Appraisal of the support vector machine to forecast residential heating demand for the District Heating System based on the monthly overall natural gas consumption

Energy ◽  
2015 ◽  
Vol 93 ◽  
pp. 1558-1567 ◽  
Author(s):  
Nima Izadyar ◽  
Hossein Ghadamian ◽  
Hwai Chyuan Ong ◽  
Zeinab moghadam ◽  
Chong Wen Tong ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Natural Gas ◽  
District Heating ◽  
Heating System ◽  
Support Vector ◽  
District Heating System ◽  
Residential Heating ◽  
Gas Consumption ◽  
Natural Gas Consumption

scholarly journals Data-Driven Machine-Learning Model in District Heating System for Heat Load Prediction: A Comparison Study

2016 ◽  
Vol 2016 ◽  
pp. 1-11 ◽  
Author(s):  
Fisnik Dalipi ◽  
Sule Yildirim Yayilgan ◽  
Alemayehu Gebremedhin
Keyword(s):  
Machine Learning ◽  
Heat Load ◽  
District Heating ◽  
Heating System ◽  
Partial Least Square ◽  
Supervised Machine Learning ◽  
Data Driven ◽  
Support Vector ◽  
Load Prediction ◽  
District Heating System

We present our data-driven supervised machine-learning (ML) model to predict heat load for buildings in a district heating system (DHS). Even though ML has been used as an approach to heat load prediction in literature, it is hard to select an approach that will qualify as a solution for our case as existing solutions are quite problem specific. For that reason, we compared and evaluated three ML algorithms within a framework on operational data from a DH system in order to generate the required prediction model. The algorithms examined are Support Vector Regression (SVR), Partial Least Square (PLS), and random forest (RF). We use the data collected from buildings at several locations for a period of 29 weeks. Concerning the accuracy of predicting the heat load, we evaluate the performance of the proposed algorithms using mean absolute error (MAE), mean absolute percentage error (MAPE), and correlation coefficient. In order to determine which algorithm had the best accuracy, we conducted performance comparison among these ML algorithms. The comparison of the algorithms indicates that, for DH heat load prediction, SVR method presented in this paper is the most efficient one out of the three also compared to other methods found in the literature.

scholarly journals Evaluating the Emissions of the Heat Supplied by District Heating Networks through A Life Cycle Perspective

2020 ◽  
Vol 2 (4) ◽  
pp. 392-405
Author(s):  
Francesco Neirotti ◽  
Michel Noussan ◽  
Marco Simonetti
Keyword(s):  
Life Cycle ◽  
Natural Gas ◽  
District Heating ◽  
Heating System ◽  
Plant Production ◽  
Life Cycle Assessment Methodology ◽  
District Heating System ◽  
Heating And Cooling ◽  
Life Cycle Perspective ◽  
Urban Contexts

The Life Cycle Assessment methodology has proven to be effective in evaluating the impacts of goods production throughout their life cycle. While many studies are available on specific products, in recent years a growing interest is related to the analysis of services, including energy supply for final customers. Different LCA evaluations are available for electricity, while the heating and cooling sector has not yet been properly investigated. The objective of this study is the analysis of the specific impacts of the heat supplied to the final users connected to a district heating system, in comparison with traditional individual natural gas boilers, which represent the baseline heating solution in several urban contexts in Europe. The results show that the comparison is heavily dependent on the allocation method used for combined heat and power plant production. District Heating impact on heat supplied to the users can vary from 0.10 to 0.47 kgCO2eq/kWh, while distributed natural gas boilers present an overall impact equal to 0.27 kgCO2eq/kWh.

scholarly journals Prediction of heating load fluctuation based on fuzzy information granulation and support vector machine

2020 ◽  
pp. 307-307
Author(s):  
Tao Wang ◽  
Tingyu Ma ◽  
Dongsong Yan ◽  
Jing Song ◽  
Jianshuo Hu ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Prediction Model ◽  
District Heating ◽  
Series Data ◽  
Support Vector ◽  
Fuzzy Information ◽  
District Heating System ◽  
Information Granulation ◽  
Heating Load ◽  
Fuzzy Information Granulation

District heating systems are an important part of the future smart energy system and are seen as a tool to achieve energy efficiency goals in the EU. In order to achieve the real sense of heating on demand, based on historical heating load data, first of all, the heating load time series data was dealing with fuzzy information granulation, and then the cross-validation was used to explore the advantages of the data potential. Then the support vector machine regression prediction model was used for the prediction of the granulation data, finally, the heating load of a district heating system is simulated and verified. The simulation results show that the prediction model can effectively predict the trend of heating load, and provide a theoretical basis for the prediction of district heating load.

scholarly journals Long-term Green Innovation Opportunities Within the Hungarian District Heating Sector Towards 2030

