Speaker Abstracts: Data science and AI for sustainability conference 2022
Policy and regulation
Julian Critchlow (Senior Advisor Bain & Company; former DG Energy Transformation & Clean Growth, BEIS)
The Challenges of Delivering Net Zero
In advance of COP26, the UK laid out a highly ambitious and comprehensive Net Zero Strategy with a full set of supporting sectoral decarbonisation plans. However the war in Ukraine has already highlighted the challenges of delivering power decarbonisation whilst maintaining security of supply – and the Net Zero Strategy is targeting similar changes in every sector of the economy. The presentation will focus on the challenges of delivering the announced plan and how government, industry and consumers will all need to work in a different way to deliver the energy transition.
Dr Ronita Bardhan (Department of Architecture, University of Cambridge)
Deep built environment design for decoupling climate related health burdens from poverty
Built environment will be a significant modifying factor of health burdens and (in)equality in the warming climate. The impacts of a dysfunctional space design are most aggravated in poorer communities where the asymmetries are profound. This talk scientifically unfolds how various data streams: (i) quantitative data from environmental/energy sensors, (i) qualitative data on agency and use of space, and (iii) big data on performance metrics like energy consumption can enable understanding the effects of building design parameters quantifiable outcomes. The talk demonstrates how design can help understand health metrics like walkability in cities, outdoor heat stress due to climate change and indoor environmental quality in slum transitional housing. One of the challenges of working in resource constraint communities is the absence of data. This talk discusses how “deep” knowledge can systematically be to generate new information and inform policy space for sustainable and healthy future.
Lucy Yu (CEO, Octopus Energy’s Centre for Net Zero)
Data-driven policy-making: how to achieve a people-centred transition
The road to net zero is about more than just business and industry change; individuals will play a critical role. Their diversity must be accounted for in policy-making and by industry if we’re to achieve an energy transition that is fast, fair and affordable. In this talk, Lucy considers the variety of actors involved in the energy transition, how modelling the differing influences of changes in behaviour, technology and policy is critical to data-driven decision making, and how this, in turn, can catalyse system-level transformation.
Technologies: energy networks
Dr Fei Teng (Imperial College London)
Security and Privacy of Energy Data
There is a growing trend to utilise data and AI to facilitate the decarbonisation of our energy sector. However, the security and privacy issues associated with energy data have not been fully addressed, which may limit the rollout of digitalization. This talk will aim to promote the discussions on the trustworthy and privacy-preserving data science and AI in energy applications.
Iulian Nitescu (Chief Technology Officer, Graphmasters)
Making transportation more sustainable using Collaborative Routing
An increasing number of vehicles are competing for finite space on our roads - bicycles, cars, HGVs and in the future autonomous vehicles. Graphmasters optimises time and space on the road network using the first collaborative routing platform in the world. This has been shown to improve traffic flow by 30% making transportation more sustainable for everyone.
Dr Ioannis Lestas (Department of Engineering, University of Cambridge)
Distributed control in a low carbon power grid
Power grids are currently undergoing radical transformations with an urgent need for an increase in the penetration of renewable energy sources. This, however, brings many challenges associated with the control of power systems that will need to be addressed. At faster timescales the low inertia of the grid implies that power electronic converters interfacing renewable energy sources need to start having a grid forming role. Furtherore, load-side participation becomes an important mechanism that can provide an ancillary service to the grid. Various challenges associated with the implementation of such distributed control mechanisms and proposed solutions will be discussed throughout the talk.
Economics: energy market trading
Dr Ramit Debnath (Judge Business School, University of Cambridge)
Digitalisation and future of energy policy in the Global South
Digitalisation is envisaged to play a vital role in decarbonising emerging economies like India. However, the digitalisation efforts in India are still at an experimental stage, which means there are issues with data quality and reliability. This talk will demonstrate how AI can help better understand data problems for digitalisation. This is primarily done by leveraging the lessons learnt from the effects of Covid-19 lockdowns in shifting household electricity demand patterns. Policy implications are drawn in collaboration with the International Energy Agency, France and the Lawrence Berkley National Laboratory, USA, to support effective digital governance in the energy sector.
Ciaran Flynn (Modelling and Analysis Manager, Sembcorp Industries Ltd)
Head of Modelling & Analysis
With increasing renewables on the GB power network, flexibility is now needed more than ever. The optimisation of flexible assets comes with challenges in terms of multiple different markets to engage in. Each market having very different characteristics and challenges. This is where data science has the capability to enhance optimal trading decisions with uncertainty. Finding key market characteristics in a volatile market place.
Steven Steer (Lead Data Consultant, Zuhlke)
A grand design to power our future
This presentation will make the case for new energy sectoral governance arrangements as published as part of the UK Energy Digitalisation Taskforce. These arrangements are to gain the benefits of whole-system architectural planning to coordinate engineering investments and it is proposed to integrate these into our liberalised market; the proposal takes advantage of best practice governance methods from the digital/data disciplines of Enterprise Architecture and Agile delivery and uses these to digitalise the market governance process applied on a national market-wide scale. This digitalisation of industry governance enables digitalisation of the energy system itself, allowing us to tackle modern energy social, stability and cost challenges.
Future cities: buildings
Ellissa Verseput (Data Team Lead, Sympower)
Empowering renewable electricity grids with flexibility & AI
Sympower is accelerating the global transition towards net zero by balancing the supply and demand of electricity across international energy networks. Our in-house software platform connects to thousands of industrial IoT assets, such as greenhouse lights, electric vehicles and machines at paper mills. By controlling their flexible electricity demand, commonly reacting within a second, we counter the imbalances on the grid fundamental to the growing supply of renewable energy. One big challenge here is to predict precisely how much electricity we can control at all times and places.
In this talk, Ellissa will introduce Sympower’s flexibility services that help customers adapt towards the energy transition. She will explain how combining data, software and hardware provides an end-to-end solution that offers real-time monitoring and balancing of electricity supply and demand. Particularly, she will discuss the set-up and challenges of the AI-based, automatic forecasting services required to monetise flexibility on different energy markets.
Dr Jim Scott (Chief Production Officer, Grid Edge)
Dr Jethro Akroyd (Department of Chemical Engineering and Biotechnology, University of Cambridge)
Digital Twins and Semantic Technology
The World Avatar project – a universal digital twin
“The World Avatar” (TWA) project aims to create a digital ‘avatar’ of the real world. The digital world is represented using a dynamic knowledge graph that contains concepts and data that describe the world, and an ecosystem of autonomous computational agents that simulate the behaviour of the world and that update the concepts and data so that the digital world remains current in time. In this manner, it is proposed that it is possible to create digital twins that can describe the behaviour of any complex system, and by doing so provide the ability to make data-driven decisions about how to optimise the systems. Examples will be presented from TWA including building management, smart city operation, climate resilience and national energy scenarios.
Dr Isabella Gaetani (Senior Scientist Smart Buildings, Arup)
Between us and AI | Where we stand and what we learnt
Data has a unique role to play in the optimization of building design and operational performance. Various examples of the use of building data within Arup are presented in this talk, spanning from digital twins, to pedestrian modelling, to ML algorithms for predictive maintenance. The focus of this talk, however, is the gap between advanced AI/ML applications and the current status of building digital transformation. We’ll talk about the role of Arup in smart enabling existing buildings and new builds, in ensuring data flows that speak with each other and the importance of setting clear targets and neat workflows.