Case Studies | SaaS B2B

Turning sunshine and tariffs into savings

Home Energy Forecasting and Optimisation

About

A SaaS B2B business working with Cloud Combinator on AWS. The client is anonymised at their request.

Challenge

The proof of concept had three focus areas, each essential to a system that can be trusted to trade a household's energy.

Forecasting consumption and generation

The home needs a reliable half-hourly view of how much energy it will use and how much its solar will generate, which in turn depends on the weather. Without an accurate forecast, every downstream decision is a guess.

Predicting battery state of charge

Knowing the battery's likely state of charge across the day is what makes it possible to plan when there is room to store cheap or solar energy and when there is surplus to sell.

Turning forecasts into profitable decisions

Forecasts only matter if they drive action. The system had to combine predicted solar, state of charge and half-hourly import and export prices into rules that pick the most profitable moments to charge, discharge, import and export, and do so generically across different tariff structures.

Solution

Cloud Combinator scoped the work as a staged programme, starting with a low-risk proof of concept focused on forecasting accuracy before moving toward production optimisation and a resident-facing AI experience.

48

Half-hourly slots forecast and optimised per day

7-14 days

Forecast horizon of the time series models

5

Representative households used to validate the models

By the numbers:

  • 48 - Half-hourly slots forecast and optimised per day
  • 7-14 days - Forecast horizon of the time series models
  • 5 - Representative households used to validate the models
Changes

Cloud Combinator delivered a working forecasting proof of concept that predicts household consumption, solar generation and battery state of charge on a half-hourly basis and turns them into tariff-aware import, export and charging decisions, proving the feasibility of the wider programme.

  • Accurate half-hourly forecasts — Consumption, solar generation and state of charge are predicted per half-hour using the client's data enriched with weather.
  • Profit-aware decisions — A generic rule set converts forecasts and next-day prices into the most profitable half-hours to charge, discharge, import and export.
  • Tariff-agnostic by design — The logic is written to work across tariff structures, from two-tier to agile and variable pricing, ready to extend in later phases.
  • Handover — The client received the POC models, the decision rules and a clear roadmap to production optimisation and an AI resident interface.

With forecasting proven, the client is positioned to move from a proof of concept to a production energy-optimisation engine and, ultimately, a home that residents can simply talk to, one that manages its own energy to keep them comfortable and their bills low.

AWS Stack

Amazon SageMaker Data Wrangler

For preparing and quality-checking the household and weather data.

Amazon SageMaker Canvas

And SageMaker endpoints for building and serving the time series forecasts.

Amazon DynamoDB

For household energy history, home locations and tariff presets.

AWS Lambda

For invoking the model endpoints and running the decision logic.

Amazon Bedrock

For the large language model behind the planned resident interface.

AWS CloudFormation

For deploying the workflow as infrastructure as code.

YOU MIGHT LIKE

Related success stories

View all case studies

Case Studies | Insights

Utilising Language Recognition, Speed, and Enhanced Security to Make Social Media a Force for Good

  • Here, we take a detailed look at how the Cloud Combinator team collaborated with another cutting-edge AI service provider that provides intelligent systems to “make social media more social” for brands and users alike.
  • Arwen AI is a UK-based startup specialising in AI solutions to manage and enhance brands’ social media interactions. Founded in 2020 by Matt McGrory, Dr. David Cole, and Joel Bailey, Arwen. AI focuses on using AI to automatically detect and remove spam, toxic comments, and other unwanted content from social media platforms.
  • The team at Arwen have three core products. ‘Moderate’ is focused on identifying and removing toxic content from social media channels. ‘Engage’ helps brands identify and engage with meaningful conversations on social media, and ‘Customize’ allows brands to apply bespoke algorithms to their channels - creating an even more effective moderation and engagement.
Read more
CONTACT US

Ready to turn AI into impact?

We'll help you spot the highest-value opportunities, reduce risk around your first AI initiative, and define a clear path to results from day one.

Why talk to us:

Outcome-driven recommendations

AWS-recognised delivery expertise

Risk-aware AI adoption

Clear next step, not a sales pitch

Start with a focused 20-minute conversation about your goals — no pressure, no commitment.

We use cookies

This website uses cookies to enhance user experience and to analyze performance and traffic on our website.

See our Privacy Policy for details.