The Generation Professionals Group is for utility professionals who work in biomass, coal, gas/oil, hydro, natural gas, or nuclear power generation fields. 

14,439 Members


You need to be a member of Energy Central to access some features and content. Please or register to continue.


In what ways will artificial intelligence and energy storage change the energy sector? (Part 2)

2019 Bilodeau CC BY-SA 4.0 Attribution-ShareAlike 4.0 International

Artificial Intelligence, Energy Storage and the Power Industry: Toward a Smart and Resilient Grid!

The global energy industry faces fundamental changes in the way it generates, sells and distributes energy. And some contradictions in the reaction appears ( There is strong pressure to improve resilience and, at the same time, reduce CO2 emissions. Therefore, methods must be found to manage the growing production of electricity from renewable sources of energy which are unpredictable and dependent on the eccentricity of local weather, or even on the global climate front when we think about the impacts of climate change.

It is more and more clear that there is a global demand for clean, cheap and reliable energy. This is not only for power grid operators but the reliability of the source of the energy and the cost of electricity is also a concern for consumers, for governments and for civil society actors, as well as for business people who all want to please to whether their customers or their constituents.

Artificial intelligence (AI) could be a very useful and even powerful tool for meeting these needs. And, we will see more and more AI applications in the energy sector. Notably, maximizing the growth of green, low-carbon electricity generation through optimal energy storage management is an artificial intelligence application that will have a potentially huge long-term impact.

Aucun texte alternatif pour cette image

The capacity of artificial intelligence to integrate diverse sources of energies including storage

Various forms of renewable sources of electricity appear as successors of traditional coal and gas power plants. However, a key problem with renewable production is its intermittency. A cloudy day or a quiet, windless series of afternoons will reduce production and create power outages. Conversely, too much energy can be generated when not needed. This was the case, in March 2018, Portugal faced sunny and windy days where it produced more renewable electricity than it consumed ( This potential waste or lack of energy means that it is important to maximize the use of energy storage and in all its forms (electrochemical, thermal, mechanical, etc.) It is also essential that this storage can be activated quickly, if we want to minimize the use of backup energy, for example, diesel generators, coal-fired power plants, or other peaker-plants, which are currently used to smooth out the swift dips into peak periods.

Smart storage or "Intelligent Energy Storage" (IES) solutions are needed to manage excessive peaks. AI can be used to predict and make energy storage management decisions. For example, AI could be used to manage electricity shortages by briefly cutting the demand for electricity on the main grid, while it uses storage in entire communities or regions. The use of AI would generate forecasts for electricity demand, production and weather can reduce the need for these safeguards by predicting and managing fluctuations in output. The speed and complexity of this task require advanced artificial intelligence. Artificial intelligence research also studies decision-making with a scale and complexity that begins to surpass that of a human operator. It could be a network of thousands of mixed energy storage units (electrical, thermal, others) installed at consumers, end-users or on highly used sites, such as industrial installations.

A gigantic but sensitive network

This will also add to the safety of supply. In North America, the average age of power plants is over 30 years and that of electrical transformers over 40 years. This deterioration of the transmission system led to the breakdown of the 2003 "Northeast" that affected several interconnected systems in the United States and Canada. This failure left 50 million people without power for several days when, stupidly, an overloaded transmission line collapsed and struck a tree. Such circumstances, which can obviously have cascading effects on the entire regional network and constitute a difficult task for utility companies to manage, could be avoided by better demand forecasts or better response from local networks. to rapid changes.

Aucun texte alternatif pour cette image

AI's ability to “understand” (or decipher) data sets, but also models or patterns in data, and to make very accurate predictions and simulations will increase opportunities for power grid optimization, energy efficiency and even a period of growth in demand.

Artificial intelligence (AI), coupled with many advanced energy storage technologies, when it comes with machine learning, deep learning, and advanced neural networks, can demonstrate tremendous potential for energy transformation and the utility sector. With decarbonisation, decentralization and the deployment of new technologies, utilities, independent power producers and other energy companies are using AI to manage the imbalance in demand and supply caused by the growing share of renewable energy sources.

The customer base has become gigantic. The customer base has grown to hundreds of millions of users, but the overall structure still needs a modern overhaul. It is a vast network of power plants, transmission lines and distribution centers. And all this, less than 140 years after Thomas Edison opened the first US power station, in 1882, in lower Manhattan, to serve the first 59 North American customers. In the United States, this network already includes nearly 5,800 power plants and more than 2.7 million km (almost 1.7M miles) of power lines. It is estimated that, if US total energy demand is expected to increase by 25% by 2050, then by 2040, global energy use is expected to increase by 15.3% (Data extracted from US Energy Information Administration).

In addition to making electrical networks and systems smart and flexible, artificial intelligence algorithms help utilities and energy companies understand and optimize user’s behavior and manage energy consumption. in different sectors in a changing context and environment. 

