scholarly journals Interpretable Forecasting of Energy Demand in the Residential Sector

Energies ◽  
2021 ◽  
Vol 14 (20) ◽  
pp. 6568
Author(s):  
Nikos Sakkas ◽  
Sofia Yfanti ◽  
Costas Daskalakis ◽  
Eduard Barbu ◽  
Marharyta Domnich
Keyword(s):  
Decision Support ◽  
Energy Demand ◽  
Demand Forecasting ◽  
Time Frame ◽  
Policy Support ◽  
Investment Planning ◽  
Explanatory Variables ◽  
Residential Sector ◽  
Time Frames

Energy demand forecasting is practiced in several time frames; different explanatory variables are used in each case to serve different decision support mandates. For example, in the short, daily, term building level, forecasting may serve as a performance baseline. On the other end, we have long-term, policy-oriented forecasting exercises. TIMES (an acronym for The Integrated Markal Efom System) allows us to model supply and anticipated technology shifts over a long-term horizon, often extending as far away in time as 2100. Between these two time frames, we also have a mid-term forecasting time frame, that of a few years ahead. Investigations here are aimed at policy support, although in a more mid-term horizon, we address issues such as investment planning and pricing. In this paper, we develop and evaluate statistical and neural network approaches for this mid-term forecasting of final energy and electricity for the residential sector in six EU countries (Germany, the Netherlands, Sweden, Spain, Portugal and Greece). Various possible approaches to model the explanatory variables used are presented, discussed, and assessed as to their suitability. Our end goal extends beyond model accuracy; we also include interpretability and counterfactual concepts and analysis, aiming at the development of a modelling approach that can provide decision support for strategies aimed at influencing energy demand.

scholarly journals Long Term Household Electricity Demand Forecasting Based on RNN-GBRT Model and a Novel Energy Theft Detection Method

2021 ◽  
Vol 11 (18) ◽  
pp. 8612
Author(s):  
Santanu Kumar Dash ◽  
Michele Roccotelli ◽  
Rasmi Ranjan Khansama ◽  
Maria Pia Fanti ◽  
Agostino Marcello Mangini
Keyword(s):  
Energy Demand ◽  
Demand Forecasting ◽  
Sudden Change ◽  
Electricity Demand ◽  
Gradient Boosting ◽  
Forecasting Model ◽  
Demand Forecast ◽  
Daily Consumption ◽  
Energy Provider

The long-term electricity demand forecast of the consumer utilization is essential for the energy provider to analyze the future demand and for the accurate management of demand response. Forecasting the consumer electricity demand with efficient and accurate strategies will help the energy provider to optimally plan generation points, such as solar and wind, and produce energy accordingly to reduce the rate of depletion. Various demand forecasting models have been developed and implemented in the literature. However, an efficient and accurate forecasting model is required to study the daily consumption of the consumers from their historical data and forecast the necessary energy demand from the consumer’s side. The proposed recurrent neural network gradient boosting regression tree (RNN-GBRT) forecasting technique allows one to reduce the demand for electricity by studying the daily usage pattern of consumers, which would significantly help to cope with the accurate evaluation. The efficiency of the proposed forecasting model is compared with various conventional models. In addition, by the utilization of power consumption data, power theft detection in the distribution line is monitored to avoid financial losses by the utility provider. This paper also deals with the consumer’s energy analysis, useful in tracking the data consistency to detect any kind of abnormal and sudden change in the meter reading, thereby distinguishing the tampering of meters and power theft. Indeed, power theft is an important issue to be addressed particularly in developing and economically lagging countries, such as India. The results obtained by the proposed methodology have been analyzed and discussed to validate their efficacy.

A hybrid data mining driven algorithm for long term electric peak load and energy demand forecasting

Energy ◽  
2020 ◽  
Vol 204 ◽  
pp. 117948 ◽  
Author(s):  
Mohammad-Rasool Kazemzadeh ◽  
Ali Amjadian ◽  
Turaj Amraee
Keyword(s):  
Data Mining ◽  
Energy Demand ◽  
Demand Forecasting ◽  
Peak Load ◽  
Energy Demand Forecasting ◽  
Hybrid Data

scholarly journals Strategic asset management approach for planning investment in a large-scale irrigation system

2020 ◽  
Vol 20 (6) ◽  
pp. 2165-2174
Author(s):  
Rita Salgado Brito ◽  
Helena Alegre ◽  
Pedro Machado
Keyword(s):  
Asset Management ◽  
Large Scale ◽  
Irrigation System ◽  
Time Frame ◽  
Management Approach ◽  
Investment Planning ◽  
Big Picture ◽  
System Breakdown ◽  
Functional Areas

