The Next Generation of Smart Meters Using Self-Learning Models

March 31, 2022

The global market for smart meters, including water, gas, heat, and electricity, is expected to reach $20 billion in 2022. However, many factors are contributing to the increasing difficulty of building reliable smart meter systems. These include an outdated smart meter infrastructure, fast urbanisation, and rising costs for testing and developing these devices, among others. Smart meter systems must fulfill complex regulations, operate in harsh climate conditions while also reducing non-revenue water losses, as well as fulfilling a carbon-neutral and sustainable future under mounting time-to-market pressure while increasing product performance.

Dragging sliders help engineers to generate new ideas and make quick design choices

 

New regulations that define metering accuracy, flow rates, valve, and metering technology require stringent calibration and regulatory tests. For a test engineer working on smart meters, Self-Learning models can be the key to success for leveraging existing and new engineering data, while not relying on expensive, time-intensive, and repetitive tests.

Ensuring accurate measurement of gas usage has widespread benefits: smart meter engineers can track and predict their own expenditure, while suppliers can understand their client base and provide a more reliable and bespoke service.

 

Monolith is a no-code application that offers engineers a new way of leveraging their smart meter test data to help them explore, understand and predict performance, thereby reducing test times by up to 70%. Additionally, Monolith offers collaboration features to ensure institutional knowledge is capitalised on, shared, and documented for generations to come.

 

The Next Generation of Smart Meters

 

When designing the next generation of smart meters, it is important to keep several key factors in mind. With higher reliability, utilities spend less on maintaining existing infrastructure and reduce overall operating costs. A lower power consumption ensures that meters can operate longer on a single battery and with smaller smart meter size, more sensors can be placed in more locations further increasing the “intelligence” and efficiency of the 'grid'—whether water, gas, heat, or electricity. 

To create more reliable, accurate or energy-efficient system designs, engineers can either retrofit existing products with IoT sensors or bring new, smarter products to market. Either way, they need to spend hundreds of hours testing to ensure the accuracy and reliability of the sensor under thousands of operating conditions to achieve certification.

 

For example, smart meters need to work for about 20 different flow rates, 30 different temperatures, and 10 different gases. That means these devices must go through at least 6,000 different test scenarios to make them work, each of which means analysing a significant amount of noisy time series data. 

 

Compatible Engineering Data Types

 

Whether your team is working with gas meters as water solutions, heating solutions or sub-metering solutions, Monolith is compatible with all of the engineer's most frequently used data types and formats that can be uploaded to Monolith’s platform. Monolith offers all pre-processing modules needed for test data and empowers every engineer to build a sequence of steps that form a data processing pipeline. Using Monolith’s collaborative functionality, the resulting dashboard can be shared with colleagues or other departments gaining new insights into the engineering workflow.

 

As an example, engineers can easily understand time-series data for received upstream and downstream signal amplitudes which indicate the speed of the gas. By evaluating the difference in arrival times inside the Monolith platform, the volume flow rate can be derived, other physical phenomena can be investigated by performing “virtual tests”, and new design choices can be made without any additional real-life testing scenarios. 

 

The following question naturally arises: what design choices should be chosen to give the most accurate meter?

 

Smart Meter Data Exploration

 

Using your gas meter test bench data, Monolith empowers you to create accurate, self-learning models to quickly understand and instantly predict the performance of the gas meter system under thousands of operating conditions.  

 

Monolith instantly determines what smart meter designs give the best performance, while self-learning models learn from new data generated along the way, indicating which designs are most promising to investigate next.

 

The performance of each gas meter design is given by its error curve, giving the percentage accuracy for a range of flow rates and ambient temperature conditions.  

 

Example of an Error Curve measured for a range of flow rates and ambient temperature conditions

 

Using your test data to create self-learning models, Monolith enables you to reveal missing data, systematic experiment errors, and mislabelled data before training additional models. By learning what intelligent correlations exist, you can quickly understand intractable physical phenomena and compare complex relationships, and as a result, understand how different design choices affect the error curve.  

Intelligent correlations. Pairs of columns are compared and any pairs with a strong physical relationship indicated. This reveals how the design choices tend to affect the error curve.

 

The resulting best model can be used to predict new error curves, giving you instant feedback to make the optimal design choices for improved product quality and performance. The error curve response can be predicted for any new set of design choices, specified by dragging sliders which empowers any engineer to interact with the model and gain new insights, with no need for programming expertise, IT set-up, and minimal training to use the platform and build self-learning models. Additionally, users can create dashboards and share results instantly. 

Conclusion 

 

Engineers can make predictions within their regulatory requirements and quickly generate new optimum designs for the meter setup and export those design parameters to the meter itself, but also inform their suppliers of corrections to the meter components.

 

Using Monolith to investigate test data, our users can combine, transform and build self-learning models inside our no-code AI platform that accurately predict flow rates for multiple material types through devices such as valves with varying throughput capabilities such as radius, length, and other relevant device measurements.

 

Test Less. Learn More. Improve Sustainability.

 

Monolith empowers engineers to spend less time running expensive, repetitive tests and more time learning from their engineering test data to help them empower a sustainable future.

Want more?
Book a quick demo today.

Author

Jousef Murad

Jousef Murad

Product Marketing Engineer

Jousef is responsible for product marketing at Monolith. He studied mechanical engineering at the Karlsruhe Institute of Technology (KIT) where he focused on computational mechanics, turbulence modeling & AI. On the side, he's an avid podcaster and video creator.

Apply Today