Search results

This study aims to compare and evaluate the application of commonly used machine learning (ML) algorithms used to develop models for assessing energy efficiency of buildings.

This study foremostly combined building energy efficiency ratings from several data sources and used them to create predictive models using a variety of ML methods. Secondly, to test the hypothesis of ensemble techniques, this study designed a hybrid stacking ensemble approach based on the best performing bagging and boosting ensemble methods generated from its predictive analytics.

Based on performance evaluation metrics scores, the extra trees model was shown to be the best predictive model. More importantly, this study demonstrated that the cumulative result of ensemble ML algorithms is usually always better in terms of predicted accuracy than a single method. Finally, it was discovered that stacking is a superior ensemble approach for analysing building energy efficiency than bagging and boosting.

While the proposed contemporary method of analysis is assumed to be applicable in assessing energy efficiency of buildings within the sector, the unique data transformation used in this study may not, as typical of any data driven model, be transferable to the data from other regions other than the UK.

This study aids in the initial selection of appropriate and high-performing ML algorithms for future analysis. This study also assists building managers, residents, government agencies and other stakeholders in better understanding contributing factors and making better decisions about building energy performance. Furthermore, this study will assist the general public in proactively identifying buildings with high energy demands, potentially lowering energy costs by promoting avoidance behaviour and assisting government agencies in making informed decisions about energy tariffs when this novel model is integrated into an energy monitoring system.

This study fills a gap in the lack of a reason for selecting appropriate ML algorithms for assessing building energy efficiency. More importantly, this study demonstrated that the cumulative result of ensemble ML algorithms is usually always better in terms of predicted accuracy than a single method.

The purpose of this paper is to assess next hour load forecast in medium voltage electricity distribution.

The methodological approach used in this paper, is based on a regressive method – artificial neural network. A real life case study is used for illustrating the defined steps and to discuss the results.

The presence of a de‐regulated environment reinforces the need of short‐term forecast algorithms (STLF). Actions like network management, load dispatch and network reconfiguration under quality of service constraints, require reliable next hour load forecasts. Methodological approaches based on regressive methods such as artificial neural networks are widely used in STLF, with satisfactory results. The construction of an “efficient” artificial neural networks goes through, among other factors, the construction of an “efficient” input vector (IV), in order to avoid over fitting problems and keeping the global simplicity of the model. The explanatory variables normally used, are grouped in two major classes, endogenous and exogenous. The endogenous variables are load values in past instants, and the exogenous variables are normally climatic. The main findings with this kind of vector presents satisfactory results compared to other proposals in the literature.

This paper makes use of a procedural sequence for the pre‐processing phase that allows capturing some predominant relations among certain different sets of the available data, providing a more solid basis to decisions regarding the composition of the IV. To deal with load increasing during the winter period, the forecast average daily temperature was used in order to produce an indicator of the daily load average for the forecast day. This information brings more accuracy to the model.

This paper aims to address a central concern in modeling and simulating electric grids and the information infrastructure that monitors and controls them. The paper discusses the need for and methods to construct simulation models that include important interactions between the physical and computational elements of a large power system.

The paper offers a particular approach to modeling and simulation of hybrid systems as an enabling technology for analysis (via simulation) of modern electric power grids. The approach, based on the discrete event system specification, integrates existing simulation tools into a unified simulation scheme. The paper demonstrates this approach with an integrated information and electric grid model of a distributed, automatic frequency maintenance activity.

Power grid modernization efforts need powerful modeling and simulation tools for hybrid systems.

The main limitation of this approach is a lack of advanced simulation tools that support it. Existing commercial offerings are not designed to support integration with other simulation software products. The approach to integrating continuous and discrete event simulation models can overcome this problem by allowing specific tools to focus on continuous or discrete event dynamics. This will require, however, adjustments to the underlying simulation technology.

This paper demonstrates an approach to simulating complex hybrid systems that can, in principle, be supported by existing simulation tools. It also indicates how existing tools must be modified to support our approach.

The purpose of this paper is to tackle the problem an electricity trader faces when trying to set and validate his sale prices.

The solution approach consists in offering adequate incentives to the customers in order to encourage them to shift their consumptions to more favorable time periods; this is achieved by suitable price modifications. The problem of determining the most sensible prices to offer yields to a quadratic programing model which can be efficiently solved to optimality.

This paper analyses an opportunity that traders can exploit for increasing their profit margins and, in general, for setting and validating their electricity sale prices. The real case of an Italian trader has been analysed and the numerical results show that the obtained sale price modifications may produce savings, both for the trader and for his customers.

This research provides insights about the problem an electricity trader faces when setting his sale prices; it mainly focuses on the Italian market although the developed mathematical model is sufficiently general to be adopted in different scenarios.

The purpose of this paper is to solve the problem of committing electric power generators (unit commitment, UC), considering network constraints.

The UC is first solved with a local search based meta‐heuristic, following the assumption that all generators and loads are connected to a single network node. For evaluation purposes, the economical production levels of the units committed are computed by running a pre‐dispatch algorithm where network constraints are not included. If a good quality solution is reached, an economic dispatch (ED) with network constraints is performed, where the geographic location of generators and loads are considered. Therefore, the production level of each committed generator is performed that leads to the global lowest solution cost, regarding both the generators' costs and constraints and the power system network constraints.

