1. |
- Ding, Yiyu, et al.
(författare)
-
A study on data-driven hybrid heating load prediction methods in low-temperature district heating : An example for nursing homes in Nordic countries
- 2022
-
Ingår i: Energy Conversion and Management. - : Elsevier BV. - 0196-8904 .- 1879-2227. ; 269
-
Tidskriftsartikel (refereegranskat)abstract
- In the face of green energy initiatives and progressively increasing shares of more energy-efficient buildings, there is a pressing need to transform district heating towards low-temperature district heating. The substantially lowered supply temperature of low-temperature district heating broadens the opportunities and challenges to integrate distributed renewable energy, which requires enhancement on intelligent heating load prediction. Meanwhile, to fulfill the temperature requirements for domestic hot water and space heating, separate energy conversion units on user-side, such as building-sized boosting heat pumps shall be implemented to upgrade the temperature level of the low-temperature district heating network. This study conducted hybrid heating load prediction methods with long-term and short-term prediction, and the main work consisted of four steps: (1) acquisition and processing of district heating data of 20 district heating supplied nursing homes in the Nordic climate (2016–2019); (2) long-term district heating load prediction through linear regression, energy signature curve in hourly resolution, providing an overall view and boundary conditions for the unit sizing; (3) short-term district heating load prediction through two Artificial Neural Network models, f72 and g120, with different prediction input parameters; (4) evaluation of the predicted load profiles based on the measured data. Although the three prediction models met the quality criteria, it was found that including the historical hourly heating loads as the input to the forecasting model enhanced the prediction quality, especially for the peak load and low-mild heating season. Furthermore, a possible application of the heating load profiles was proposed by integrating two building-sized heat pumps in low-temperature district heating, which may be a promising heat supply method in low-temperature district heating.
|
|
2. |
- Habib, Mustapha, PhD, et al.
(författare)
-
A hybrid machine learning approach for the load prediction in the sustainable transition of district heating networks
- 2023
-
Ingår i: Sustainable cities and society. - : Elsevier BV. - 2210-6707. ; 90
-
Tidskriftsartikel (refereegranskat)abstract
- Current district heating networks are undergoing a sustainable transition towards the 4th and 5th generation of district heating networks, characterized by the integration of different types of renewable energy sources (RES) and low operational temperatures, i.e., 55 ◦C or lower. Due to the lower temperature difference between supply and return, it is necessary to develop novel methods to understand the loads accurately and provide operation scenarios to anticipate demand peaks and increase flexibility in the energy network, both for long- and short- term horizons. In this study, a hybrid machine-learning (ML) method is developed, combining a clustering pre-processing step with a multi-input artificial neural network (ANN) model to predict heat loads in buildings cluster-wise. Specifically, the impact of time-series data clustering, as a pre-processing step, on the performance of ML models was investigated. It was found that data clustering contributes effectively to the reduction of data training costs by limiting the training processes to representative clusters only instead of all datasets. Additionally, low-quality data, including outliers and large measurement gaps, are excluded from the training to enhance the overall prediction performance of the models.
|
|
3. |
- Lari, Giacomo M., et al.
(författare)
-
Environmental and economical perspectives of a glycerol biorefinery
- 2018
-
Ingår i: Energy and Environmental Sciences. - : Royal Society of Chemistry (RSC). - 1754-5692 .- 1754-5706. ; 11:5, s. 1012-1029
-
Tidskriftsartikel (refereegranskat)abstract
- Glycerol conversion into chemicals and fuel additives is pursued to valorise a burgeoning by-product in the bioenergy sector. To this aim, heterogeneous catalysts have been developed that enable, in many cases, efficient and green transformations. Still, the evaluation of the environmental and economic footprint that would be associated with their large-scale application has often been neglected, limiting their commercial attractiveness. Furthermore, the impact of integrating different glycerol upgrading routes within a biorefinery, which is highly instrumental to determine the effective sustainability and profitability of biodiesel production from vegetable oils, has not been assessed. Here, the manufacture of the most relevant chemical derivatives of glycerol is considered, i.e., lactic acid, acrylic acid, glycerol carbonate, propanediols, epichlorohydrin and allyl alcohol. State-of-the-art catalysts for each upgrading route are briefly reviewed. Based on their performances, processes are rigorously modelled and relevant indicators, the global warming potential, the cumulative energy demand and the operating costs, quantified by life-cycle analysis. Glycerol-based processes are generally found more attractive than the conventional technologies nowadays applied for the production of the same chemicals, among which the paths to lactic acid and glycerol carbonate are particularly promising. In addition, the process variables mostly contributing to the environmental and cost metrics are identified. Accordingly, future studies should target further optimisation mainly in relation to selectivity, solvent volatility, reactants ratio and catalyst stability. Finally, the processes are integrated simulating a prospective glycerol biorefinery and the advantages deriving from the exchange of heat between the different routes quantified. If the glycerol feed is split equally among all routes the CO 2 emissions and energy requirements are decreased by 15 and 32%, respectively, and the profit is increased by 5% as compared to the sum of the individual glycerol-based processes. In order to minimise the ecological impact of the biorefinery, glycerol should be rather divided in an 80:20 mass ratio among 1,2-propanediol and glycerol carbonate production, which are expected to have a significant market size. The innovative approach outlined in this work holds potential to guide both fundamental chemical research and process design in the development of CO 2 and other bio-refineries.
