The mission of this group is to bring together utility professionals in the power industry who are in the thick of the digital utility transformation. 

Post

DIGITAL GRID - Artificial Intelligence applied in the control and reduction of Technical and Commercial Losses.

image credit: Google

Based on data observation and automation learning, "AI" detect typical conditions and types of sensor/equipment and aggregate such as good or intervention needed or unusual behavior. It also triggers actions accordingly, such as preventive maintenance, repair or replacement of a Distribution Transformer, Circuit Division, Capacitor Bank, Sensors, etc.

Utilities will incorporate data science into their grid planning to move from reactive to predictive grid management. It will maximize the value of their data for more precise targeting and participation in customer programs.

Your access to Member Features is limited.

Please or apply for membership to continue reading this post.

Today on average this division between Technical and Commercial Losses that the proportion of 58% for Technical Losses and 42% for Commercial Losses. The control of Technical and Commercial losses of electricity needs to be rigorously implemented and monitored. The Utilities must therefore be able to identify the losses by type - Technical or Commercial - and where they occur, to try to reach the optimum level of losses.
In relation to Commercial losses, the optimal level is zero, ie, the ideal is that all energy is actually delivered to customers billed correctly. The Commercial losses are the easiest to be identified, but not so easiest to be eliminated.

The good relationship between utilities and consumers is a powerful tool and combined with other initiatives of cultural and behavioral change are key to its reduction. Digital and innovative solutions are key for our grids in being the backbone of the energy transition.

Commercial Losses involves administrative efficiency, promotional campaigns and a better relationship with consumers. Consumers are a diverse group, if you have a vision of how to meet these different classes of consumers, and what tools to use for each class of consumer, it can be reduced to a minimum.

“Or rather, adapting to the behavior of their consumers” - Now when a utility sees anomalies in usage, dramatic changes in usage over time, or the beginnings of such change, it can simulate program fixes in the replica, using an “AI” driven recommendations engine to select the best program option.

It must be created a feedback loop, powered by machine learning, to assess the results, constantly recalibrating the output and refining it, so the utility could engage in an even more nuanced way with its customers. As the algorithms continue to learn and improve over time based on real customer feedback and adoption rates, the utility increases its ability to make the right offer to the right customer at the right time with the right messaging.

Understanding the customer, the audience of one, is now possible and can build upon that individual understanding to create better, more accurate categories or groupings of customers to whom programs can be best matched. We can also use a digital replica of each customer to simulate the impact of various program offers to make personalized recommendations to cohorts of customers.

Already, in relation to Technical Losses, the optimal level is a function of topology and net length, materials and equipment used, the behavior of the load (balance, load factor, demand maximum permissible loading level, etc.)  The assessment of quality and reliability of supply of electricity is a concern common to electric utilities, and is directly related to the Technical Losses which require simple and reliable indicators that measure the quality of electricity supply to the target well investments and resolve issues.

The Reactive Power and Power Factor are the main factors for the increase in Technical Losses and poor power quality.
The Reactive Power produces an increase in losses in the power grid and reduces the voltage level on consumers.
It can be assumed that the transmission lines and power distribution are sources of reactive power due to its reactance.

Power Factor is one of the main parameters to be controlled in the Distribution Energy and is the relationship between Active Energy and the Total Energy consumed.

It shows the relationship Consumer Unit consumes electricity properly or not, because it relates to efficient use of Active and Reactive Energy of an electrical installation, one of the main indicators of energy efficiency.

The lower the power factor, more power is required to meet the same number of consumers.
The most significant Technical Losses in distribution system occur in the primary drivers in distribution transformers and secondary conductors, and are generally neglected the losses in the branches connecting the consumer.

Technical Losses represent a significant share in the cost matrix of distribution systems and, therefore, have always had great prominence in planning studies of electric utilities, especially in recent years due to energy conservation programs. In distribution systems are directly related to consumers' load curves, which vary due to seasonality and/or rapid changes in load over the year, resulting in uncertainty in determining the amount of losses. These uncertainties can be determined from the elaboration of a decision support system that considers the random nature of load curves through a set of measurements along the feeders.

