AI enhancement of capacity management in mobile networks

The optimisation of capacity management in mobile networks is vital: too little capacity constraints revenue opportunities and impacts customer experience, but idle capacity risks high opex and under-performing investment in assets. Capacity management has always used mathematical modelling techniques to attempt to find the sweet spot, and optimise opportunities and costs. In the past, such predictions were based on historical data, but now AI enhancement of capacity management changes that. The deployment of network virtualization, 5G and network slicing requires the use of cognitive planning; it is vital that capacity planning models are able to assess a step-change in the volume of data points in real-time or near-real-time.

RAN Automation Architect and Data Scientist at Digis Squared, Obeid Allah Ali, describes how AI, automation and advanced analytics are being deployed to gain even greater network capacity planning efficiencies.

What exactly is machine learning, and why is it important?

Machine Learning (ML) is an application of artificial intelligence (AI) that enables computer programs to learn and improve over time because of their interactions with data.

It automates analytics by making predictions using algorithms that learn repeatedly.

Its easy self-learning technique, rather than rule-based programming, has found widespread use in a variety of contexts.

So, whether it’s making life easier with navigation advice based on predicted traffic behaviour, assessing large amounts of medical data to identify new patterns and links, or warning you about market volatility so you can adjust financial decisions, AI and ML technology has permeated many aspects of our daily lives.

The power of prediction machines

In simplified terms, prediction is the process of filling in the missing information. It takes the information you have, often called ‘data,’ and uses it to generate information you don’t have. Most machine learning algorithms are mathematical models that predict outcomes.

How will machine learning impact businesses?

There are two major ways that forecasts will alter the way businesses operate.

  1. At low levels, a prediction machine can relieve humans of predictive activities, resulting in cost savings, and for example removing emotional bias.
  2. A prediction machine could become so accurate and dependable that it alters how a company operates.

How big is the growth in mobile connectivity?

Above: from GSMA “The State of Mobile Internet Connectivity Report 2021” [3], their most recent report

Some further statistics on the growth in mobile data, from the same GSMA report [3],

  • global data per user reaching more than 6 GB per month – double the data usage for 2018
  • 94% of the world’s population covered by mobile broadband network
  • By the end of 2020, 51% of the world’s population – just over 4 billion people – were using mobile internet, an increase of 225 million since the end of 2019

And from [4] GSMA Mobile Economy 2021 report,

  • By the end of 2025, 5G will account for just over a fifth of total mobile connections.

Capacity and performance of mobile networks

The rapid growth of mobile traffic places enormous strain on mobile networks’ ability to provide the necessary capacity and performance.

To meet demand, communications services providers (CSPs), mobile network operators and their suppliers need a range of options, including more spectrum, new technology, small cells, and traffic offloading to alternate access networks.

To meet commercial business objectives, mobile network operators are under pressure to maximize the utilization of existing resources while avoiding capacity bottlenecks that reduce revenues and negatively influence end-user experience.

Additionally, network operators have to assess risk, contractual SLAs (especially in the context of MVNOS who utilise their network, and corporate contracts), the total cost of ownership, and the impact on customer experience, perception and brand.

Radio Access Network costs are estimated to be 20% of the opex cost of running a network [1]. And the impact of opex on network quality correlates strongly with increased ARPU and reduced churn; when network quality is highest, service providers benefit from a higher average ARPU (+31 %) and lower average churn (-27%) [2].

Finding the perfect balance of capacity, quality, efficiency and cost – not too much, not too little – is complex and dynamic.

Capacity forecasting for mobile networks

The Digis Squared team have developed machine learning algorithms and decoders that can, based on network activity, decode how User Traffic Profiles are changing. With the deployment of 5G and network slicing techniques, modelling network usage patterns and customer behaviour and predicting future demand becomes immediately far more complex – the only way to successfully model this will be with AI.

Detecting a problem

We detect anomalies in cells in the existing network, plus highly utilized cells, using machine learning and a design approach algorithm based on several reported KPIs. We use this information to distinguish what requires immediate attention from what should be monitored for proactive action. Using multivariable modeling techniques, that is, assessing multiple KPIs across each cell, enables us to have a highly nuanced model, optimising all available capacity.

