The stability of power grids supplying energy to our homes and businesses is emerging as a critical success factor for maintaining both physical and economic security. Regardless of the electric grid size—a microgrid with several hundred users or a regional grid with millions of users—grid complexity is on the rise. Trends such as the sharp increase in Internet of Things (IoT) devices and digital solutions   that tax large and small grid capacities, a growing installed base of renewable energy generation, and the proliferation of distributed energy resources (DER) behind the meter at the grid’s edge, are all contributing to this complexity.   Unfortunately, the electric design of existing grids has not been optimized to accommodate these new behaviors. Local and national grids are experiencing significant changes in energy flows. In the past, the energy consumption pattern was easy to interpret. At around 6:00 p.m. rates of energy consumption were high and not much energy was consumed during the night. Now, businesses, hospitals, and homeowners, for example, may be producing energy at midday with solar panels. An increasing quantity of electric cars are also consuming energy in the middle of the night to recharge their batteries. Energy prices that sometimes change minute-by-minute are also altering where and when enterprises choose to consume the most energy. This makes the flow of energy within grids more volatile. Instead of traditional top down energy distribution, grids must deal with bidirectional energy flows which change throughout the day and night.   To accommodate the changing nature of the grid, stakeholders are investing in both technology and manpower to better forecast short-term evolution of electricity in their operation. Without accurate consumption forecasting, nodes within the grid can become saturated with energy demand that is too high which, in turn, can lead to grid failures and blackouts.     Why AI Digital Solutions Can Improve Forecasting Accuracy   This is where we at Predictive Layer, a Schneider Electric Technology Partner, offer support.  Electrical utilities and microgrid managers need to forecast, with high accuracy and speed, short-term grid energy consumption across the geography of their grids. We have developed an artificial intelligence (AI) engine   to address the new layers of grid network complexity.   Today most large grids deal with the challenge of energy consumption forecasting by assigning teams of mathematicians to automate and scale the forecast. Should the parameters of energy consumption change—an extreme weather event, or a societal event where many people are forced to work from home—those complex mathematical models have to be rapidly reworked in order to align with the new reality.  When thousands of grid network nodes are involved, the task becomes too complex to execute in a rapid fashion—even for the best mathematicians. The task is also challenging for microgrids and smaller local grids who typically have few human resources to dedicate to forecasting.   An AI-driven forecasting engine learns from both past energy consumption patterns and from real time live situations. For example, the changes that are taking place within a grid (like the addition of new transformers in a location) and the intricate nuances in energy consumption demand automatically are fed into the model on an ongoing basis. This includes data from transformers, information about the behavior of subscribers connected to the network, and information surrounding weather-related and calendar date-based patterns of consumption.     Benefits Include Less Downtime and Lower Operational Costs   The AI engine learns how to better forecast what is happening every day, everywhere within the confines of the grid, and continues to get smarter as it processes more data. At each point of the day or night it can generate, on behalf of grid operators, local schedules of how much energy should be delivered to designated locations and expected volumes of energy coming in or out. The AI forecasting tool also automatically reconfigures itself as changes occur across the grid. If a new enterprise suddenly turns the lights on in a new facility within a geography, the engine can recalculate that the energy consumption peak will now occur at 4:00 p.m. rather than at 6:00 p.m. in that area.   Instead of a team of people generating 10 forecasts of what is happening in each of their regions, the software can generate thousands of such forecasts in minutes. These forecasts can account for every locality within the grid. (In New York state, for example, there may be 10,000 transformers in the entire network that distribute energy to users.)   The benefits of having access to such an automated system include less network downtime, better operational management and cost control, and higher efficiency of electricity distribution. The tool also makes it easier to manage a crisis where rapid changes in consumption require immediate actions. The goal is to sustain the level of customer expected quality and uptime regardless of the changes that are taking place across the grid.   -----------------------   Originally posted on   SE Blog & Authored by Olivier Cognet   About the author:  Oliver Cognet, CEO, Predictive Layer, is a business leader, corporate developer, and entrepreneur. He has 25+ years of experience in High Tech, Software Development, and Telecom markets focusing on enterprise and consumer markets. Mr. Cognet knows that technology and innovation can help businesses better understand the behavior and needs of consumers, thus helping businesses to grow. Predictive Layer brings the full power of machine learning artificial intelligence (AI) to businesses so they can simply and intuitively model and establish forecasts and predictive analytics of their key target indicators.   ... View more

