Lilli Frison
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Lilli Frison has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
Simon Gölzhäuser
4 shared publicationsEtienne Ouss
2 shared publicationsHugues Bosche
2 shared publicationsMalte Vahlenkamp
2 shared publicationsMarina Reyboz
2 shared publicationsMartial Mermillod
2 shared publications
Latest Publications
- Open Access
- 11 November 2026
- Published by Springer Nature in Energy Informatics
- Vol. 9 (1)
Uncertainty-aware day-ahead thermal-load forecasting in expanding district heating networks with attention-enhanced encoder-decoder LSTM
Reliable day-ahead thermal-load forecasts with quantified uncertainty can support risk-aware control decisions and reduce unnecessary safety margins. This paper applies an Attention-Encoder-Decoder Long Short-Term Memory (AEDL) architecture with direct multi-horizon decoding to rolling 24-hour-ahead thermal-load forecasting and compares three variants: deterministic AEDL, Gaussian-AEDL, and Quantile-AEDL. Gaussian-AEDL predicts a parametric Gaussian distribution, while Quantile-AEDL predicts non-parametric quantile levels. Two AEDL versions handle the growing load: version A scales the load of each input window, and version B adds a linear shortcut from the load of the last 24 h. The methods are evaluated on data from an expanding district heating network in Germany, using two rolling test periods that cover six months. Using the weather forecasts available at each forecast origin as inputs over the 24 h forecast horizon, the mean absolute percentage error (MAPE) ranges from 6.95 to 7.10%. Both versions outperform seasonal-naive, LSTM, and Temporal Fusion Transformer (TFT) baselines. Compared with TFT, they reduce the point-forecast error by 4 to 6% at about a quarter of the computational cost. Gaussian-AEDL achieves the lowest calibrated continuous ranked probability score (CRPS) of 161 kW, compared with 166 kW for Quantile-AEDL. Validation-based calibration raises central 80% interval coverage to 77 to 78%. Without weather forecasts, the forecast errors increase by 16 to 27%. Overall, the results show that probabilistic AEDL models retain point-forecast accuracy while providing useful uncertainty information, but their prediction intervals require calibration before operational use.
- 11 November 2026
- Published by Springer Nature in Energy Informatics
- Vol. 9 (1)
Open AccessUncertainty-aware day-ahead thermal-load forecasting in expanding district heating networks with attention-enhanced encoder-decoder LSTM
Reliable day-ahead thermal-load forecasts with quantified uncertainty can support risk-aware control decisions and reduce unnecessary safety margins. This paper applies an Attention-Encoder-Decoder Long Short-Term Memory (AEDL) architecture with direct multi-horizon decoding to rolling 24-hour-ahead thermal-load forecasting and compares three variants: deterministic AEDL, Gaussian-AEDL, and Quantile-AEDL. Gaussian-AEDL predicts a parametric Gaussian distribution, while Quantile-AEDL predicts non-parametric quantile levels. Two AEDL versions handle the growing load: version A scales the load of each input window, and version B adds a linear shortcut from the load of the last 24 h. The methods are evaluated on data from an expanding district heating network in Germany, using two rolling test periods that cover six months. Using the weather forecasts available at each forecast origin as inputs over the 24 h forecast horizon, the mean absolute percentage error (MAPE) ranges from 6.95 to 7.10%. Both versions outperform seasonal-naive, LSTM, and Temporal Fusion Transformer (TFT) baselines. Compared with TFT, they reduce the point-forecast error by 4 to 6% at about a quarter of the computational cost. Gaussian-AEDL achieves the lowest calibrated continuous ranked probability score (CRPS) of 161 kW, compared with 166 kW for Quantile-AEDL. Validation-based calibration raises central 80% interval coverage to 77 to 78%. Without weather forecasts, the forecast errors increase by 16 to 27%. Overall, the results show that probabilistic AEDL models retain point-forecast accuracy while providing useful uncertainty information, but their prediction intervals require calibration before operational use.
- Open Access
- 30 September 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 10 (3) , 1-24
HAR-ASIC: A Configurable Edge-AI Human Activity Recognition Circuit for Ultra-Low Power Wearable Devices
We present an application-specific integrated circuit (ASIC) using digital hardware design to maximise energy-efficiency of human activity recognition (HAR) in autonomous wearable devices. The HAR-ASIC was designed in 22 nm technology and includes a battery of configurable, hardware-optimised feature extraction functions along with a decision tree ensemble classifier, thus serving as an edge AI device for local sensor data processing. We validate the HAR-ASIC based on post-layout process data with five HAR datasets and show the design scalability for configurations to maximise energy saving and others to maximise recognition performance. We show that feature extraction often requires up to 100 times more energy than the classification function. Our configuration analysis shows that feature extraction energy consumption can be reduced by factors of two to five, with at most 3% loss in F1-score, depending on the dataset. Across all datasets, feature extraction and classification energy was between 64 and 678 nJ per inference for Pareto-optimal configurations using sliding window buffers of up to 512 samples. We conclude that the highly configurable HAR-ASIC design could be the basis to realise ultra-low power sensor-edge AI systems for continuous wearable HAR and possibly further edge AI applications.
