Businesses and consumers agree that sustainability must be an imperative in how organisations operate today.

The assumption is that change can only happen slowly, as infrastructure evolves and is gradually updated.

However, leading manufacturers are discovering that introducing a dynamic Artificial Intelligence (AI) model supported by edge computing technology into their current environments can significantly reduce energy use – cutting carbon emissions and initiating a fall in energy costs of between 5-15% within a few months.

Looking for ways to reduce energy use is not new to manufacturing organisations – but creating scalable ways to do it is. Historically, identifying where and how to reduce wastage has often been complex and quantifying the savings was difficult. Many organisations find that reporting on the initiatives is hard, or that if they do produce reports, they can’t explain the audit trail.

There’s a gap between the intention to reduce wastage and the ability to make it happen

In reality, most current equipment isn’t running at optimal levels, so there are significant energy savings to be made. Additionally, keeping existing equipment avoids the environmental impact of creating new replacements and disposing of the old. In many cases, the more environmentally friendly option is to run the current equipment efficiently to the end of its life.

Optimising performance is fundamental to reducing energy use and increasing sustainability in a manufacturing environment. AI-powered algorithms make it possible to identify and adjust the variables that impact energy consumption – but they can’t be applied without the support of an edge computing solution.

The algorithms need real-time performance data from sensors on equipment. ‘Real time’ is critical here.

In effect, sending data to central clouds or data centres for processing introduces a latency lag, so edge computing moves the processing closer to the source of data generation and also connects the sensors to the wider network so that only data highlights need to be sent to the core. Distributed data centres or clouds sit at the edge, often at the customer’s premises, creating a platform that can process content rapidly – essential to turning data into better insights, actions and results, and to doing it faster.

With an edge computing solution in place, manufacturers can quickly start fine-tuning their performance using an AI-driven sustainability app.

An effective app will bring together real-time data from sensors and edge devices, machinery control settings, databases, external data and energy bills to identify the variables that impact energy consumption.

It will then plot an Energy Efficiency Index (EEI) to look at past processes, comparing them to see which were the most energy efficient and why. It should also compare sites and equipment to look for best practice, as well as automatically training and deploying AI models to identify strategies for reducing energy consumption and carbon emissions.

Look for a sustainability app that shows the specific EEI score for each production run or process, with the ability to drill down and see how it could have been improved and what the individual saving would have been in money and carbon.

The end result should be recommendations that are updated every few hours or every day to keep production in the operational sweet spot that will keep energy consumption as low as possible.

Our Edge Compute solution brings intelligent data processing closer to where it’s created and supports sustainability by enabling the data analysis that identifies more energy efficient ways of operating. Together with our sustainability app, it’s been proved to reduce energy costs by between 5-15%.