|
|
4. |
- Papadokonstantakis, Stavros, 1974, et al.
(författare)
-
Superstructure investigation for P-recovery technologies integration with macroalgae based hydrothermal liquefaction
- 2018
-
Ingår i: Computer Aided Chemical Engineering. - 1570-7946. ; 44, s. 1753-1758
-
Bokkapitel (övrigt vetenskapligt/konstnärligt)abstract
- The aim of this work is to identify profitable and environmentally benign technological paths connecting phosphorus (P) recovery with macroalgae based hydrothermal liquefaction (HTL). For this purpose, a thorough literature review of relevant technologies in different fields of application was carried out. Together with a citation network analysis (CNA) a framework comprising qualitative and quantitative information about process significance, conditions, material and energy flows for a comprehensive list of potentially involved technologies was developed. On the basis of this information framework, processes were combined into a superstructure of options for P-recovery from macroalgae based HTL. Based on criteria such as technology maturity and severity of process conditions, two different but not mutually exclusive approaches for utilizing HTL waste streams were identified: exploiting the carbon and/or the nutrients potential of the streams. The process layout selected consists of hydrothermal liquefaction, catalytic hydrothermal gasification (CHG), incineration of solid residues, acidic leaching of incineration ashes, crystallization and precipitation of P in form of magnesium ammonium phosphate (struvite), methane steam reforming and biocrude upgrading through hydrotreatment. The selected layout's model was based on HTL reaction kinetics (kinetic constants extrapolated from experiment data and verified with laboratory results from HTL of macroalgae Ulva Lactuca collected from several sites of the Swedish coast) and on performances averaging (according to literature sources) for the other subprocesses sections. Net revenues as high as 21 $/tdry macroalgaewere predicted, coming mainly from upgraded oil and a small part from struvite, while including material and energy costs for operating the system. This revenue is highly affected by the cost of the macroalgae feedstock. Finally, environmental aspects and constraints related to the process, were addressed and evaluated with the cumulative energy demand (CED) indicator, which resulted stable around 34 MJeq/kgproducts.
|
|
5. |
- Timoudas, Thomas Ohlson, et al.
(författare)
-
A novel machine learning approach to predict short-term energy load for future low-temperature district heating
- 2022
-
Ingår i: The REHVA European HVAC Journal. ; :Dec, s. 19-24
-
Tidskriftsartikel (refereegranskat)abstract
- In this work, we develop machine learning methods to forecast the day-ahead heating energy demand of district heating (DH) end-users in hourly resolution, using existing metering data for DH end-users and weather data. The focus of the study is a detailed analysis of the accuracy levels of short-term load prediction methods. In particular, accuracy levels are quantified for Artificial Neural Network (ANN) models with variations in the input parameters. The importance of historical data is investigated – in particular the importance of including historical hourly heating loads as input to the forecasting model. Additionally, the impact of different lengths of the historical input data is studied. Our methods are evaluated and validated using metering data from a live use-case in a Scandinavian environment, collected from 20 DH-supplied nursing homes through the years of 2016 to 2019. This study demonstrates that, although there is a strong linear relationship between outdoor temperature and heating load, it is still important to include historical heating loads as an input for prediction of future heating loads. Furthermore, the results show that it is important to include historical data from at least the preceding 24 hours, but suggest diminishing returns of including data much further back than that. The resulting models demonstrate the practical feasibility of such prediction models in a live use-case.
|
|