- 30 September 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 10 (3) , 1-24
Open AccessHAR-ASIC: A Configurable Edge-AI Human Activity Recognition Circuit for Ultra-Low Power Wearable Devices
We present an application-specific integrated circuit (ASIC) using digital hardware design to maximise energy-efficiency of human activity recognition (HAR) in autonomous wearable devices. The HAR-ASIC was designed in 22 nm technology and includes a battery of configurable, hardware-optimised feature extraction functions along with a decision tree ensemble classifier, thus serving as an edge AI device for local sensor data processing. We validate the HAR-ASIC based on post-layout process data with five HAR datasets and show the design scalability for configurations to maximise energy saving and others to maximise recognition performance. We show that feature extraction often requires up to 100 times more energy than the classification function. Our configuration analysis shows that feature extraction energy consumption can be reduced by factors of two to five, with at most 3% loss in F1-score, depending on the dataset. Across all datasets, feature extraction and classification energy was between 64 and 678 nJ per inference for Pareto-optimal configurations using sliding window buffers of up to 512 samples. We conclude that the highly configurable HAR-ASIC design could be the basis to realise ultra-low power sensor-edge AI systems for continuous wearable HAR and possibly further edge AI applications.
- Open Access
- 16 May 2026
- Published by Elsevier in SSRN Electronic Journal
Laboratory and season-long field evaluation of AI-based predictive control for residential heat pumps in DHW and space-heating operation
Residential heat pumps are commonly controlled using static rule-based controllers such as fixed heating curves and hysteresis-based DHW control, which can lead to unnecessary temperature lifts and avoidable storage losses as building and occupancy conditions change. This paper presents two AI-enabled predictive control strategies for (i) DHW production and (ii) space-heating supply-temperature control. In both cases, forecasting/modeling and optimization are separated to facilitate implementation. For DHW, a learned demand forecast is combined with Modelica-based simulation-in-the-loop scheduling that minimizes electrical energy while enforcing service constraints. Laboratory experiments show reductions in electrical energy use of 5-8% for an individual-housing configuration and 38-43% for a collective-housing configuration, together with a substantial increase in the heat-pump coefficient of performance (COP). For space heating, an attention-augmented encoder-decoder LSTM temperature predictor is embedded in a fast surrogate-assisted receding-horizon controller. A field trial in one residential building during the 2024-2025 heating season showed an 8% reduction in daily electricity use, an increase in mean COP from 3.95 to 4.15, and a reduction in mean absolute comfort deviation from 0.3 to 0.1 K. The results demonstrate that forecast-informed optimization can improve heat-pump efficiency while maintaining comfort, although broader field validation across building types and climates remains necessary.
- 16 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessLaboratory and season-long field evaluation of AI-based predictive control for residential heat pumps in DHW and space-heating operation
Residential heat pumps are commonly controlled using static rule-based controllers such as fixed heating curves and hysteresis-based DHW control, which can lead to unnecessary temperature lifts and avoidable storage losses as building and occupancy conditions change. This paper presents two AI-enabled predictive control strategies for (i) DHW production and (ii) space-heating supply-temperature control. In both cases, forecasting/modeling and optimization are separated to facilitate implementation. For DHW, a learned demand forecast is combined with Modelica-based simulation-in-the-loop scheduling that minimizes electrical energy while enforcing service constraints. Laboratory experiments show reductions in electrical energy use of 5-8% for an individual-housing configuration and 38-43% for a collective-housing configuration, together with a substantial increase in the heat-pump coefficient of performance (COP). For space heating, an attention-augmented encoder-decoder LSTM temperature predictor is embedded in a fast surrogate-assisted receding-horizon controller. A field trial in one residential building during the 2024-2025 heating season showed an 8% reduction in daily electricity use, an increase in mean COP from 3.95 to 4.15, and a reduction in mean absolute comfort deviation from 0.3 to 0.1 K. The results demonstrate that forecast-informed optimization can improve heat-pump efficiency while maintaining comfort, although broader field validation across building types and climates remains necessary.
