lisbon, Portugal // 3rd-4th May 2017


How machine learning can solve wireless network issues

speaker ajay malik guest

Ajay Malik

Head Architecture/ Engineering, Worldwide Corporate Networking & Services at Google

Ajay Malik has over 25 years of engineering leadership and entrepreneurial experience in delivering award-winning innovative products in the Software, SAAS, Wi-Fi, RTLS (real time location), IOT (internet of things), and SDN (Software defined networking). He has led multiple turnarounds/successful exits. He has over 70 patents issued/pending and is author of "RTLS for Dummies"; and "Augmented Reality for Dummies". He now works at Google.

Wi-Fi is crucial to the way we work today. Fast, reliable, and consistent wireless coverage in an enterprise is business-critical. Many day-to-day operations in the enterprise depend on it. And yet, most of the time, IT teams are flying blind when it comes to individual experience. This springs from two main challenges.

The first challenge is data collection. We want to know the state of every user at every given time. But these states change constantly as network conditions and user locations change. With tens of thousands of devices being tracked, there is a huge amount of information to be collected. This volume of data simply cannot be handled in an access point or a controller running on an appliance with fixed memory and CPU. The second challenge is data analysis. It takes considerable time and effort to sort through event logs and data dumps to get meaningful insights. And significant Wi-Fi intelligence is required to actually make heads or tails out of the data.

Someday soon, I believe, big data and machine learning will solve the above hurdles. It will allow me to ask my network how it is feeling, it will tell me where it hurts, and it will provide detailed prescriptions for fixing the problem (or will automatically fix it for me). While this seems to be a futuristic vision, the foundation to achieve it is already being laid out through big data tools and machine learning techniques like unsupervised training algorithms.

Using these technologies, we can now continuously update models that measure and enforce the experience for our wireless users. For example, we can ensure specific internet speeds in real time (i.e throughput) with a high level of accuracy. This allows the IT staff to know a wireless user is suffering before they even realize it — and thus before they have to log a call with the help desk.

Once a user problem is detected, machine learning classification algorithms can isolate the root cause of the problem. For example, is the throughput issue due to interference, capacity, or LAN/WAN issues?

After isolating the problem, machine learning can then automatically reconfigure resources to mediate the issue. This minimizes the time and effort IT teams spend on troubleshooting, while delivering the best possible wireless experience.

I’ve written before how artificial intelligence will revolutionize Wi-Fi. I would love to be able to just unleash IT teams on sifting through hordes of data so they can glean meaningful information. But it is like finding a needle in a haystack. Machine learning is key to automating mundane operational tasks like packet captures, event correlation, and root cause analysis. In addition, it can provide predictive recommendations to keep our wireless network out of trouble.

Also key to this vision is the elastic scale and programmability that modern cloud elements bring to the table. The cloud is the only medium suitable for treating Wi-Fi like a big data problem. It has the capacity to store tremendous amounts of data, with a distributed architecture that can analyze this data at tremendous speed.

Wi-Fi isn’t new. But how we use Wi-Fi has evolved. And now more than ever, Wi-Fi needs to perform flawlessly. We are in an era where wireless needs to be managed like a service, with all the flexibility, agility, and reliability of other business-critical platforms. With machine learning, big data, and the cloud, this new paradigm is quickly becoming a reality.

In the connectivity mix

Shipments of wireless multi-protocol ICs and devices will increase nearly 54 per cent between now and 2020, driven by surging Wi-Fi traffic, new use cases, and emerging IoT applications, according to a new forecast by market analysts ABI Research.

It highlights how the connectivity technology used in mobile devices will become largely irrelevant to users, who increasingly demand seamless connection as they move around, regardless of the technologies being used.

“The proliferation of multi-protocol ICs and devices will allow for much simpler product creations and quicker times to market regardless of the deployed technology,” said Andrew Zignani, Industry Analyst at ABI Research.

Zignani quotes Qorvo’s recent GP695 SoC product announcement that integrates multiple communication protocols, including IEEE 802.15.4, ZigBee, and Bluetooth Low Energy (BLE), as a prime example.

“The technology collaboration reduces complexity for IoT device designers by enabling them to take advantage of a single SKU development platform,” he added.

The report also notes that short-range wireless connectivity market technologies, such as ZigBee, Thread, Bluetooth Low Energy (BLE), Z-Wave, Wi-Fi, and NFC, will continue to evolve to meet new market demands, as evidenced by Bluetooth 5 speed enhancements to benefit wearables and other handheld devices with quicker performance times, quicker data transfers and syncing, and faster firmware updates, while keeping power consumption down.

