IoT based Smart Energy Meters Architecture and Solutions

Introduction to Smart Meters

In the Energy Upgrade solution, IoT is playing a significant role. Use of smart meters is increasing, which enables the intelligent and efficient use of energy at homes and businesses. Many grid power supply companies, small and large industries, private residential sector are also implementing the smart solution for energy efficiency and sustainability.

Business Challenge for Building the Analytics Platform

We need to build a complete analytical solution that can be used for the energy-saving recommendation based on the usages for the large buildings and industries. Also, the challenges were to filter the results found on floors, buildings, heat, water, electricity. Along with the dashboard, alerting for usage also should be used based on usage.

IoT Analytics Platform for Real-Time Data Ingestion

Solution Approach for Building IoT based Smart Meters

Complete Smart meter based analytical dashboards which includes -

Recommendation for energy saving
Predictive results for Energy Bills
Real-time alerting on some defined alerting rules
Analytical results on the base of historical data

Architecture for Building Smart Meters using AWS IoT Services

In this architecture, the first thing is the connectivity of the smart meters with the cloud. Here we are using AWS IoT core as the IoT hub, which is connecting to each device. AWS IoT core is sending results to the AWS Kinesis Firehose. After this, the architecture is divided into four parts: Alerting and Notification, Real-time Results, Analytical dashboard, Predictive results on the dashboard. In alerting part, Kinesis Analytics is consuming streams from Kinesis Firehose and doing the transformation on the streamed data. After these transformations, AWS Lambda Function is used for further data validation and filtering to identify an anomaly.

Based on these anomalies, the message has been sent to AWS SNS queue. AWS SQS can also be used at the place of AWS SNS. While integrating real-time data with the dashboard, we are using the same transformed result which is being used by AWS Lambda. This real-time transformed stream is sent to AWS Kinesis Stream. After that, it will be sent to Web Socket Server, which can be further integrated with the dashboard for real-time visualization. For the Analytical Dashboard, the real-time firehose stream is writing data to the AWS S3 bucket with is raw data zone for the IoT events.

In Azure, IoT Hub acts as the central unit which allows connecting, monitoring and managing millions of devices using bi-directional messaging. It supports AMQP, MQTT, and HTTP protocols for communication with IoT devices. It also helps their own protocol gateway Azure IoT Protocol Gateway, in case a device doesn’t support AMQP, MQTT, or HTTP.

Adopt AWS IoT Platform for building Scalable and Predictive analytics and decision-making Applications in Enterprises Click to explore, AWS Industrial IoT Consulting Services and Solutions.

In the next step, an AWS Glue ETL job is defined to collect the data from the data zone and put it into the trusted data zone after doing all the transformation. On top of AWS S3, we are using AWS Athena for interactive SQL queries on the AWS S3 bucket. This a complete serverless service by AWS which can be used to do analytical queries on the AWS S3. This can be integrated directly with the dashboard. Now the last and most important part is running the Machine learning model on the incoming results and getting predictive results. At this stage, AWS Sagemaker is using a trusted data lake for the model training. And for the model inference, AWS Fargate is being used, which is calculating the prediction results and storing it into AWS DynamoDB. AWS DynamoDB is integrated with the dashboard to show the predictive results.