As governments and enterprises seek to combat climate change, one of the most difficult challenges will be reducing carbon footprints in hard-to-abate (HTA) sectors like heavy industries, commercial transport, aviation, and shipping. These industries remain heavily reliant on fossil fuels, and substituting more climate-friendly feedstocks and energy sources cannot be achieved easily without affecting the quality of output. Progress so far has been slow: According to the International Energy Agency, 68% of the industrial sector’s global energy mix was supplied by fossil fuels in 2021 — only a minor reduction from 72% around 12 years ago.
These industries can remove some of their greenhouse gas emissions through carbon capture, utilization and storage (CCUS) or nature-based processes, and they can reduce energy use through greater efficiency. However, the impacts of these interventions are inherently limited. That leaves HTA industries with one option to achieve the bulk of their emissions reductions: largely replacing fossil fuel energy sources and feedstocks with renewables.
This will not be easy, but HTA sectors can take one technology-driven approach to ease their energy transition pathways: advanced data modeling. By embracing scenario modeling, demand forecasting, and optimization engines, enterprises in HTA sectors can gain insights to make decisions that achieve both planetary and organizational sustainability.
Shortlisting Clean Energy Options: Scenario Modelling
Scenario modelling is an invaluable tool as enterprises explore a wider set of energy transition options and shortlist them based on industry processes and end uses. At its core, it can consider variables such as technology suitability, flexibility (short- and long-term availability of clean energy/feedstock material, pure vs. blended applications, etc.) and — for feedstocks — end-use factors such as the safety, integrity, and functionality of the final product.
For some industries (see image below), fossil fuels combined with CCUS may remain the most applicable energy source in the near term, though all industries can and should begin experimenting with other options. And while industry-wide scenario models can provide general guidelines, the exact applicability of various energy sources will depend on geography- and company-specific factors.
Demand Forecasting and Optimization Modelling for HTA Sectors
Once the most attractive potential energy and feedstock options have been identified, enterprises in HTA sectors need a quantitative way to model how the new sources and delivery mechanisms will be orchestrated. Such a model needs to take into account region-specific pricing and capacity limits related to various clean energy options. In addition, the model will need to identify an appropriate balance between reducing end-use energy consumption, reducing cost, and maintaining the high throughput and high-quality output that will drive new business and increase revenue.
This modelling effort begins with a demand forecasting model predicting the enterprise’s future demand for each general type of energy or input (electricity, heat, hydrogen, etc.). The modelled demand is then given as an exogenous input to an AI/ML-based optimization modelling engine. The modelling engine suggests the optimal way to utilize renewable energy sources in order to achieve both a sustainable cost and a significant reduction in the resulting carbon footprint.
Optimization models have the benefit of significant flexibility and applicability, given that most energy pathways will require navigating though complex but ultimately limited sets of variables.
In the context of commercial transport, optimization models could inform decisions about the placement of EV charging stations to simultaneously meet future demand and reduce overall charge station cost (setup and operation) while improving revenue. For steel production, an optimization model could evaluate various energy options with respect to their flexibility, interoperability, intensity, cost of unit production, and reliability. Such a model design would require a linear or integer programming-based approach to set an objective function that would arrive dynamically at the right energy mix, taking into account factors such as market and industry dynamics or anticipated regulatory factors.
In the future, AI-driven optimization modelling use cases for sector-specific energy transition pathways could also include:
A Path Toward Abating the Hard-to-Abate
According to the IEA, alternate fuel and energy sources will have to make up an additional 10% share of the industrial energy mix by 2030 to be on track for reaching sectoral net-zero emissions targets in 2050 and beyond.
As hard-to-abate sectors pursue energy transition ambitions and net-zero objectives, numerous emerging technologies will need to be rapidly deployed at scale. Increasingly, new solutions will apply even in hard-to-abate sectors. Even so, companies in those areas will need data-driven approaches to decide how and when to make numerous micro-transitions as they re-balance their global climate impacts.
The attractiveness of each new energy option will shift in real time as pricing, supply, and demand fluctuate and new sources come online. Fortunately, data modelling approaches will become an indispensable tool as companies in HTA industries chart their energy transition pathways and strive to achieve substantial emissions reductions while maintaining successful business models.
Sudhansu Choudhury, Consulting Partner, Wipro Energy Downstream Domain
Sudhansu is a senior consulting partner in the energy domain. With 24 years of experience in energy industry and IT domain consulting, he drives solutions and services for global energy clients. He is focused on building capability at scale, orchestrating new age solutions, developing thought leadership and driving customer-centric transformation across product supply chain, customer and mobility, and low-carbon energy. He has helped energy enterprises advance business capability and deliver business solutions and transformation initiatives within their downstream and new energy business.
Pranav Kolachana, Strategy Consultant
Pranav is a consultant with an energy domain background and more than 8 years of experience in energy industry and IT consulting. His focus is on strategy, organizational transformation, and business model development, and is informed by his work on large projects with oil and gas supermajor clients.
Eldo Kuriakose, Managing Consultant, I&E DE – Architecture
Eldo is a managing consultant in the energy domain. His core areas of focus are cloud-centric application transformation and optimization techniques that leverage data-oriented approaches and modelling solutions in the areas of low carbon energy, energy transitions, supply-chain optimizations, fleets and logistics, data compliance and security standards, AI/ML, and IoT-based integrations. He is actively participating in the development of cutting-edge, cloud-agnostic applications in the energy industry.