Forecasting

Operators must be able to estimate the required traffic capacity for their mobile networks in this competitive climate to invest in extensions when they are truly needed, and deploy the most cost-effective solution, while maximizing investment and maintaining good network quality.
In this phase of the development of the model, we will discover future troublesome cells to guide our approach and actions using predictive models.

AI enhancement of capacity management: what’s next?

Today, we use an open-loop control system to apply our AI methods. However, as predictive model accuracy improves, we anticipate transitioning to a fully automated Self-Organized Network (SON) – enabling closed-loop network management with self-planning, self-configuration, self-optimization, and self-healing – system in the near future.

In conversation with Obeid Allah Ali, RAN Automation Architect and Data Scientist at Digis Squared.

If you or your team would like to discover more about our capabilities, please get in touch: use this link or email sales@DigisSquared.com .

Discover more

Digis Squared, independent telecoms expertise.

References

Capacity management ◦ Now more than ever, as staff return to offices, handle unpredictable demand with agility

As network capacity and demand flex again, Communications Service Providers (CSPs) and Mobile Network Operators need to adapt to shifts in office use and working patterns – how can AI help?

As the initial phases of the pandemic swept around the world, communication providers and network operators worked hard to reconfigure their networks to address the unpredictable changes in demand, and keep communities connected. Now, as staff return to offices in increasing numbers, the networks need to be reconfigured again, and be ready to continue to adapt, as changes in society and working patterns rapidly evolve. But predicting how to adjust capacity is complex – some businesses are encouraging the continuation of home-working, others are rotating teams with one week in and the next at home, or splitting teams by day of the week. And all of these changes in office use, and the retail and social spaces they support, are fluidly adapting to the ebb and flow of local lockdowns. Can AI help CSPs and MNOs to manage their network capacity to address this lack of pattern and constant change?

In our blog on Capacity Management in May, we shared stats illustrating the big shift in communication demands,

“The five largest operators in Spain reported a 40% increase in overall IP traffic, a 25% increase in mobile traffic and a 50% increase in mobile voice traffic since the start of the outbreak.”

Analysys Mason (1)

Home working, with its heavy use of video conferencing and collaboration, combined with a surge in demand for digital entertainment, home studying and intensive use of multiple devices simultaneously, led to a previously unimaginable surge in demand for capacity on both fixed and mobile networks. The changes in mobile network demand highlighted difficult to predict anomalies – in many cities, as people stayed at home, significant demand was off-loaded to home wifi networks (Deloitte (2): “some telcos say they have seen a 300% increase in the use of these voice-over-WiFi services.”), in contrast with rural areas and other poorly served broadband-black-spots, mobile data demand has soared.

“…the way to consider a crisis of this magnitude is to identify three phases: Respond, Recover and Thrive.”

Deloitte (2)

Now that the initial rush to support business employees working from home has passed, more countries are slowly re-opening business premises – with staggered start times, and changes in working practice. The need to maintain agility in capacity management is vital, as lockdowns will be enforced dynamically over the months and years ahead.

Planning ahead

Short-term challenges addressed earlier in the pandemic,

  • After the initial dynamic changes in customer behaviour, and the lack of revenue from roaming charges, many operators continue to experience significant pressure on operating expenses, and have taken quick business decisions to remove costs
  • Capital expenditure plans have been rapidly re-assessed to ensure re-prioritisation to meet the new revenue and business continuity needs
  • Re-assessment of supply chains, equipment procurement issues, safe social distancing in the workplace, and staff absence levels
  • Rapid revenue and cash management, as economies globally continue to experience a massive downturn.

Now, plans are being made to manage the “next new normal”, as changes in society and working patterns continue to evolve, and staff return to offices. At Digis Squared we believe this next phase is even harder, as “Business As Usual” will mean a constant need for agility and flexing to meet demand. But the good news is that we can help MNOs and CSPs address the exceptional levels of uncertainty and dynamic change, and AI is part of the mix,

  • Accelerate digital transformation: use AI and RPA to manage higher customer service call volumes to support remote working, and handle mundane repetitive tasks and digital self-service via automation
  • Revise Business Continuity Plans: review assumptions, re-plan and re-scale
  • Accelerate 5G deployment and integration to better handle high demand dynamically
  • Implement autonomous capacity management, to ensure that your mobile networks work efficiently.