An extending decentralized production

Another challenge is the emergence and growth of decentralized generation, where private users generate and use their own electricity from renewable sources, such as wind and solar power. This complicates supply & demand oblige utilities to buy surplus energy from private users, who produce more electricity than they consume and send it back to the grid. Since 2010, the use of solar energy has more than tripled and this trend is expected to continue with photovoltaic cells, devices generating electricity from sunlight, reducing costs and increasing efficiency.

Aucun texte alternatif pour cette image

The current systems have generally not been designed to take into account this diversification of energy sources, particularly the increase in renewable resources. For example, in many American jurisdictions, when demand outstrips supply, utilities activate fossil fuel-based power plants, known as "state of the art" power plants, just a couple minutes in advance to avoid a cascading disaster. This procedure is the most expensive and, but also, the most profitable part for these companies. It results in a higher electricity bill for consumers and an increase in greenhouse gas emissions into the atmosphere. These problems will be exacerbated as energy demand is expected to increase substantially in the coming years. To avoid these non-optimal (for the least) operating mode with IES, AI can enable automatic learning algorithms, combined with data on these complex networks and real-time meteorological data (from satellites, ground observations and climate models), to be exploited with the full potential to predict the electricity generated by RES, such as wind, sun and oceans.

Combined with other technologies such as Big Data, the Cloud and the Internet of Things (IoT), energy storage with AI can play an important role in power grid management by improving the accessibility of power sources. renewable energies.

A smart grid with energy storage

To face the various challenges that come up, it appears that one of the key sustainable and reliable solutions will be Intelligent Energy Storage, where artificial intelligence will be the brain. This “Smart grid with energy storage” will continuously collect and synthesize huge amounts of data from millions of smart sensors to make timely decisions on how best to allocate energy resources. In addition, advances made from "deep learning" algorithms, a system in which machines learn by themselves from pattern and anomaly markings in large data sets, will revolutionize demand and supply of the energy economy.

As a result, we will see more and more specialized micro-grids managing local energy needs with finer resolution. These can be combined with new energy storage technologies of various kinds that allow for continuous exchange between local communities, even when extreme weather conditions or other failures affect the wider power system.

On the supply side, IES will shift to a portfolio with a greater energy mix characterized by increased production of renewable resources and minimal disruption due to the natural intermittency associated with these sources, due variable intensity of solar radiation and wind. For example, when renewable energies operate above a certain threshold, due to increased wind strength or sunny days, the grid would reduce its production from fossil fuels, thereby limiting gas emissions. harmful greenhouse effect. The opposite would be true during periods of below-peak renewable energy production, allowing all energy sources to be used as efficiently as possible and relying only on fossil fuels when necessary. In addition, producers will be able to manage the generation of energy generated from multiple sources to cope with social, spatial and temporal variations in real-time demand.

A winning combination

Over the next few years, the IES technologies are expected to increase the efficiency of the renewable energy sector by automating its operations in the solar and wind energy sectors. It will also enable utilities and PPIs to launch new business and service models.

If such a smart grid with energy storage is able to use energy sources, including fossil fuels, in the most efficient way by better integrating renewable resources as these technologies evolve in sophistication and capacity, the entire system may be able to greatly reduce its carbon footprint. Despite this uncertainty about future technological innovations, we can also expect the smart grid system to reduce electricity bills and prevent catastrophic power outages by optimizing supply and demand at the local and national levels.

Aucun texte alternatif pour cette image

Likewise, applications based on the IES can create additional revenue opportunities for the energy and utility sector by:

• Enable software applications to analyze large data sets, identify patterns, detect anomalies and make accurate predictions, or able to autonomously make accurate decisions based on learning.

• Facilitate the active participation of customers in demand response programs by using advanced algorithms and leveraging the blockchain to protect data and enable customer-centric solutions.

• Use predictive analytics ( to improve equipment operation and maintenance and provide for downtime, which can extend the life of the equipment.

For those seeking to influence the future of society, the interface between AI and energy storage is an excellent starting point. Technological innovation is radically changing the way we think about these two industries and their integration is in its infancy. Their synergy can change the world as we never know it and open up opportunities while improving its sustainability... toward a Smart and Resilient Grid!

This Article was first Posted on Linkedin Pulse on March 21st 2019: 


Stephane Bilodeau, Eng., Ph.D., FEC

This is the 2nd article in a series on artificial intelligence, energy storage and the energy industry (you can refer to the first article here:

Stephane Bilodeau's picture

Thank Stephane for the Post!

Energy Central contributors share their experience and insights for the benefit of other Members (like you). Please show them your appreciation by leaving a comment, 'liking' this post, or following this Member.


No discussions yet. Start a discussion below.

Get Published - Build a Following

The Energy Central Power Industry Network is based on one core idea - power industry professionals helping each other and advancing the industry by sharing and learning from each other.

If you have an experience or insight to share or have learned something from a conference or seminar, your peers and colleagues on Energy Central want to hear about it. It's also easy to share a link to an article you've liked or an industry resource that you think would be helpful.

                 Learn more about posting on Energy Central »