2016 ◽  
Vol 4 (1) ◽  
pp. 12-24
Author(s):  
Balint Horvath ◽  
Maria Borocz ◽  
Sandor Zsarnoczai ◽  
Csaba Fogarassy
Keyword(s):  
Natural Gas ◽  
District Heating ◽  
Heating System ◽  
Simple Fact ◽  
District Heating System ◽  
Primary Input ◽  
Cooling Systems ◽  
The Public ◽  
Heating And Cooling

Abstract Natural gas is still the primary input of the Hungarian heating and cooling systems, therefore it still makes most of the overheads. One of the main obstacles of a competitive district heating system is the public opinion which still considers this service more expensive than the traditional heating forms. According to the absolute numbers this assumption might be valid but from a more accurate economic perspective, heat production has more aspects to stress. Most people forget about the simple fact that the maintenance costs of natural gas based systems are rather outsourced to the consumer than in the case of district heating. Furthermore, the uneven rate of the fixed and variable costs of this technology does not prove to be optimal for service developments. Investigating the future tendencies highlight that encouraging the efficiency improvement of district heating and the spread of technological innovation in the sector does not belong to the top priorities. Still, avoiding this problem it could lead serious deadweight losses in the case of the heating sector.

Short-Term Forecasting of Natural Gas Consumption Using Factor Selection Algorithm and Optimized Support Vector Regression

2018 ◽  
Vol 141 (3) ◽  
Author(s):  
Nan Wei ◽  
Changjun Li ◽  
Chan Li ◽  
Hanyu Xie ◽  
Zhongwei Du ◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Natural Gas ◽  
Support Vector Regression ◽  
Series Data ◽  
Support Vector ◽  
Selection Algorithm ◽  
Short Term ◽  
Proposed Model ◽  
Gas Consumption ◽  
Natural Gas Consumption

Forecasting of natural gas consumption has been essential for natural gas companies, customers, and governments. However, accurate forecasting of natural gas consumption is difficult, due to the cyclical change of the consumption and the complexity of the factors that influence the consumption. In this work, we constructed a hybrid artificial intelligence (AI) model to predict the short-term natural gas consumption and examine the effects of the factors in the consumption cycle. The proposed model combines factor selection algorithm (FSA), life genetic algorithm (LGA), and support vector regression (SVR), namely, as FSA-LGA-SVR. FSA is used to select factors automatically for different period based on correlation analysis. The LGA optimized SVR is utilized to provide the prediction of time series data. To avoid being trapped in local minima, the hyper-parameters of SVR are determined by LGA, which is enhanced due to newly added “learning” and “death” operations in conventional genetic algorithm. Additionally, in order to examine the effects of the factors in different period, we utilized the recent data of three big cities in Greece and divided the data into 12 subseries. The prediction results demonstrated that the proposed model can give a better performance of short-term natural gas consumption forecasting compared to the estimation value of existing models. Particularly, the mean absolute range normalized errors of the proposed model in Athens, Thessaloniki, and Larisa are 1.90%, 2.26%, and 2.12%, respectively.

scholarly journals Effects of implementation of co-generation in the district heating system of the Faculty of Mechanical Engineering in Nis

2010 ◽  
Vol 14 (suppl.) ◽  
pp. 41-51 ◽  
Author(s):  
Mladen Stojiljkovic ◽  
Mirko Stojiljkovic ◽  
Bratislav Blagojevic ◽  
Goran Vuckovic ◽  
Marko Ignjatovic
Keyword(s):  
Natural Gas ◽  
Energy Savings ◽  
Boiler House ◽  
District Heating ◽  
Electrical Energy ◽  
Heating System ◽  
Primary Energy ◽  
District Heating System ◽  
Heating Systems ◽  
District Heating Systems

Implementation of co-generation of thermal and electrical energy in district heating systems often results with higher overall energy efficiency of the systems, primary energy savings and environmental benefits. Financial results depend on number of parameters, some of which are very difficult to predict. After introduction of feed-in tariffs for generation of electrical energy in Serbia, better conditions for implementation of co-generation are created, although in district heating systems barriers are still present. In this paper, possibilities and effects of implementation of natural gas fired cogeneration engines are examined and presented for the boiler house that is a part of the district heating system owned and operated by the Faculty of Mechanical Engineering in Nis. At the moment, in this boiler house only thermal energy is produced. The boilers are natural gas fired and often operate in low part load regimes. The plant is working only during the heating season. For estimation of effects of implementation of co-generation, referent values are taken from literature or are based on the results of measurements performed on site. Results are presented in the form of primary energy savings and greenhouse gasses emission reduction potentials. Financial aspects are also considered and triangle of costs is shown.

Sign in / Sign up

Export Citation Format

Share Document