The determination of the Technical Losses in transmission and distribution systems can be performed by different processes.
In transmission systems, losses are estimated by studies of power flow and energy balance through the segment.
In distribution systems, the vast majority of utility companies using, among other procedures, such as network management, power flow, processes and statistical geometric models.

The methodology used by utilities, is to calculate the Technical Losses by segment in the distribution system (power meter, household connection network secondary distribution transformer, the primary network and distribution substation) within a policy of calculating monthly periodical.

Energy losses affect the amount of energy retained by the distributor. These costs, as well as the industry charges and other costs are recognized as "unmanageable" and thus given directly to final consumer tariffs, known as “pass throw”, because the amounts and variations are beyond the control of the distributor.

These costs are passed on to prices, ie, the larger the Technical and Commercial losses, the greater the rate of energy.

Starting with early efforts toward enabling an “intelligent grid,” utilities deployed the piece parts of digitalization: advanced meters, sensors, distribution automation systems, communications technologies, analytics and controls. The goals were fairly simple: more energy and operationally efficient and reliable grids, with an eye toward better integration of distributed renewables.

An "AI" platform, analyzes and visualizes components and potential defects within the grid infrastructure. It acts as a power management system, integrating data over the entire network. It then translates this information using "AI" forecasting algorithms for the management and control of all operations of the power distribution systems.

The control of Commercial Losses of electricity needs to be rigorously implemented and monitored in Utilities. The inefficiency and waste must be constantly fought with programs and activities and effective date.
The cost is very high for Utilities that neglect.
The occurrences of theft and fraud, with the consequent loss of business, have hampered the efforts of utilities to regularize the supply and proper collection of electric service to consumers.
The first point in combating fraud is to identify where it occurs. Currently, smart meters are already installed in several Utilities, incorporating the concepts of Artificial Intelligence and Machine Learning.

Digital technological tools that enable the analysis and identification of metering irregularities. Reading the data obtained by the meters allows the system to generate algorithms that create a list of possible fraud parameters. This approach to flagging fraud, as any relevant changes raise an alarm. Then the detection processes, which were previously done manually, are now triggered automatically.

The reduction of Technical and Commercial Losses for Utilities has more impact than the Environmental appeals and others. Because it directly affects the profits of Utilities and the price of tariffs, in-fact is the consumer who pays the bill.
The less efficient the transmission and distribution sector, and will be the most expensive price tariffs charged to the consumer.

With or without "AI", the grid is changing. But "AI" distinguishing features, decentralized architectures, and programmability through smart meters are compelling for an electricity system with much greater customer side participation than ever before.

In a high-level view, Data Science allows the extraction of knowledge from large volumes of data, structured or not. With this, it is possible to obtain specific answers and insights that, in a traditional way, would not be obtained in a timely manner.

"It is all about performance. You can see how technology could make the world of work more meritocratic by focusing more on substance and less on style”.

 

Joao Batista Gomes's picture
Thank Joao Batista 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.
More posts from this member

Discussions

Spell checking: Press the CTRL or COMMAND key then click on the underlined misspelled word.
Matt Chester's picture
Matt Chester on Mar 1, 2021

With or without "AI", the grid is changing. But "AI" distinguishing features, decentralized architectures, and programmability through smart meters are compelling for an electricity system with much greater customer side participation than ever before.

Very well said, Joao-- AI isn't why the grid is changing, but because AI is available it means stakeholders on the grid can keep pace with and leverage that already changing grid!

Joao Batista Gomes's picture
Joao Batista Gomes on Mar 3, 2021

For a long time and for many voices, we heard about the need to change the behavior of electricity consumers. This is a unique case, where the customer has to adapt to his supplier. It seems to me that this solution has little chance of success. Utilities must adopt an architecture that is adaptive to consumer behavior, which changes their load profile throughout the day and the seasons.

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 »