Building Energy Management for Demand Response Using Kernel Lifelong Learning

Kim, Sunyong; Mowakeaa, Rami; Kim, Seung Jun; Lim, Hyuk

doi:10.1109/access.2020.2991110

Cited by 18 publications

(6 citation statements)

References 24 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the uncertainty of various environmental and psycho-economic factors such as the residents' energy consumption patterns are among the main challenges in scheduling building energy consumption. For example, the datadriven machine learning methods proves to be an efficient approach in tackling these types of challenges [67].…”

Section: B Optimization and Scheduling Methodsmentioning

confidence: 99%

Deep Learning in Energy Modeling: Application in Smart Buildings With Distributed Energy Generation

et al. 2021

View full text Add to dashboard Cite

Over 33% of final energy consumption is used in buildings which leads to nearly 40% of total direct and indirect CO 2 emissions in the world. While energy consumption is steadily rising globally, managing building energy utilization by on-site renewable energy generation can help responding this demand. This paper proposes a deep learning method based on a discrete wavelet transformation and long short-term memory method (DWT-LSTM) and a scheduling framework for the integrated modelling and management of energy demand and supply for buildings. This method considers several factors including a two-step electricity price, uncertainty in climatic factors, availability of renewable energy resources (wind and solar), energy consumption patterns in buildings, and the non-linear relationships between these parameters. This novel method analyzes and continuously learns from data patterns based on hourly, daily, weekly and monthly intervals. The method enables monitoring and controlling renewable energy generation, the share of energy imports from the grid, employment of saving strategy based on the user priority list, and energy storage management. The main objective of the proposed method is to minimize the reliance on the grid and electricity cost, especially during the peak days. The results demonstrate that the proposed method can forecast building energy demand and energy supply with a high level of accuracy, showing a 3.63-8.57% error range in hourly data prediction for one month ahead. The results also show that the method can supply 304 days (83.2%) of a year without reliance on energy grids, decreasing 87.2% in energy demand on one hand and exporting annually 7777 kWh to the grid on the other hand. In addition, the rescheduling framework decreased the imported electricity cost with the higher electricity tariff by 98 %. The combination of the deep learning forecasting, energy storage, and scheduling algorithm enables reducing annual energy import from the grid from 6709 to 858 kWh (84.3%).

show abstract

Section: B Optimization and Scheduling Methodsmentioning

confidence: 99%

Deep Learning in Energy Modeling: Application in Smart Buildings With Distributed Energy Generation

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In terms of technologies, at the top of the list and with special emphasis, are renewables (mainly solar PV), energy storage systems (mainly batteries and ultra-capacitors), and all aspects of electric mobility that require the power grid for charging purposes. Specifically, contemplating these technologies in future power grids, it is important to establish advanced metering infrastructure and demand-side management strategies (e.g., to deal with the uncertainties of power production from renewables, the consumption profiles of loads in different sectors, and cooperation of variable production of renewables with energy storage [44]), including the participation of buildings, the residential sector, and even data centers, as well as the impact of prediction errors in scenarios of demand-side management [45][46][47][48][49][50]. Specifically, the contextualization of a High Variable Renewable Energy Penetration in hybrid AC/DC grids is presented in [51].…”

Section: Hybrid Ac/dc Gridsmentioning

confidence: 99%

Review of a Disruptive Vision of Future Power Grids: A New Path Based on Hybrid AC/DC Grids and Solid-State Transformers