Whilst many short terms solutions have been rapidly implemented, now is the time to ensure they are robust and resilient enough to continue to handle the longer term, and to re-assess Business Continuity Plans.

AI-led autonomous capacity management

We can help communications services providers and mobile network operators to achieve more with your network resources: absorb new traffic demands, and optimize the expansions you need by using Digis Squared’s vendor-agnostic, off-the-shelf solutions.

Use our expertise to dynamically assist your teams

Our areas of focus are,

  • Vendor agnostic AI-led capacity modelling for all network technologies (2G/3G/4G/5G)
  • Machine learning algorithms using network data enriched with multiple data feeds from radio access network, Customer Experience Management (CEM), geolocation systems and crowdsourced data
  • Predictive traffic growth based on AI-power algorithms followed by degradation preventive actions and expansions prediction
  • Action-centric benchmarking (BM) reports including KPIs, KQIs and Customers QOEs
  • ROI calculations for network investments.

Many of our clients use modular capacity management modules developed by Digis Squared team, with bespoke adaptations if needed, to,

  • Balance the traffic between cells & technologies
  • Recommend soft actions needed
  • Activate & reshuffle sites licenses
  • Capacity enhancement feature recommendations
  • Physical changes
  • Network expansions and reshuffling required.

Our teams can use these capabilities to deliver value to service providers and mobile network operators,

  • Start the smart CAPEX journey, and identify pathways to OPEX saving
  • Maximize network investment ROI and help operators make well-informed, data-centred investment decisions
  • Speed-up network capacity plans through our automated-predictive solution.

We can assist you right now with our ready-to-go, adaptive-modular capacity management modules, developed by the Digis Squared team to,

  • Balance the traffic between cells & technologies
  • Recommend soft actions needed
  • Activate & reshuffle sites licenses
  • Capacity enhancement feature recommendations
  • Physical changes
  • Network expansions and reshuffling required.

Discover more about our Digis-Capacity, AI & ML capabilities.

Now more than ever, capacity management ensures you can handle unpredictable demand with agility.

To discuss how our capacity management expertise can help your business, please use this link or email sales@DigisSquared.com to arrange an informal chat.

Keep up to speed with company updates, product launches and our quarterly newsletter, sign up here.

“In the words of one the telecom operator we spoke to: ‘ideally we never go back to the way we operated before this crisis’.”

Source: Deloitte (2)

Sources,

Image credit: Daniel Von Appen

INOS ◦ Now more than ever, know your network strengths, and weaknesses

Understand what has changed, then invest

As work patterns continue to change, operators struggle to model their network capacity and investment plans. Understanding current network coverage, performance and quality of experience, and that of competitors, is vital before investment decisions are made.

Our cloud-controlled INOS automated testing platform delivers both drive testing, and in building data, enabling operators and service providers to efficiently obtain the insights needed for key upgrade decisions. [Our tools need just one person in the vehicle or building – no engineers are needed on-site, ensuring that they can do their work safely and together we can keep our communities connected.]

Know your strengths, and weaknesses. Now more than ever, ensure you know the capability, performance, quality of experience and coverage of your voice and data networks, and that of your competitors, before you invest. Discover more about how INOS can help you, here.

Now more than ever, use INOS to benchmark coverage, performance & QoE.

To discuss how our network benchmarking expertise can help your business, please use this link or email sales@DigisSquared.com to arrange a convenient time for an informal conversation.

Keep up to speed with company updates, product launches and our quarterly newsletter, sign up here.

Digis Squared, independent telecoms expertise.

Image credit: Klavs Taimins

Capacity management ◦ Now more than ever, handle unpredictable demand with agility

Across the globe Communications Service Providers (CSPs) and Mobile Network Operators have faced enormous, dynamic changes in capacity and demand this year.

“In this “new normal,” CSPs are leading the effort for remote working, online learning and social distancing.”

Source: Forbes (1)

Home working, with its heavy use of video conferencing and collaboration, combined with a surge in demand for digital entertainment, home studying and intensive use of multiple devices simultaneously, has led to a previously unimaginable surge in demand for capacity on both fixed and mobile networks. The changes in mobile network demand have highlighted difficult to predict anomalies – in many cities, as people stayed at home, significant demand was off-loaded to home wifi networks (Deloitte (2): “some telcos say they have seen a 300% increase in the use of these voice-over-WiFi services.”), in contrast with rural areas and other poorly served broadband-black-spots, mobile data demand has soared.