- Open Access
- 7 May 2026
- Published by Elsevier in SSRN Electronic Journal
Development and field evaluation of AI-driven adaptive control algorithms for enhancing residential heat pump efficiency
Residential heat pumps are commonly controlled using static rule-based controllers such as fixed heating curves and hysteresis-based DHW control, which can lead to unnecessary temperature lifts and avoidable storage losses as building and occupancy conditions change. This paper presents two AI-enabled predictive control strategies for (i) DHW production and (ii) space-heating supply-temperature control. In both cases, forecasting/modeling and optimization are separated to facilitate implementation. For DHW, a learned demand forecast is combined with Modelica-based simulation-in-the-loop scheduling that minimizes electrical energy while enforcing service constraints. Laboratory experiments show reductions in electrical energy use of 5-8% for an individual-housing configuration and 38-43% for a collective-housing configuration, together with a substantial increase in the heat-pump coefficient of performance (COP). For space heating, an attention-augmented encoder-decoder LSTM temperature predictor is embedded in a fast surrogate-assisted receding-horizon controller. A field trial in one residential building during the 2024-2025 heating season showed an 8% reduction in daily electricity use, an increase in mean COP from 3.95 to 4.15, and a reduction in mean absolute comfort deviation from 0.3 to 0.1 K. The results demonstrate that forecast-informed optimization can improve heat-pump efficiency while maintaining comfort, although broader field validation across building types and climates remains necessary.
- 7 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessDevelopment and field evaluation of AI-driven adaptive control algorithms for enhancing residential heat pump efficiency
Residential heat pumps are commonly controlled using static rule-based controllers such as fixed heating curves and hysteresis-based DHW control, which can lead to unnecessary temperature lifts and avoidable storage losses as building and occupancy conditions change. This paper presents two AI-enabled predictive control strategies for (i) DHW production and (ii) space-heating supply-temperature control. In both cases, forecasting/modeling and optimization are separated to facilitate implementation. For DHW, a learned demand forecast is combined with Modelica-based simulation-in-the-loop scheduling that minimizes electrical energy while enforcing service constraints. Laboratory experiments show reductions in electrical energy use of 5-8% for an individual-housing configuration and 38-43% for a collective-housing configuration, together with a substantial increase in the heat-pump coefficient of performance (COP). For space heating, an attention-augmented encoder-decoder LSTM temperature predictor is embedded in a fast surrogate-assisted receding-horizon controller. A field trial in one residential building during the 2024-2025 heating season showed an 8% reduction in daily electricity use, an increase in mean COP from 3.95 to 4.15, and a reduction in mean absolute comfort deviation from 0.3 to 0.1 K. The results demonstrate that forecast-informed optimization can improve heat-pump efficiency while maintaining comfort, although broader field validation across building types and climates remains necessary.
- Open Access
- 10 August 2024
- Published by Elsevier in Smart Energy
- Vol. 15
Presentation of a distributed testing infrastructure for joint experiments across multiple remote laboratories for robust development of new district heating concepts
- 10 August 2024
- Published by Elsevier in Smart Energy
- Vol. 15
Open AccessPresentation of a distributed testing infrastructure for joint experiments across multiple remote laboratories for robust development of new district heating concepts
- Open Access
- 13 January 2024
- Published by Elsevier in Applied Energy
- Vol. 358
Model predictive control of bidirectional heat transfer in prosumer-based solar district heating networks
- 13 January 2024
- Published by Elsevier in Applied Energy
- Vol. 358
Open AccessModel predictive control of bidirectional heat transfer in prosumer-based solar district heating networks
- Open Access
- 1 November 2019
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1343 (1) , 012068
Model-predictive control for testing energy flexible heat pump operation within a Hardware-in-the-Loop setting
Model-predictive control is a smart control technique that can unlock the potential of the building’s thermal production leading to improvements in energy efficiency or energy flexibility, which is obtained by a demand responsive operation based on external grid signals. This work explains the set-up of a Hardware-in-the-Loop experiment to test an energy flexible heat pump controller under realistic conditions. The developed simple, low-cost model-predictive control algorithm can easily be integrated with a traditional heat pump controller.
- 1 November 2019
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1343 (1) , 012068
Open AccessModel-predictive control for testing energy flexible heat pump operation within a Hardware-in-the-Loop setting
Model-predictive control is a smart control technique that can unlock the potential of the building’s thermal production leading to improvements in energy efficiency or energy flexibility, which is obtained by a demand responsive operation based on external grid signals. This work explains the set-up of a Hardware-in-the-Loop experiment to test an energy flexible heat pump controller under realistic conditions. The developed simple, low-cost model-predictive control algorithm can easily be integrated with a traditional heat pump controller.