Intelligent Consumer Flexibility Management With Neural Network-Based Planning and Control

Kiljander, Jussi; Sarala, Roope; Rehu, Jari; Pakkala, Daniel; Pääkkönen, Pekka; Takalo-Mattila, Janne; Känsälä, Klaus

doi:10.1109/access.2021.3060871

Cited by 9 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In theory, any generic function approximator could be used instead of an ANN to approximate the physics-based simulator. An ANN model was selected for this study mainly for following reasons: (1) ANN models are highly parallel and thus provide fast inference, (2) ANN models provide gradient based optimization through back propagation, which is important when the model is used in planning and control [17][18][19], and (3) ANN platforms such as TensorFlow also provide good support for model deployment in edge environments [14,15].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Building Heat Demand Forecasting by Training a Common Machine Learning Model with Physics-Based Simulator

et al. 2021

Self Cite

View full text Add to dashboard Cite

Accurate short-term forecasts of building energy consumption are necessary for profitable demand response. Short-term forecasting methods can be roughly classified into physics-based modelling and data-based modelling. Both of these approaches have their advantages and disadvantages and it would be therefore ideal to combine them. This paper proposes a novel approach that allows us to combine the best parts of physics-based modelling and machine learning while avoiding many of their drawbacks. A key idea in the approach is to provide a variety of building parameters as input for an Artificial Neural Network (ANN) and train the model with data from a large group of simulated buildings. The hypothesis is that this forces the ANN model to learn the underlying simulation model-based physics, and thus enables the ANN model to be used in place of the simulator. The advantages of this type of model is the combination of robustness and accuracy from a high-detail physics-based model with the inference speed, ease of deployment, and support for gradient based optimization provided by the ANN model. To evaluate the approach, an ANN model was developed and trained with simulated data from 900–11,700 buildings, including equal distribution of office buildings, apartment buildings, and detached houses. The performance of the ANN model was evaluated with a test set consisting of 60 buildings (20 buildings for each category). The normalized root mean square errors (NRMSE) were on average 0.050, 0.026, 0.052 for apartment buildings, office buildings, and detached houses, respectively. The results show that the model was able to approximate the simulator with good accuracy also outside of the training data distribution and generalize to new buildings in new geographical locations without any building specific heat demand data.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Machine learning models also typically provide fast enough inference for model-based optimization. Moreover, gradient-based methods such as neural networks make it possible to utilize gradient information and thus converge much faster than gradient-free methods [17][18][19]. However, ML models also have their limitations.…”

Section: Introductionmentioning

confidence: 99%

Building Heat Demand Forecasting by Training a Common Machine Learning Model with Physics-Based Simulator

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Reference [34] used a dense neural network with Bayesian regulation backpropagation to predict the maximal demand change. In [35], a dense neural network that captured the user behaviors was integrated in the model predictive control scheme. A similar idea was applied in [36] where some special designs were implemented to improve the estimation accuracy.…”

Section: B Literature Reviewmentioning

confidence: 99%

Estimating Demand Flexibility Using Siamese LSTM Neural Networks

Ruan,

Kirschen,

Zhong

et al. 2021

Preprint

View full text Add to dashboard Cite

There is an opportunity in modern power systems to explore the demand flexibility by incentivizing consumers with dynamic prices. In this paper, we quantify demand flexibility using an efficient tool called time-varying elasticity, whose value may change depending on the prices and decision dynamics. This tool is particularly useful for evaluating the demand response potential and system reliability. Recent empirical evidences have highlighted some abnormal features when studying demand flexibility, such as delayed responses and vanishing elasticities after price spikes. Existing methods fail to capture these complicated features because they heavily rely on some predefined (often oversimplified) regression expressions. Instead, this paper proposes a model-free methodology to automatically and accurately derive the optimal estimation pattern. We further develop a twostage estimation process with Siamese long short-term memory (LSTM) networks. Here, a LSTM network encodes the price response, while the other network estimates the time-varying elasticities. In the case study, the proposed framework and models are validated to achieve higher overall estimation accuracy and better description for various abnormal features when compared with the state-of-the-art methods.

show abstract

Using existing cold stores as thermal energy storage

Svane,

Enevoldsen,

Xydis

2023

Environ Sci Pollut Res

View full text Add to dashboard Cite

The industrial cold stores can act as thermal energy stores that can store the energy as passive thermal energy. The cold stores have intentions to contribute with flexible consumption but need some knowledge about the potential. By cooling the cold stores and the goods further down when the energy is cheaper, there is a potential of an attractive business case, especially if the elspot price can be predicted further into the future. The cold stores can provide flexibility by load shifting to the energy grid by moving their extensive energy use to off-peak hours. To fulfill the potential, it is necessary to measure some data in the cold stores to be able to control them and ensure food safety. A case study was tested and revealed that by cooling further in periods of low-cost electricity could results in 30% savings. With proper elspot price forecasting this percentage could reach up to 40%. Theoretically, by utilizing the full capacity of cold stores in Denmark for thermal energy storage, it is possible to use 2% of the average wind electricity production.

show abstract

Intelligent Consumer Flexibility Management With Neural Network-Based Planning and Control

Cited by 9 publications

References 29 publications

Building Heat Demand Forecasting by Training a Common Machine Learning Model with Physics-Based Simulator

Building Heat Demand Forecasting by Training a Common Machine Learning Model with Physics-Based Simulator

Estimating Demand Flexibility Using Siamese LSTM Neural Networks

Using existing cold stores as thermal energy storage

Contact Info

Product

Resources

About