et al. 2021

View full text Add to dashboard Cite

Power grids are evolving with the aim to guarantee sustainability and higher levels of power quality for universal access to electricity. More specifically, over the last two decades, power grids have been targeted for significant changes, including migration from centralized to decentralized paradigms as a corollary of intensive integration of novel electrical technologies and the availability of derived equipment. This paper addresses a review of a disruptive vision of future power grids, mainly focusing on the use of hybrid AC/DC grids and solid‑state transformers technologies. Regarding hybrid AC/DC grids in particular, they are analyzed in detail in the context of unipolar and bipolar DC grids (i.e., two‑wire or three‑wire DC grids), as well as the different structures concerning coupled and decoupled AC configurations with low‑frequency or high‑frequency isolation. The contextualization of the possible configurations of solid‑state transformers and the different configurations of hybrid transformers (in the perspective of offering benefits for increasing power quality in terms of currents or voltages) is also analyzed within the perspective of the smart transformers. Additionally, the paper also presents unified multi‑port systems used to interface various technologies with hybrid AC/DC grids, which are also foreseen to play an important role in future power grids (e.g., the unified interface of renewable energy sources and energy storage systems), including an analysis concerning unified multi‑port systems for AC or DC grids. Throughout the paper, these topics are presented and discussed in the context of future power grids. An exhaustive description of these technologies is made, covering the most relevant and recent structures and features that can be developed, as well as the challenges for the future power grids. Several scenarios are presented, encompassing the mentioned technologies, and unveiling a progressive evolution that culminates in the cooperative scope of such technologies for a disruptive vision of future power grids.

show abstract

“…Different EMSs-in-Bs [92][93][94][95][96][97][98] have been proposed. Besides, there are many EMSs whose objectives are to increase BEE [99], reduce energy-use [100], optimize energy demand [101,102], increase occupants' comfort [103], manage operations at buildings [104,105], provide smart services for smart buildings [106][107][108][109] and many others have been reviewed and cited in this paper.…”

Section: Literature Reviewmentioning

confidence: 99%

Energy Management Systems and Strategies in Buildings Sector: A Scoping Review

et al. 2021

View full text Add to dashboard Cite

Energy management systems in buildings (EMSs-in-Bs) play key roles in energy saving and management to which an efficient energy management system in buildings (EMS-in-Bs) design contributes. Different scope-based designs of EMS-in-Bs are reviewed. The objective is to highlight different scope-based designs of EMS-in-Bs in which scopes of reviewed papers aim to implement a function of, for example, "monitor energy performance", "estimate energy-use", or "control energy-use". This paper aims to constitute a comprehensive conception of how efficient such an EMS-in-Bs to perform more than one scope (i.e., function). Meaning, is the proposed EMS-in-Bs able to perform several sequential functions? This paper's contribution is to give a function-focused EMS's review utilizing the scope of reviewed papers. That is, reviewed papers are classified based on the scope/function the selected EMS-in-Bs is designed for. This could help select an EMS-in-Bs to perform certain scope/function(s). Another contribution is that, numerous EMSsin-Bs are reviewed in a classified way so that the most adequate EMS-in-Bs for a certain scenario considering the performed scopes/functions e.g., "monitor" are highlighted. Findings showed that "control-optimize"functioned EMS-in-Bs achieved highest energy-saving rates ~30% compared to "estimate-predict" with 10%. Findings, insights given by reviewed studies, current problems faced, future directions, and remarks are drawn in conclusion. Analysis done on reviewed papers has found that the highest and lowest averagedenergy saving rates were obtained with papers whose their scopes are implementing "control"-with-"optimize" and "estimate"-with-"predict", respectively. Energy saving rates for these two classes of scopes have been equal to 22.57% and 10%, respectively. We recommend that there is a need to enhance the estimation-and prediction-related EMS-in-Bs to achieve a higher energy saving rate.

show abstract

Building Energy Management for Demand Response Using Kernel Lifelong Learning

Cited by 18 publications

References 24 publications

Deep Learning in Energy Modeling: Application in Smart Buildings With Distributed Energy Generation

Deep Learning in Energy Modeling: Application in Smart Buildings With Distributed Energy Generation

Review of a Disruptive Vision of Future Power Grids: A New Path Based on Hybrid AC/DC Grids and Solid-State Transformers

Energy Management Systems and Strategies in Buildings Sector: A Scoping Review

Contact Info

Product

Resources

About