Maximising renewable energy investments with artificial intelligence

Muhammed Malik, CEO and Founder, NeuerEnergy

Urgency to reduce carbon emissions is accelerating, with the UK government recently committing to a 68% reduction by 2030, on the path to achieving net zero by 2050. Currently, the public sector accounts for 3% of the UK’s carbon emissions and has an estimated annual carbon footprint of over 13 MtCO₂e. As such, public sector bodies are increasingly being tasked with leading the shift to a low carbon economy.

However, the tricky part is staying on top of a continuously evolving ecosystem made up of disparate systems and a diverse range of providers. For example, in the UK specifically, the government’s Ten Point Plan for a Green Industrial Revolution is advancing offshore wind, driving growth of low carbon hydrogen, and delivering new and advanced nuclear power, meaning investment in these areas will progress swiftly.

For energy managers in the public sector, their goal for 2021 is clear: save their organisation money whilst continuing to transition to high-quality renewable energy sources. Yet, transitioning schools, universities, hospitals, government offices and military facilities to more sustainable energy is no easy feat, and there are multiple factors to consider, particularly around cost and risk. Even with the financial support available – including grants from the Public Sector Decarbonisation Scheme (PSDS) – the sector has a seemingly mammoth task ahead of it.

While it’s true that manually selecting renewable energy providers can require a great deal of marketplace analysis and time spent on RFPs, fortunately, advances in technology can simplify and streamline the process. Through the use of AI-based algorithms that build and monitor partnerships with solar, wind or carbon reduction energy providers, energy managers can easily uncover new opportunities with local suppliers that meet their diverse energy demands while reducing carbon emissions, without labour-intensive research. So, how can they put this into practice?

1. Integrate energy data for a ‘single source of truth’:

Energy data is often stored independently by individual facilities, in disparate systems. As such, energy managers should harness AI technologies to pull all that information together, which is possible through simple API-based data integrations, enabling them to better evaluate the existing energy mix across multiple facilitates and management systems. With disparate data sets connected together in a single platform, energy managers can then gain a clear understanding of their purchasing workflows, including current power purchase agreements (PPAs), and  combine that information with outside data sets to deliver a full picture of the green energy options available to their organisation.

2. Automate renewable energy purchasing:

Traditionally, PPAs encourage buyers to use just one supplier – meaning organisations tend to rely on low risk, high volume providers. But this approach often takes months of manual research and RFPs. However, with intelligent AI capabilities, energy managers can standardise the energy acquisition process to maintain a more dynamic and diverse energy portfolio. AI algorithms, for example, can produce the perfect provision of green energy from low-risk high-volume suppliers, while standardising partial fulfillment agreements with independent initiatives and new developments, furthering the positive impact of public sector green energy investment across the growing renewable grid. In turn, by grouping PPAs and automating the complex legal workflow, public sector bodies will save a magnitude of time, money and personnel.

3. Manage risk in real-time:

AI algorithms can leverage numerous data sets via one platform, meaning the commercial and environmental implications of various scenarios can be understood in real-time. With this information in one place, AI algorithms can then suggest actions to ensure energy provision is maintained to minimise risk to organisational operations. For example, sensor and climatic data can be correlated to predict energy needs ahead of time, according to seasonal variations, and align this energy demand with grid load and outages. AI algorithms can also analyse risks that are inherent with new technologies, such as intermittent energy generation, and suggest actions accordingly.

4. Streamline emissions reporting:

AI models can provide insight into the current and potential results of renewable energy initiatives, enabling energy managers to make informed decisions that will help them to stay on track with sustainability targets. Real-time intelligence can be delivered both quantitatively, with reportable checklist-style scoring, and qualitatively, with a more in-depth commentary on progress. Outcomes can then be cross-referenced across inter-connected targets to deliver short-term and long-term insight, and to report to the relevant parties, enabling a more transparent and accountable approach to emissions reporting.

Looking ahead, pressure will not ease on public sector organisations to minimise their emissions and lead the way to a more circular economy. The key starting point is to gain a complete view of internal and external data, ideally via a single platform. Only then will energy managers be able to automate and standardise the renewable energy acquisition process, whilst managing risks and costs. This ‘single source of truth’ will be vital for energy managers to manage a more diverse renewables portfolio, while also equipping them with the necessary information to prove that they are driving truly impactful results for their public sector organisation.