Challenges Shaping Strategy
The impact of logistical realities on the African towerco
Despite its proliferation across a wide range of industries, artificial intelligence remains something of an enigma: the notion of reshaping sectors in a way that doesn’t rely on human nature is a lot to get your head around. Yet, the speed, accuracy, efficiency, and predictive benefits of AI have converted it from being a ‘nice to have’ option, to a ‘must have’ tool to futureproof business. The telecommunications sector has been built on innovation and keeping ahead of the curve, yet it is still exploring the full potential of this crucial tool.
AI is a set of smart, focussed systems that can augment the best skills in the mobile tower industry that is a ‘must have’ to better manage future challenges to come. In order to adopt the level of automation AI brings at scale, there is a need to better understand AI’s role as an augmenter and enricher of current people, processes and projects, not as a replacement.
Whilst AI cannot replace the human intervention in those daily problem- solving challenges that human experience will always be able to deal with more suitably, AI is better suited to deal with peripheral and repetitive tasks, that are often overlooked or put on the backburner while human workers continue to tackle operations that can more accurately be conducted by machines.
If businesses were to truly introspect on how much time they ask their workers to spend on sifting through granular information across spreadsheets and corresponding data points on numerous systems, then the results would likely be shocking. For every task revolved around forecasting, data assimilation, risk analysis, and a host of additional technical or administrative functions relying on human guesswork, the overarching question is: ‘why not AI?’
PowerX’s AI solution helps clients save millions of dollars in operational savings, and as much as 50% in CO2 emission savings.
To illustrate this better, PowerX team continuously looks at how AI can optimise power sources mix even in cases where, relying on manual interventions, teams of cell tower experts optimise to perfection the different power sources equipment and their operations using set threshold rules.
In the first instance, AI identifies sites where existing solar panels installed are able to generate more solar power during the course of the day than the battery capacity that exists on those sites is scheduled and able to store. The typical profile of solar energy that is wasted on sites is illustrated below:
AI identifies in, real-time, all sites with extra spare energy that can be extracted out of the battery and solar assets already available on sites. By using the spare energy identified, AI also highlights the reduction of Diesel Generator (DG) runtime it can achieve as illustrated at individual site-level below:
Without AI automation, manually configured site operations rely on set thresholds to determine the mix of power available on sites. These are typically set to switch power sources at set times in the day and comply with generic rules to manage autonomy thresholds for all sites. These processes require hours of manual inputs and optimisations to squeeze optimum performance on sites. The illustration below shows how a manually optimised rural site would typically use power sources on a daily basis:
AI dynamic control is able to switch remotely in real-time the optimum power source based on multiple inputs and predictions to ensure the site remains fully autonomous at any point in time. Such real-time inputs include: assets measured capacity, weather forecasts, historical patterns, actual load, state of health, maximum autonomy available in the assets etc. As a result, under AI dynamic control, the lowest source of energy was chosen at all times to optimise for full site availability at lowest cost. The illustration below, shows the daily mix of power sources for the same site as above over the same period but under AI dynamic control.
As illustrated, AI significantly reduces the diesel generator runtime as it maximizes the power available in the other energy sources installed on sites. The net effect of these optimizations result in a direct increase in the contribution made by greener or cheaper power sources, such as solar, to power each site over time driving continuous optimization of the cost per kWh at each site. These optimizations are tailored for each individual site for thousands of sites in real-time, achieving unprecedented economies of scale.
AI automation takes care of peripheral and repetitive tasks without fail and at a scale impossible to be achieved with human interventions. In exchange, time is freed up for manual interventions to be focused on the more difficult problem-solving tasks that only human decisions can solve.
With AI-driven operations, granular site-level of optimisations and automations happen in real-time, 24/7 across thousands of sites with minimum human intervention.