The report also notes that Wi-Fi’s continued evolution will come in the form of several new protocols, including 802.11ax (for network efficiency improvements), 802.11ad (for 4K streaming, docking, and VR applications) and 802.11ah (low-power IoT applications).

As a result, Wi-Fi chipsets that incorporate 802.11ax, WiGig, or HaLow technologies will make up 60 per cent of all wireless IC shipments by 2021, says the report.

The report highlights how a mix of connectivity technologies will be required to meet demand for consumers, businesses, smart cities and IoT applications, all of which will need to work seamlessly together as required. That’s why SMS welcomes the entire spectrum of communications stakeholders, without banging the drum for a single technology.

SMS Lisbon 2017, to be held 3-4th May 2017, will focus on two of the most important subjects in the communications industry today – Smart cities & IoT, and Next-Generation Mobile Technologies – with a day of presentations, panel debates, and networking, dedicated to each.

We believe that the industry will need to collaborate in an open manner in order to meet demand for seamless connectivity, and profit from the opportunities offered by the transformation currently occurring.

That’s why we are collecting some of the industry’s leading speakers and thinkers for our event, including a keynote from João Vasconcelos, Secretary of State for Industry for the Portuguese Government, and presentations from Charbel Aoun, Board Member of Future Cities Catapult in London, and Antonio Ponzo Pellegrini, Deputy Mayor of Empoli (Italy), to name just a few.

If you want to be a part of the future of the communications industry, then ensure that you’re a part of the conversation. Sign up now at

How can operators confirm their place at the forefront of IoT innovation?

This week the UK SME incubator Digital Catapult – set up to help digital businesses innovate – launched an Internet of Things (IoT) network across London to encourage startups and small businesses to tap into the potential of the IoT and to encourage innovation in the rapidly growing field.

The programme, known as Things Connected, will initially provide 50 LoRaWAN base stations across the UK capital, in order to provide a large-scale public network as the first phase of the testbed, with a further low-power WAN (LPWAN) to be added as the network develops.

It will be the UK’s largest LoRaWAN network for IoT development, and is free to use. It aims to help boost the development of services for common IoT use cases – such as infrastructure provision, traffic and transport services and energy management and environment sensing – as well as more advanced applications such as traffic congestion and management capabilities, temperature, air quality and humidity monitoring, and even the development of much-touted parcel delivery drones through the use of wind speed and turbulence sensors around the capital.

Jeremy Silver, CEO of Digital Catapult said: “Things Connected will help remove the barriers to IoT technology for businesses, and create new revenue opportunities for entrepreneurs and for smaller and larger companies.”

What is interesting about the project is the broad spectrum of stakeholders that Things Connected already involves, including BT, four major London universities, as well as a mix of commercial organisations.

Indeed, as Smart Mobility Summit has noted before, the future opportunities offered by the IoT, smart cities, 5G, HetNets, and other connectivity technologies, requires collaboration and partnerships between a fluid mix of organisations and stakeholders, with each project requiring a unique blend of expertise and, of course, leadership.

The potential rewards are there to see. According to the Centre of Economics and Business Research (CEBR), for example, big data and the IoT could add £322 billion, and over 200,000 new jobs, to the UK economy by 2020.

Of course, operators will be an essential component in ensuring the success of the IoT and smart city projects. But it will not be enough to simply provide an infrastructure that can carry the burgeoning volume of IoT data, as well as the different types of data, from high-volume, low importance information to mission-critical data. Operators will need to be at the centre of the mix, helping to develop new apps, services and technologies.

Already, some forward-thinking operators have dived into the world of IoT innovation. For example, Spain’s Telefónica offers an IoT product called Thinking Things, which allows developers to create apps for smart homes and offices, while UK Orange has developed a machine-to-machine (M2M) communications system in collaboration with Nespresso and Coca-Cola. Germany’s Deutsche Telekom, meanwhile, offers its Industry 4.0 initiative, which aims to support the digitisation of manufacturing.

It’s essential that operators look to innovate in these new and exciting fields. Merely providing the ‘pipe’ will not suffice, and so they will need to innovate and collaborate with a broad mix of new and different partners in order to tap into the new revenue streams on offer.

At Smart Mobility Summit we have always been committed to embracing the broadest spectrum of stakeholders possible, as we believe that this is the only way the industry will fulfil the potential of the exciting new opportunities and revenue streams that are already on the horizon.

Our events provide an open platform for debate, and ample opportunity for networking and sharing insight with industry peers, in the hope that the industry can find new ways to collaborate and innovate in order to help shape the future landscape of communications technologies.

Come and join the conversation! Register now at

Stay informed

Sign up for our weekly newsletter to keep up to date with the latest Smart Mobility stories and updates on the conference.

Please enter your email address

Keep up to date by following us:

Linkedin Twitter