Abstract Typically, large-scale irrigation systems are built almost entirely in a short time-frame, a significant part of the assets age at the same time and concentrated investment needs for rehabilitation are predictable. This paper focuses on planning these needs in an aggregated way, providing a big picture for the long term investment plan. A methodology for this purpose was developed and applied to a large-scale irrigation utility in Portugal. For such, the following steps were taken: (i) system breakdown by functional areas; (ii) infrastructure components disaggregation; (iii) diagnosis of the reference situation; (iv) evaluation of long-term alternatives for rehabilitation investment planning. The methodology is in line with the IAM approach recommended by IWA and the ISO55000 standards. In this paper, the specificities of this particular application, namely a proposal of irrigation component classes, and the studied alternatives, are presented. As an overall result, it was possible to indicate a path for economic sustainability without committing the infrastructure sustainability: it is based on gradual replacement of the assets reaching their useful life, combined with a constant rehabilitation rate. This paper is a contribution to an AM system for irrigation utilities, so alignment with IAM and the contribution to a broader IAM system is highlighted.

Electricity Demand Forecasting

2014 ◽  
Vol 2 (1) ◽  
pp. 1-19
Author(s):  
Fawwaz Elkarmi ◽  
Nazih Abu Shikhah
Keyword(s):  
Power System ◽  
Planning Process ◽  
Demand Forecasting ◽  
Energy Forecasting ◽  
Forecasting Models ◽  
Forecasting Methods ◽  
Long Term Forecasting ◽  
Time Frames ◽  
And Control

Forecasting is the backbone of any planning process in all fields of interest. It has a great impact on future decisions. It is also of great importance to the operation and control of business, which is reflected as profits or losses to the entity. This paper aims to provide the planner with sufficient knowledge and background of the different scopes of forecasting methods, in general, and when applied to power system field, in particular. Various load and energy forecasting models, and theoretical techniques are discussed from different perspectives, time frames, and levels. The paper presents the attributes and importance of forecasting through several cases of research conducted by the author for the Jordanian power system. In all cases the methodologies selected cover short, medium and long term forecasting periods and the results are accurate.

Long-Term Outcomes of Endoscopic Repair of Cerebrospinal Fluid Leaks and Meningoencephaloceles

2005 ◽  
Vol 19 (6) ◽  
pp. 582-587 ◽  
Author(s):  
Jodi Zuckerman ◽  
James A. Stankiewicz ◽  
James M. Chow
Keyword(s):  
Cerebrospinal Fluid ◽  
Surgical Repair ◽  
Time Frame ◽  
Csf Leak ◽  
Endoscopic Repair ◽  
Medline Search ◽  
Postoperative Time ◽  
Time Frames ◽  
Csf Leaks

Background The management and surgical approach to cerebrospinal fluid (CSF) leaks and meningoencephaloceles have undergone transformation throughout the last 10 years. It is our interest to examine the long-term surgical outcome and reoccurrence rates of CSF leaks or meningoencephaloceles in patients having endoscopic surgical repair. Methods We performed a retrospective evaluation of 50 patients that underwent endoscopic surgical repair of a CSF leak, meningoencephalocele, or both, between September 1985 and October 2003. Results Cumulatively, reoccurrence rates were 15% (7/47) among the CSF leak patients with an average time frame for reoccurrence ranging from 1 to 25 months (average, 7 months). Patients with meningoencephaloceles had an overall reoccurrence rate of 8% (1/13). In addition, a Medline search on CSF leaks and meningoencephaloceles provided the names of 32 authors that have studied outcomes of endoscopic surgical repair. Of the 151 patients still followed in the 5- to 10-year postoperative group, there were 37 recurrences of CSF leaks and 5 reoccurrences of the meningoencephaloceles with a total recurrence rate of 27% (37 + 5/151). Of the 19 patients still followed in the >10-year postoperative group, there were three reoccurrences of CSF leaks and no reoccurrences of meningoencephaloceles, giving a reoccurrence rate of 16% (3 + 0/19). Conclusion Based on our cumulative results, a reoccurrence of a CSF leak or meningoencephalocele after endoscopic repair will occur within the first 2 years postoperatively. Once patients pass these postoperative time frames they are relatively free of reoccurrence from this very effective surgical management. Endoscopic repair results are better than craniotomy with much less morbidity.

Sign in / Sign up

Export Citation Format

Share Document