The algorithm proposed is computationally efficient, given the time available for decision making. In addition, the solution for this algorithm, in terms of minimization of total costs, is generally better than the solution of the two phases approach. Some contractual and legal aspects related with the injection in network connections can also be included in the model.

UC with network constraints has a large potential of use, especially for small and medium size power systems. It reflects reality in a closer way and provides a more complete and realistic knowledge about the system in operation.

The paper presents an approach where the ED with network constraints is integrated with the UC procedure. The model described is currently implemented in an EMS package offered in the market – making it a case of successful transfer from science to industry.

The objective of this study is to highlight the questions arising in the design of district heating and cooling systems (DHCSs) in a distributed generation context and to present a model to help find cost‐effective solutions.

Literature on energy systems optimisation is reviewed and a mixed integer programming model for decentralized DHCSs design is developed and applied to two real case studies.

Distributed cooling generation partly coupled with distributed cogeneration and DH is the preferred solution in the examined areas. The optimal configurations, with special reference to network sizing and layout, significantly depend on heating demand profiles and energy prices.

Interdependencies between energy units sizing and network layout definition should be considered. Obtaining more robust and reliable network configurations should be the objective of future modelling efforts.

Despite the growth of distributed energy conversion, designers often rely on centralized concepts in order to reap economies of scale. The presented model helps in discovering less usual solutions representing the most profitable option.

Combining and comparing central and distributed production of heat and cooling under consideration of network costs.

The aim of this paper is to assess the state of spot price convergence between several European electricity day‐ahead markets.

The concept of a fully integrated market is developed through the arbitrage relationship in which spot prices at one location should equal spot prices at another location plus the price of transmission. Accordingly, neighbouring markets are analysed to measure the relevance or their respective interconnecting and transmission constraints. Exploratory data approach is used and results are discussed, namely by correlation analysis.

This paper empirically shows that price differences have decreased during the analysed period, suggesting that integration between markets might be rising. The correlation analysis indicates very few relationships between these continental European power exchanges, what makes us to anticipate continuing difficulties in the building of a single electricity market. Nevertheless, there is some evidence for local integration and some price convergence. Only France and Germany appear to be relatively integrated with higher correlation coefficients, compared to the other cases. In respect to the other markets, this correlation analysis demonstrates that price variations in several locations do not affect prices in the neighbouring locations. Spain appears to be poorly integrated with the other locations as might be expected by its peripheral position and limited cross‐border transmission capacity.

The paper assesses electricity market integration in the context of European Union spot prices and industry structure.

The purpose of this paper is to analyze medium‐term risks faced by electrical generation companies in competitive environments. Market risks faced by generation companies are caused by several variables subject to uncertainty. Hydro conditions, fuel (coal and natural gas) prices, system demand, and CO₂ emission price are the risk factors considered in the paper. Taking into account these risk factors, generation companies have to take decisions that would affect their economic results and their risk exposure.

This paper proposes a methodology to support the risk‐analysis decision‐making process. Firstly, different scenarios of risk factors are generated. Then, a market equilibrium model is used in order to assess the impact of the different sources of uncertainty. Finally, decision trees are used in order to analyze the variables subject to interest, such as electricity prices or companies' profits.

The proposed methodology can be enhanced to take into account scenarios of more risk factors, such as equipment failure or agents' behavior. Another future enhancement could be a detailed study of correlation between different risk factors.

A realistic case study is presented, showing the advantages of these techniques for medium‐term risk‐analysis and decision‐making processes. Several decision trees have been generated to assess the impact of the different risk factors in electricity prices and companies' profits. These decision trees provide valuable information for companies when facing their risk‐management process.

The approach presented here constitutes a valuable support to gain useful information for wise decision making and to hedge against risk.

The purpose of the work is to elaborate a model framework that includes location related temporal characteristics in energy supply and demand. These characteristics in mind an imaginable energy system setup can be explored with the framework. In a case study the possible coverage of the global energy demand, by solar‐ and wind power in junction with a backup technology is treated.

Spatially and temporally high disaggregated data describing different aspects of the energy supply side (especially devoted to renewable resources and related availabilities) as well as the energy demand side are investigated. This information is processed to serve as input for the TIMES model generator in a special adapted model. The complete workflow is enclosed in a graphical user interface implemented as a plugin in the software package ArGIS.

The elaborated case study shows the practicability of the approach to treat spatially and temporally high disaggregated problems in the energy system. Especially sensibilities of an optimal system setup in dependency on assumptions on specific costs for energy transport or storage can be investigated in a very detailed manner.

Since the spatial and temporal disaggregated examination implies the treatment of huge datasets, simplifications have to be made in the description of the technological setup of the energy system. The approach is appropriate to describe single scenario set‐ups but not a complete forecast based system development.

Geographic information systems (GIS) and geographic information are tied together with a conventional modeling approach of energy systems. That enables the cognition and quantification of influences and sensibilities related to spatial and temporal deviations in our energy system either on the supply or the demand side.