Thanks to everyone who encouraged me to finally get this up and running. Thought I would do a post on two of my favorite topics, AI and renewable energy. I’d like to highlight how they overlap both now and potentially in the future. These overlaps come from recent news articles, but I plan to take a deeper dive into each of these topics in future posts.
The Energy Collective analyzed the potential use cases of AI for renewable and utility companies. Although there are numerous use cases, I’ve highlighted three below which can generally categorize the majority of AI applications in renewable energy.
- Renewable management: Where AI runs the majority of renewable forecasting, equipment maintenance, wind and solar efficiency and storage analysis
- Demand management: AI use cases covering areas such as demand response, building energy management systems, overall energy efficiency and DR game theory
- Infrastructure management: Managing the performance of the grid is also getting AI attention. In this area use cases include digital asset management, equipment operation and maintenance and generation management.
CO2 emissions are commonly attributed to industries such as the automobile, aviation or manufacturing industry. What may surprise some people, is that the ICT industry today generates approximately 2% of global CO2 emissions. This is actually on par with the global aviation industry. With expected growth to 4% of the world’s total CO2 emissions in just five years, the greening of ICT is increasing in importance.
Diving into the numbers, recent studies reveal the ICT industry is growing by 30-40% per year which is 30 times its current traffic in 10 years and 1,000 times current traffic in just 20 years. Theoretically, in a decade, ICT could consume 60% of all global energy resources.
Two areas that need to be addressed are energy use by systems and the demands on those systems. AI can have an impact in both cases by identifying and measuring activity at the network level and at the connected device level by sifting vast amounts of data to extract patterns and trends. AI can then be applied to reconfigure the network in real-time to minimize power consumption.
In June 2017, a working paper was released by Meghan O’Sullivan, Indra Overland and David Sandalow with support from Columbia, Harvard and the Norwegian Institute of International Affairs. The topic was the geopolitics of renewable energy.
All three of them describe a future in which the share of renewables of total primary energy is between 30-45% in 2035/2040 and between 50-70% in 2050. With such a large share of global energy, supply chains and global business opportunities with regards to rare earth metals will evolve with the rise of renewable energy. At the same time, energy’s impact on geopolitics will only continue to increase and shift dynamically.
Rare earth elements (including dysprosium, neodymium, terbium, europium and yttrium) are often considered to be critical components of renewable energy hardware. Lithium is also critical for renewable energy technologies. Lithium ion batteries are used to help manage the intermittency of solar and wind power and in electric vehicles. They are also widely used in other industries, including personal electronics. Indium and cobalt are also used in renewable energy technologies including solar panels and batteries.
A country’s geological reserves are not absolute, but a function of factors including: demand; investment in geological exploration; technologies available for geological exploration, extraction and processing, and their costs; introduction of robots and artificial intelligence in mining operations; scale economies at all levels. Countries trying to beef up their geological reserves in these rare-earth metals may prioritize the development of AI and robots into mining operations to increase efficiency.
An alternative to greening conventional energy is to install very big (“grid scale”) batteries capable of storing renewable power to be released when required. This has generated a lot of interest lately. But given the costs of current battery technology, grid-scale storage requires expensive upfront investments.
The U.K. is developing an alternative known as demand-side response. One aspect involves rewarding certain electricity consumers for reducing their usage at short notice. The other aspect of demand response involves asking customers who own equipment that can store power to help balance surges in demand.
Once signed up for grid storage, it should be possible to estimate the useful lifetime of a battery pack or unit by applying prognostic algorithms to its charging/discharging data. Owners will then receive appropriate compensation, plus the added incentive of knowing how long their battery will last. Another line of AI research draws on insights from algorithmic game theory to develop reward/penalty mechanisms that ensure enough customers in the pool are willing to participate, and actually respond when necessary
A recent article from the MIT Technology Review stated big data and artificial intelligence are producing ultra-accurate forecasts that will make it feasible to integrate much more renewable energy into the grid.
For example, wind power is booming on the open plains of eastern Colorado. AI is often used to record the wind speed and its own power output. turbines records the wind speed and its own power output. Every five minutes they dispatch data to high-performance computers 100 miles away at the National Center for Atmospheric Research (NCAR) in Boulder.
The forecasts are helping power companies deal with one of the biggest challenges of wind power, its intermittency. Using small amounts of wind power is no problem for utilities. A utility that wants to use a lot of wind power needs backup power to protect against a sudden loss of wind. These backup plants, which typically burn fossil fuels, are expensive and dirty. But with more accurate forecasts, utilities can cut the amount of power that needs to be held in reserve, minimizing their role.