“The five largest operators in Spain reported a 40% increase in overall IP traffic, a 25% increase in mobile traffic and a 50% increase in mobile voice traffic since the start of the outbreak.”

Analysys Mason (3)

Now that the initial rush to support business employees working from home has passed, more countries are starting to consider slowly re-opening business premises – with staggered start times, and changes in working practice, this will bring with it a new set of behaviours and capacity requirements. But the need to maintain agility in capacity is vital, as countries anticipate lockdowns will be enforced dynamically over the months and years ahead.

Planning ahead

In the short term, service providers are addressing four key challenges,

  • With dynamic changes in customer behaviour, and the lack of revenue from roaming charges, many are experiencing significant pressure on operating expenses, and taking quick business decisions to remove costs
  • Capital expenditure plans are being rapidly re-assessed to ensure they are re-prioritised to meet the new revenue and business continuity needs
  • Re-assessing supply chains, in terms of equipment procurement issues, safe social distancing in the workplace, and staff absence levels
  • Rapidly addressing revenue and cash management, as economies global experience a massive downturn

In the longer term, plans need to be made to manage the “next new normal”, as changes in society and working patterns continue to evolve. At Digis Squared we believe this next phase is even harder, as “Business As Usual” will mean a constant need for agility and flexing to meet demand,

  • Accelerate digital transformation: use AI and RPA to manage higher customer service call volumes to support remote working, and handle mundane repetitive tasks and digital self-service via automation
  • Revise Business Continuity Plans: review assumptions, re-plan and re-scale
  • Accelerate 5G deployment and integration to better handle high demand dynamically
  • Implement autonomous capacity management, to ensure that your mobile networks work efficiently.

“…the way to consider a crisis of this magnitude is to identify three phases: Respond, Recover and Thrive.”

Deloitte (2)

Whilst many short terms solutions have been rapidly implemented, now is the time to ensure they are robust and resilient enough to continue to handle the longer term, and to re-assess Business Continuity Plans.

Autonomous capacity management

We can help communications services providers and mobile network operators to achieve more with your network resources: absorb new traffic demands, and optimize the expansions you need by using Digis Squared’s vendor-agnostic, off-the-shelf solutions.

Use our expertise to dynamically assist your teams

Our areas of focus are,

  • Vendor agnostic capacity modeling for all network technologies (2G/3G/4G/5G)
  • Machine learning algorithms on network data enriched with multiple data feeds from radio access network, Customer Experience Management (CEM), geolocation systems and crowdsourced data
  • Predictive traffic growth based on AI-power algorithms followed by degradation preventive actions and expansions prediction
  • Action-Centric BM reports including KPIs, KQIs and Customers QOEs
  • ROI calculations for network investments

Many of our clients use modular capacity management modules developed by Digis Squared team, with bespoke adaptations if needed, to,

  • Balance the traffic between cells & technologies
  • Recommend soft actions needed
  • Activate & reshuffle sites licenses
  • Capacity enhancement feature recommendations
  • Physical changes
  • Network expansions and reshuffling required

Our teams can use these capabilities to deliver value to service providers and mobile network operators,

  • Start the smart CAPEX journey, and identify pathways to OPEX saving
  • Maximize network investment ROI and help operators make well-informed, data-centred investment decisions
  • Speed-up network capacity plans through our automated-predictive solution

We can assist you right now with our ready-to-go, adaptive-modular capacity management modules, developed by the Digis Squared team to,

  • Balance the traffic between cells & technologies
  • Recommend soft actions needed
  • Activate & reshuffle sites licenses
  • Capacity enhancement feature recommendations
  • Physical changes
  • Network expansions and reshuffling required

Discover more about our Digis-Capacity, AI & ML capabilities.

Now more than ever, capacity management ensures you can handle unpredictable demand with agility.

To discuss how our capacity management expertise can help your business, please use this link or email sales@DigisSquared.com to arrange an informal conversation.

Keep up to speed with company updates, product launches and our quarterly newsletter, sign up here.

“In the words of one the telecom operator we spoke to: ‘ideally we never go back to the way we operated before this crisis’.”

Source: Deloitte (2)

Sources

Image credit: Mike Kononov