Machine learning, microgrids and new models for energy management – Economist Impact

Report on AI and Microgrids in Advancing Sustainable Development Goals

Introduction: The Energy Transition and Sustainable Development

The global energy landscape is undergoing a fundamental transformation, a shift critical to achieving the 2030 Agenda for Sustainable Development. According to Peter Weckesser, Chief Digital Officer at Schneider Electric, this transition is characterized by the rise of the “prosumer”—entities that both produce and consume energy. Each prosumer, regardless of scale, effectively operates as a microgrid, creating a decentralized energy system. This evolution is central to advancing several Sustainable Development Goals (SDGs), particularly those related to energy, infrastructure, and climate action.

Decentralization: A Catalyst for SDG 7 (Affordable and Clean Energy)

The move towards a decentralized and dynamic energy system directly supports the objectives of SDG 7 by making energy more accessible, reliable, and clean. However, this new paradigm introduces significant management complexities for both prosumers and grid operators.

• Forecasting Demands: Stakeholders must accurately forecast bidirectional electricity flows—how much energy a microgrid will draw from the network and how much it will supply back.
• Grid Stability: Without effective management of these distributed control points, the stability of the main electricity network is compromised, threatening the goal of reliable energy for all.
• Infrastructure Integration: The integration of new assets, such as Electric Vehicle (EV) infrastructure, presents both an opportunity for large-scale energy storage and a management challenge.

Systemic Challenges and the Imperative for Resilient Infrastructure (SDG 9 & SDG 11)

The complexity of the new energy system represents a significant control system challenge, demanding innovation in line with SDG 9 (Industry, Innovation, and Infrastructure) and SDG 11 (Sustainable Cities and Communities). Building resilient and intelligent infrastructure is paramount.

1. Inadequacy of Traditional Models: Classical approaches to creating demand models are insufficient to manage the current and future complexity of the grid.
2. Scalability Issues: As the energy transition accelerates, new prosumers and nodes will be added daily, making manual maintenance of grid models an unsustainable task.
3. Optimization Requirement: A substantial optimization challenge exists both within individual microgrids and across the wider energy system to ensure efficiency and stability.

Artificial Intelligence: The Key Enabler for Sustainable Energy Management

Artificial Intelligence (AI) is identified as the critical technology to navigate these challenges and unlock the full potential of a decentralized grid. Mr. Weckesser describes AI as “the most powerful tool for the demand-side management of energy consumption,” directly contributing to SDG 7.3 (double the global rate of improvement in energy efficiency) and SDG 12 (Responsible Consumption and Production).

• Asset Optimization: AI will empower all stakeholders, from homeowners to system operators, to optimize their assets by providing guidance on when to consume, store, or dispatch electricity.
• Predictive Management: High-performance AI can manage the complexity of forecasting and control, ensuring grid stability and efficient resource allocation.
• Climate Action (SDG 13): By enabling greater integration of renewables and optimizing energy use, AI-driven management is a core tool for climate action, helping to build a low-carbon energy system.

Analysis of SDGs in the Article

1. Which SDGs are addressed or connected to the issues highlighted in the article?

1. SDG 7: Affordable and Clean Energy
   • The article’s core theme is the “energy transition,” which involves shifting to more sustainable and decentralized energy systems like microgrids. It discusses managing electricity from various sources, which is central to ensuring access to clean energy.
2. SDG 9: Industry, Innovation, and Infrastructure
   • The text highlights the need for new infrastructure (microgrids, EV charging stations) and advanced technology (“high-performance artificial intelligence”) to manage the complexity of the new energy landscape. This points to upgrading infrastructure and adopting innovative, clean technologies.
3. SDG 11: Sustainable Cities and Communities
   • The concept of “prosumers” and “microgrids” managing electricity within buildings and communities is fundamental to creating sustainable urban environments. Efficient energy management at the local level contributes to reducing the environmental impact of cities.
4. SDG 13: Climate Action
   • The “energy transition” described is a primary strategy for climate change mitigation. By creating a more stable and efficient grid that can handle decentralized renewable energy sources, the technologies discussed directly support actions to combat climate change.

2. What specific targets under those SDGs can be identified based on the article’s content?

1. Under SDG 7 (Affordable and Clean Energy):
   • Target 7.2: “By 2030, increase substantially the share of renewable energy in the global energy mix.” The article’s focus on “prosumers” and “microgrids” implies the integration of decentralized renewable energy sources (like solar panels) into the main grid.
   • Target 7.3: “By 2030, double the global rate of improvement in energy efficiency.” The article explicitly mentions that AI is “the most powerful tool for the demand-side management of energy consumption,” which is a direct reference to improving energy efficiency.
2. Under SDG 9 (Industry, Innovation, and Infrastructure):
   • Target 9.4: “By 2030, upgrade infrastructure and retrofit industries to make them sustainable, with increased resource-use efficiency and greater adoption of clean and environmentally sound technologies…” The article discusses the fundamental change in the “future energy landscape,” requiring new infrastructure and the adoption of AI to manage it sustainably.
3. Under SDG 11 (Sustainable Cities and Communities):
   • Target 11.b: “By 2020, substantially increase the number of cities and human settlements adopting and implementing integrated policies and plans towards inclusion, resource efficiency, mitigation and adaptation to climate change…” The management of microgrids and EV infrastructure as described are integrated plans for resource (energy) efficiency and climate change mitigation at a community level.
4. Under SDG 13 (Climate Action):
   • Target 13.2: “Integrate climate change measures into national policies, strategies and planning.” The technological solutions discussed, such as AI-managed grids and EV storage, are key components of strategies to manage the energy transition and thus mitigate climate change.

3. Are there any indicators mentioned or implied in the article that can be used to measure progress towards the identified targets?

1. For Target 7.2 (Renewable Energy Share):
   • An implied indicator is the amount of electricity a microgrid supplies back to the network. This measures the contribution of decentralized (and often renewable) energy sources to the overall grid.
2. For Target 7.3 (Energy Efficiency):
   • The article implies that AI will provide answers to “when prosumers should consume, store or dispatch electricity.” An indicator would be the level of optimization in energy consumption achieved through AI-driven demand-side management.
3. For Target 9.4 (Sustainable Infrastructure):
   • The article states that “New prosumers and new nodes in the grid will be added daily.” A direct indicator is the number of new microgrids and EV storage systems integrated into the energy network.
4. For Target 13.2 (Climate Change Measures):
   • A key challenge mentioned is preventing grid instability. Therefore, an indicator of successful implementation of these climate measures would be the stability of the main electricity grid while managing an increasing number of decentralized control points.

4. Table of SDGs, Targets, and Indicators

Source: impact.economist.com