By Eamonn Ryan
The following article derives from a panel discussion at the Solar & Storage Africa Live conference and expo held in Gauteng in March, on the topic ‘From crisis to capacity: how SA businesses are using storage to survive and thrive’.
The panel consisted of:
- Thabisile Kubheka, Smartgrid SA director of stakeholders engagement and community liaison
- Lydia Kapangila, African Youth in Energy
- David Raphael, SOLINK
- Wale Odugbesan, Royal Power & Energy
- Pitso Sekhoto, Eskom
This is part two of a three-part series.
While the promise of smart solar is compelling, the reality on the ground tells a more complex story. Many installed systems are failing to deliver expected performance, leaving significant energy and financial value unrealised. Building on the discussion around intelligent systems, the panel turned its focus to a critical question: how can data, connectivity and advanced analytics be used not just to manage solar assets – but to unlock their full potential?
Beyond individual solar installations, the session explored how IoT and AI are transforming grid-level operations. The integration of distributed solar systems into national or regional grids requires real-time co-ordination between generation and demand. IoT devices provide the necessary visibility into system performance, while AI enhances forecasting accuracy on both the supply and demand sides.
At the substation and grid control level, automation systems are increasingly being used to support grid stability. These systems help manage the variability of renewable energy by enabling faster response times and better co-ordination between distributed energy resources. Previously, solar installations primarily injected power into the grid when available, but modern systems are becoming active participants in grid balancing and stability.
This evolution is particularly important in industrial contexts, where energy reliability and predictability are critical. AI-enhanced forecasting combined with IoT-based monitoring allows grid operators and industrial users to better align energy supply with operational demand, improving both efficiency and resilience.
System performance challenges and the case for digital twins
A striking insight from the session was the acknowledgment that a large proportion of installed solar systems are not performing optimally. It was estimated that only about 40–60% of systems operate at expected efficiency levels. This performance gap represents a significant financial and energy loss across industrial deployments.
For example, a nominal 1MW solar installation may only deliver around 600kW under real operating conditions due to issues such as environmental conditions, equipment degradation or suboptimal maintenance practices. Over time, this shortfall results in substantial revenue and energy losses.
To address this challenge, the concept of digital twins was presented as a key innovation. A digital twin is a virtual replica of a physical solar installation that continuously mirrors its performance in real time. By aggregating data across multiple sites, digital twins enable operators to detect patterns, identify recurring faults and predict failures before they occur.
This also introduces a network effect: if one site detects a specific issue – such as dust accumulation, cable degradation or grid instability – other connected sites can be alerted proactively. This shared intelligence allows for system-wide optimisation rather than isolated troubleshooting, significantly improving operational efficiency across portfolios of assets.
Financial implications of underperformance
The discussion also made clear that system inefficiency is not just a technical issue but a major financial one. Small percentage losses in energy output translate into significant cumulative revenue losses over time.
When scaled across multiple industrial sites, even modest underperformance can result in large financial amounts in lost value per site annually. This reinforces the importance of continuous monitoring, predictive maintenance and system optimisation strategies. The cost of not maintaining solar assets properly is therefore often far higher than the cost of implementing intelligent monitoring systems.
Summary
A key takeaway was that underperformance is both a technical and financial challenge – but also a major opportunity. With tools like digital twins, predictive analytics and IoT-enabled monitoring, operators can shift from reactive maintenance to proactive optimisation. As solar systems become interconnected, shared intelligence across sites creates powerful network effects, enabling smarter, more efficient energy ecosystems at scale.