As the energy marketplace has grown more complex, energy producers, grid operators, and consumers require more intelligence and faster data analysis to interpret pricing patterns. Producers need to know how and when to maximize their energy output during times of the day and week when pricing will work the most to their advantage. Consumers need to accurately perform short-term forecasts of both their consumption and pricing to optimize their purchasing power.   Part 1 of this two-part blog series “Changes in Energy Resources Marketplace Behaviors Usher in New Era of AI-driven Price Forecasting” reviews the reasons why the marketplace has evolved and explains how new energy trends are impacting pricing complexity across the industry.   This blog post (Part 2) highlights some of the advantages utilities and other energy stakeholders can accrue when they deploy an AI-driven forecasting digital solutions   model.   When compared to classic mathematical forecasting models, automated AI models can forecast consumption and production with 20 percent to 30 percent more precision – which leads to direct bottom line savings. In addition, field studies also determine that AI models prevent more large errors than do classic models.     Unique Abilities of AI Digital Solutions Tools Act as Accurate Differentiators   We at Predictive Layer, a Schneider Electric Energy Management Technology Partner, have developed an AI system to help large enterprises, traditional utilities, and producers of renewable energy resources to better forecast energy consumption and pricing so that customers can save money through smarter energy choices.   Listed below are some of the reasons why energy stakeholders are investing in such AI-driven forecasting digital solutions:   Global application Many countries today have created their own specific energy demand, supply, and pricing rules. Besides providing energy supply and demand forecasting, AI tools also can learn the unique characteristics of the pricing models of each of these local markets. People who understand these local pricing models are very difficult to replace when they retire. The AI model provides an insurance policy that pricing knowledge is retained and put to good use.   Access to a richer data pool AI models directly access multiple sources of information, including Transmission System Operator (TSO) energy balancing reference information, multiple weather forecasts, pricing alerts, market prices published in real time, published client activity plans (e.g., vacations, holidays, major events) and any published signals on open platform forums like Schneider Electric Exchange. This collection of data enables unique precision and provides stakeholders with enough response time to adjust to marketplace changes.   Increased savings AI models consider all the variables at play and propose the best purchase or trade plan for the upcoming weeks, months, and quarters. This enables savings of 5% to 10% when compared to exercising a standard purchase plan approach. These gains are possible because the machine learning aspects of the AI tool recompute models and automatically adapt to new patterns in the marketplace much faster and much more accurately than a human remodeling, especially, if the individual has to manage multiple forecasts simultaneously.   Self-monitoring abilities AI models are constantly self-monitoring the health and accuracy of their own forecasting model. They also suggest the integration of additional inputs that can continue to sharpen the accuracy of the model thereby further reducing risk for error as time goes on. Organizations that have deployed our AI solution in the field over the last 18 months have developed enough confidence in the tool that they now rely on it as their main resource for pricing-related decisions. Only automated alerts surrounding anomalies are sent to a human manager. Such automation allows the forecasting team to be freed up to both further scale their forecasting systems and to build in more resilience to enable the servicing of new opportunities.   Resources on Artificial Intelligence Tools To learn more about how artificial intelligence tools can better manage grid consumption forecasting, read Part 1 of this blog series ”Changes in Energy Resources Marketplace Behaviors Usher in New Era of AI-driven Price Forecasting”. You can also find our offers on the Schneider Electric Exchange Shop.   -----------------------   Originally posted on   SE Blog & Authored by   Olivier Cognet   About the author:  Oliver Cognet, CEO, Predictive Layer, is a business leader, corporate developer, and entrepreneur. He has 25+ years of experience in High Tech, Software Development, and Telecom markets focusing on enterprise and consumer markets. Mr. Cognet knows that technology and innovation can help businesses better understand the behavior and needs of consumers, thus helping businesses to grow. Predictive Layer brings the full power of machine learning artificial intelligence (AI) to businesses so they can simply and intuitively model and establish forecasts and predictive analytics of their key target indicators. ... View more

