In Europe buildings use around 45% of total energy and HVAC systems are one of the major energy consumers. That makes HVAC optimization one of the priorities in efficiency upgrade with results in reducing carbon footprint and energy usage by 20% to 40%.
SmartCat solution for this challenge is Optimus Power.
Optimus Power is a software which gives us information about load base and profiles in consumption, identifies anomalies in system and in prescriptive phase, where we use reinforcement learning agents, we are able to predict, control, and optimize HVAC consumption in real time without additional cost for complicated hardware.
Optimus Power main features:
a) it infers base load profiles and does load prediction for HVAC consumption,
b) detects multiple types of anomalies and
c) does optimal control, ie. prepares policies for savings by shedding.
Optimus Power gives reliable predictions, is adaptive to changes in users behaviour or simple change of seasons, is robust and scalable (thanks to chosen tech-stack and algorithms) and saves money and energy (up to 35% compared to baselines)!. This way, Optimus Power plays the descriptive, predictive and, with optimal control, also a very important prescriptive analytics role in energy management.
Optimization, energy optimization, climate, smart homes, smart buildings
Our target market is Enterprise Energy Management Software (EEMS) Specialists and although the EEMS market is dominated by US suppliers, Europe holds a strong foothold, with 34.5% of overall sales in 2015, neck and neck with the US with 35.5%.
- Adoption of cloud-based energy management software
- Growing concept of Internet of Things in Buildings (BIoT)
- Increasing awareness for the efficient utilization of energy consumption
- The demand is increasing due to incentives being provided by governments of Europe as well as the benefits associated with the deployment of such solutions
- the value of data in commercial buildings is an increasing focus and increased customer education
Since our solution for energy efficiency - Optimus Power is hardware agnostic we see huge opportunity at the market for small-and medium-size buildings. Advancements in sensor and controls technology enable a new wave of advanced, non-invasive, cost-effective, and quick-to-install products without software as vendor lock in. The “big data” these new IoT devices generate can be gathered into cloud-based management and analytics services via existing networks, and the devices can be easily monitored and controlled by facilities managers, which are our target group.
Optimus Power is hardware agnostic software which analyze data collected from existing hardware or IoT solutions in buildings and give customers all information they need to make right decisions about HVAC consumption and savings in their facilities.
Optimus Power is based on machine learning algorithms which creates and predict consumption profiles, detects anomalies, gives real time HVAC optimization and track savings.
Our competition usually offers one or two services as expertise and don’t tackle other, so Optimus Power unique selling point is ability to have all relevant information and functionalities in one solution without upfront large investments.
Energy sector is going through lots of changes with new opportunities emerging for applications that are based on data mining and real-time analytics. Optimus Power seizes some of these opportunities by offering reliable, personalized, adaptive and real-time solution based on state-of-the-art tech-stack. Specific innovations that come with these five features are:
- Optimus Power gives Reliable consumption predictions based on user’s historical profiles of energy usage. Difference to traditional consumption predictions is granularity - Optimus Power does predictive modelling on all consumption measurements (up to 300 measurements per day) in contrast to predictions only on end-of-month bills.
- Personalization: usually missing in traditional and rigid energy solutions offered by energy distributors and providers. With Optimus Power, end energy consumers will be offered personalized features like optimal control that is not based on the tariffs or some preset categories, but applied based on their own consumption history and settings. Also, Optimus Power enables energy managers to drill down vast amounts of data and preview data for custom set filters and personalize their dashboard with specific anomalies they want to track or specific profiles of end user consumption.
- By using advanced data mining techniques Optimus Power could be Adaptive to change of seasons or customer behaviour and offer relevant insights or opportunity for better control.
- Real-time analytics and anomaly detection make Optimus Power adjustable to any changes in setup or malfunctions and also supports advanced control techniques.
Tech-stack of Optimus Power is scalable and flexible. It consists of proven tools in the domains of Big Data and IoT, like Apache Kafka, Apache Cassandra, Apache Spark. For optimal control Optimus Power uses state-of-the-art reinforcement learning approach theorized in academia but rarely deployed to production.