Machine learning models have proven to be reliable methods in classification tasks. However, little research has been conducted on the classification of dwelling characteristics based on smart meter and weather data before. Gaining insights into dwelling characteristics, which comprise of the type of heating system used, the number of inhabitants, and the number of solar panels installed, can be helpful in creating or improving the policies to create new dwellings at nearly zero-energy standard. This paper compares different supervised machine learning algorithms, namely Logistic Regression, Support Vector Machine, K-Nearest Neighbor, and Long-short term memory, and methods used to correctly implement these algorithms. These methods include data pre-processing, model validation, and evaluation. Smart meter data, which was used to train several machine learning algorithms, was provided by Groene Mient. The models that were generated by the algorithms were compared on their performance. The results showed that the Long-short term memory performed the best with 96% accuracy. Cross Validation was used to validate the models, where 80% of the data was used for training purposes and 20% was used for testing purposes. Evaluation metrics were used to produce classification reports, which indicates that the Long-short term memory outperforms the compared models on the evaluation metrics for this specific problem.
Global awareness on energy consumption and the environmental impacts of fossil fuels boost actions and create more supportive policies towards sustainable energy systems, in the last energy outlook, by the International Energy Agency, it was forecasted totals of 3600 GW from 2016 to 2040 of global deployment of renewables sources (RES), covering 37% of the power generation. While the Natural Gas overtake the coal demand in the energy mix, growing around 50%, manly by more efficiency system and the use of LNG for long-distance gas trades. The energy infrastructure will be more integrated, deploying decentralized and Hybrid Energy Networks (HEN).This transformation on the energy mix leads to new challenges for the energy system, related to the uncertainty and variability of RES, such as: Balancing flexibility, it means having sufficient resources to accommodate when variable production increase and load levels fall (or vice versa). And Efficiency in traditional fired plants, the often turn on and off or modify their output levels to accommodate changes in variable demand, can result in a decrease in efficiency, particularly from thermal stresses on equipment. This paper focus in the possibility to offer balancing resources from the LNG regasification, while ensure an efficient system.In order to asses this issue, using the energy Hub concept a model of a distributed HEN was developed. The HEN consist in a Waste to Energy plant (W2E), a more sustainable case of Combine Heat and Power (CHP) coupled with a LNG cold recovery regasification. To guarantee a most efficiency operation, the HEN was optimized to minimized the Exergy efficiency, additionally, the system is constrained by meeting Supply with variable demand, putting on evidence the sources of balancing flexibility. The case study show, the coupled system increases in overall exergy efficiency from 25% to 35% compared to uncoupled system; it brings additional energy between 1.75 and 3 MW, and it meets variable demand in the most exergy efficient with power from LNG reducing inputs of other energy carriers. All this indicated that LNG cold recovery in regasification coupled other energy systems is as promising tool to support the transition towards sustainable energy systems.
The future energy system could benefit from the integration of independent gas, heat and electricity infrastructures. Such a hybrid energy network could support the increase of intermittent renewable energy sources by offering increased operational flexibility. Nowadays, the expectations on Natural Gas resources forecast an increase in the application of Liquefied Natural Gas (LNG), as a means of storage and transportation, which has a high exergy value. Therefore, we analyzed the integration of decentralized LNG regasification with a Waste-to-Energy (W2E) plant for a practice-based case to get an idea on how it might affect the balancing of supply and demand, under optimized exergy efficient conditions. We compared an independent system with an integrated system that consists of the use of the LNG cold to cool the condenser of the W2E plant, as well as the expansion of the regasified LNG in an expander, using a simplified deterministic model based on the energy hub concept. We use the hourly measured electricity and heat demand patterns for 200 households with 35% of the households producing electricity from PV according to a typical measured solar insolation pattern in The Netherlands. The results indicate that the integration affects the imbalance for electricity and heat compared to the independent system. If the electricity demand is met, both the total yearly heat shortage and heat excess are reduced for the integrated system. If the heat demand is met, the total yearly electricity shortage is also reduced (with 100 MWh). However, the total yearly electricity excess is then increased (with 300 MWh). We observed that these changes are solely due to the increase in exergy efficiencies for heat and electricity of the W2E Rankine cycle. The efficiency of the expander is too low to offer a significant contribution to the electricity demand. Therefore, future research should focus on the affect that can be obtained by to other means of integration (e.g. Organic Rankine Cycle and Stirling Cycle).
