Real-time Numerical Optimization in Reconfigurable Hardware with Application to Model-Predictive Control
Lead Research Organisation:
Imperial College London
Department Name: Electrical and Electronic Engineering
Abstract
This proposal is concerned with the hardware acceleration of iterative numerical algorithms, with a focus on model predictive control implementations. Such model predictive controllers typically require the solution of a quadratic progamming problem every sample period. The solution of the quadratic programming problem typically requires several multidimensional Newton optimizations, each of which requires the solution of many systems of linear equations. Thus the lessons learned will be applicable to a wide class of numerical algorithms arising in practical problems within and beyond Control.The main adventurous feature of the approach from the digital electronics perspective is the potential to use Control and Systems theory to inform one of the central design problems in custom reconfigurable computing: efficient silicon utilization through appropriate finite precision number representation. In sequential (single core) computer architecture, questions of numerical precision have, by and large, been answered through the introduction of area costly high-precision IEEE compliant arithmetic units. In modern computing systems, whether FPGA-based or manycore, attention is now turning to how to make the most effective use of the silicon available for computation and, in this context, questions of numerical accuracy requirements are arising once more.The proposed approach forms a radical departure from standard industrial and academic practice in both model predictive control (MPC) and digital electronics. The main adventurous feature of the approach from the end-user perspective is the utilization of reconfigurable hardware devices, namely Field-Programmable Gate Arrays (FPGAs), to implement model predictive controllers operating at high sample rates, allowing MPC to be utilized in application areas where the computational load has been considered too great until now, such as spacecraft, aeroplanes, uninhabited autonomous vehicles, automobile control systems and gas turbines. From the theoretical perspective, the main adventure in Control is in the development of novel formulations that explcitly take advantage of parallel computational architectures.The development of a methodology to tackle this problem will involve highly novel research areas resulting from the application of control theoretic ideas to hardware development, as well as the application of hardware implementation methodologies to control system design. In particular, this proposal is the first to investigate massively parallel real-time numerical optimization on FPGAs, the first to apply control-theoretic techniques to determine appropriate number systems in custom hardware designs, and the first to study the tradeoff between circuit parallelism and numerical accuracy within a closed-loop behavioural context.As a result, this proposal directly falls within the scope of EPSRC's recently signposted Microelectronics Grand Challenge 3 - Moore for Less.
Organisations
- Imperial College London (Lead Research Organisation)
- Agility Design Solutions (Collaboration)
- NANYANG TECHNOLOGICAL UNIVERSITY (Collaboration)
- European Space Agency (Collaboration)
- The Mathworks Ltd (Collaboration)
- Xilinx Corp (Collaboration)
- Siemens (United Kingdom) (Project Partner)
- MathWorks (United Kingdom) (Project Partner)
- Xilinx (United States) (Project Partner)
- European Space Research and Technology Centre (Project Partner)
Publications
Jerez J
(2014)
Embedded Online Optimization for Model Predictive Control at Megahertz Rates
in IEEE Transactions on Automatic Control
Jerez J
(2015)
A Low Complexity Scaling Method for the Lanczos Kernel in Fixed-Point Arithmetic
in IEEE Transactions on Computers
Kerrigan E
(2015)
Computer architectures to close the loop in real-time optimization
Le Lann C
(2011)
Reconfigurable Computing: Architectures, Tools and Applications
Liu Q
(2012)
Optimizing Hardware Design by Composing Utility-Directed Transformations
in IEEE Transactions on Computers
Longo S
(2011)
Parallel move blocking Model Predictive Control
Longo S
(2014)
Constrained LQR for low-precision data representation
in Automatica
Longo S
(2011)
A parallel formulation for predictive control with nonuniform hold constraints
in Annual Reviews in Control
Rafique A
(2012)
Enhancing performance of Tall-Skinny QR factorization using FPGAs
Description | That reconfigurable computing can allow optimization based control methods to be used in high performance settings. That control theory can be used to inform design metrics in cyber physical systems. |
Exploitation Route | This work has spawned a number of ongoing special sessions in the major control conferences - several groups in academia and industry (e.g. ABB) now actively work taking this forward. |
Sectors | Aerospace Defence and Marine Digital/Communication/Information Technologies (including Software) Electronics Energy |
Description | Several companies have taken up this work (notably ABB) and one of the researchers on this project (Juan Jerez) has launched a startup in this area (embotech). |
First Year Of Impact | 2010 |
Sector | Aerospace, Defence and Marine,Digital/Communication/Information Technologies (including Software),Electronics,Energy |
Impact Types | Societal Economic |
Description | FP7 STREP - EMBOCON |
Amount | £685,139 (GBP) |
Funding ID | EMBOCON |
Organisation | European Commission |
Sector | Public |
Country | European Union (EU) |
Start | 09/2010 |
End | 09/2013 |
Description | Siemens Research Award |
Amount | £174,767 (GBP) |
Organisation | Siemens AG |
Sector | Private |
Country | Germany |
Start | 09/2013 |
End | 09/2016 |
Description | Agility - MPC |
Organisation | Agility Design Solutions |
Country | United States |
Sector | Private |
PI Contribution | Research Output |
Collaborator Contribution | Staff time |
Impact | Agility DS was bought out |
Start Year | 2009 |
Description | ESA - MPC |
Organisation | European Space Agency |
Country | France |
Sector | Public |
PI Contribution | Research output |
Collaborator Contribution | Staff time |
Impact | Research output, follow-on funding |
Start Year | 2009 |
Description | Mathworks - MPC |
Organisation | The Mathworks Ltd |
Country | United Kingdom |
Sector | Private |
PI Contribution | Research output |
Collaborator Contribution | Staff time, licences |
Impact | Publications |
Start Year | 2009 |
Description | NTU - MPC |
Organisation | Nanyang Technological University |
Country | Singapore |
Sector | Academic/University |
PI Contribution | Research output |
Collaborator Contribution | Staff time |
Impact | Joint publications, student exchanges |
Start Year | 2009 |
Description | Xilinx - MPC |
Organisation | Xilinx Corp |
Country | United States |
Sector | Private |
PI Contribution | Research output |
Collaborator Contribution | Staff time, licences, devices |
Impact | Publications |
Start Year | 2009 |