The energy provider marketplace is rapidly changing. Ongoing deregulation has pushed many utilities to develop new commercial offerings that provide both enterprises and households with increased contractual flexibility. In most European and Asian countries and in the United States, clients can now potentially receive proposals from 10 or more utility providers. The ongoing energy transition also opens the market to new producers who generate their energy from very different sources. Renewable energies such as solar, wind, and hydro complement existing fossil fuel energy resources and now produce up to 25 percent of the total production during certain periods of the year. Renewables address a marketplace need for low carbon power generation and sustainable energy development.   These types of marketplace variables significantly add to the complexity of forecasting energy consumption behaviors across grids. As a result, the ability to forecast energy prices using traditional methods becomes less accurate, and grid operators have a more difficult time remaining profitable. To address this issue, grid operators can now turn to AI-driven   technologies to forecast energy prices.       Energy Consumption Pattern Changes Impact Pricing Energy consumption patterns have also changed. Enterprises and households now have more control over how and when they consume energy. This new-found flexibility allows them to lower their cost of consumption.  In some cases, they may even act as temporary energy producers when using their own solar panels. They are also shifting their energy consumption to periods of the day when energy prices and overall energy demand is lower. Retailers and offices, for example, control their lighting, and channel the intensity of their heating or cooling to times of the day or night when prices are lower. Residential homes are also starting to use devices like smart thermostats to better control their heating and cooling and can schedule the recharging of their electric vehicle (EV) batteries at night when rates are low. For the energy producers who support these customers, the traditional top/down model of managing a grid is no longer a sustainable energy business model.   Market and Lifestyle Changes Alter Electricity Pricing Mechanisms In this context of changing regulations, power sources, and consumer preferences, the way energy is priced has evolved. In fact, many regions of the world have developed their own specific demand/supply/pricing rules. Energy is now traded in public market forums like the   European Energy Exchange (EEX). In addition to being linked to primary energy prices (i.e., prices for Brent crude and gas), electricity contracts are also priced for periods representing future days, weeks, months and even into the next year–and these prices fluctuate on a daily basis. Such prices may evolve by a factor of 1 to 2 during their trading periods. In fact, intraday prices regularly evolve by a factor of 1 to 5 on an average basis. Very high price peaks are observed during certain days–for example, when a large industrial asset unexpectedly requires maintenance in winter and is taken off-line. Negative prices are also becoming more and more of a market reality as renewable production sometimes results in an unexpectedly high volume (high supply) of available energy due to misinterpreted weather forecasts.   Digital Solutions Enable Forecasting and Increase Accuracy As a result of these conditions, it has become much more difficult for both utilities and major energy consumers to predict both energy production and portfolio consumption. Therefore, they find themselves in a situation where they cannot access an optimally low energy price. The solution is to enable a level of forecasting that increases the accuracy of supply, demand and prices. Only then can electrical utilities and distributors maintain and/or increase their profitability. This is where   new artificial intelligence   (AI) digital solutions play an integral role. We at   Predictive Layer, a Schneider Electric Energy Management   Technology Partner, have developed such a system to help large enterprises, traditional utilities, and producers of renewable energy to better forecast energy consumption and pricing.   AI and Machine Learning Provide Higher Accuracy and Adaptability Forecasting technologies, statistics, and models over the last 50 years were developed by small teams of expert energy forecasters. Their approach worked well in managing the previous generation of grid operations. Now, accelerating levels of complexity across grids create limits on the effectiveness of these human forecasting teams. However, new generations of distributed IT and infrastructure tools allow very affordable and resilient high-performance computing that enables the creation of more accurate forecasting models. These models now supplement forecasting on a daily basis. In fact, technology evolution is such that it is no longer necessary to manually build new forecasting models. New AI and machine learning tools automatically evolve the forecasting models by incorporating new trending and network supply and demand behaviors on a daily basis. With the proper AI tools, forecasting teams can produce and manage forecasts with 10x more accuracy than before.   -----------------------   Originally posted on   SE Blog & Authored by   Olivier Cognet   About the author:  Oliver Cognet, CEO, Predictive Layer, is a business leader, corporate developer, and entrepreneur. He has 25+ years of experience in High Tech, Software Development, and Telecom markets focusing on enterprise and consumer markets. Mr. Cognet knows that technology and innovation can help businesses better understand the behavior and needs of consumers, thus helping businesses to grow. Predictive Layer brings the full power of machine learning artificial intelligence (AI) to businesses so they can simply and intuitively model and establish forecasts and predictive analytics of their key target indicators.   ... View more