Time-Coordinated Multienergy Management of Smart Buildings Under Uncertainties

Sharma, Sumedha; Xu, Yan; Verma, Ashu; Panigrahi, Bijaya Ketan

doi:10.1109/tii.2019.2901120

Cited by 62 publications

(35 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After taking an action, the agent acquires an immediate reward ( , ), observes the next state +1 and updates the Q-value ( , ) via Eq. (8). This process is repeated until the state +1 is terminal.…”

Section: Repeatmentioning

confidence: 99%

See 1 more Smart Citation

A Multi-Agent Reinforcement Learning-Based Data-Driven Method for Home Energy Management

Jia

et al. 2020

IEEE Trans. Smart Grid

Self Cite

285

107

View full text Add to dashboard Cite

This paper proposes a novel framework for home energy management (HEM) based on reinforcement learning in achieving efficient home-based demand response (DR). The concerned hour-ahead energy consumption scheduling problem is duly formulated as a finite Markov decision process (FMDP) with discrete time steps. To tackle this problem, a data-driven method based on neural network (NN) and Q-learning algorithm is developed, which achieves superior performance on cost-effective schedules for HEM system. Specifically, real data of electricity price and solar photovoltaic (PV) generation are timely processed for uncertainty prediction by extreme learning machine (ELM) in the rolling time windows. The scheduling decisions of the household appliances and electric vehicles (EVs) can be subsequently obtained through the newly developed framework, of which the objective is dual, i.e. to minimize the electricity bill as well as the DR induced dissatisfaction. Simulations are performed on a residential house level with multiple home appliances, an EV and several PV panels. The test results demonstrate the effectiveness of the proposed data-driven based HEM framework.

show abstract

Section: Repeatmentioning

confidence: 99%

“…Ref. [8] proposes a multi-time and multi-energy building energy management system, which is modeled as a non-linear quadratic programming problem. Ref.…”

mentioning

confidence: 99%

A Multi-Agent Reinforcement Learning-Based Data-Driven Method for Home Energy Management

Jia

et al. 2020

IEEE Trans. Smart Grid

Self Cite

285

107

View full text Add to dashboard Cite

show abstract

“…In addition, the designed DRL-based algorithm should be scalable since the number of HVAC systems in residential building microgrids or the number of zones served by an HVAC system in commercial building microgrids is large. Last but not least, the designed algorithms should deal with multi-time scale optimization problem since hydrogen storage devices and battery operate in microgrids have different time scales [4].…”

Section: E Drl-based Energy Optimization For Building Microgridsmentioning

confidence: 99%

“…For example, global buildings consumed 30% of total energy and generated 28% of total carbon emission in 2018 [3]. Moreover, the energy demand of buildings is expected to increase by 50% in the next 30 years [4]. Under the above background, smart buildings have received more and more attention in recent years, which can provide sustainable, economical and comfortable operation environments for occupants using many advanced technologies, e.g., Internet of Things (IoT), cloud computing, machine learning and big data analytics [5]- [7].…”

Section: Introductionmentioning

confidence: 99%

Deep Reinforcement Learning for Smart Home Energy Management

Xie

et al. 2020

IEEE Internet Things J.

307

View full text Add to dashboard Cite

In this paper, we investigate an energy cost minimization problem for a smart home in the absence of a building thermal dynamics model with the consideration of a comfortable temperature range. Due to the existence of model uncertainty, parameter uncertainty (e.g., renewable generation output, nonshiftable power demand, outdoor temperature, and electricity price) and temporally-coupled operational constraints, it is very challenging to determine the optimal energy management strategy for scheduling Heating, Ventilation, and Air Conditioning (HVAC) systems and energy storage systems in the smart home. To address the challenge, we first formulate the above problem as a Markov decision process, and then propose an energy management strategy based on Deep Deterministic Policy Gradients (DDPG). It is worth mentioning that the proposed strategy does not require the prior knowledge of uncertain parameters and building thermal dynamics model. Simulation results based on real-world traces demonstrate the effectiveness and robustness of the proposed strategy.

show abstract

“…TES is integrated into the proposed system to decouple the FEL and FTL modes of operation of the CCHP system. The TES in the proposed off-grid microgrid is hot-water storage that operates on the general principle of energy storage, as follows [68]:…”

Section: Thermal Energy Storage (Tes)mentioning

confidence: 99%

Optimal sizing and multi‐energy management strategy for PV‐biofuel‐based off‐grid systems

2020

Self Cite

View full text Add to dashboard Cite

This study proposes a comprehensive framework for developing a multi-energy off-grid microgrid with the decoupled flow of thermal and electrical energies in a rural setting. A carbon-neutral microgrid with a hybrid generation system constituting a photovoltaic unit and a biofuel generator is proposed. In order to enhance the fuel utilisation efficiency, the biofuel generator is operated in combined cooling, heating, and power mode, and the recovered thermal energy forms the heat distribution network in the microgrid. The flexibility of system operation is improved by suitable multi-energy (electrical and thermal) storage. Firstly, an optimal sizing framework has been developed for the system as a mixed integer linear programming model. Secondly, a coordinated multi-energy management system (MEMS) has been developed for combined optimal dispatch of multiple generation and storage resources. The MEMS has been developed as a mixed integer non-linear programming model, which minimises system operational cost while considering minimum battery degradation to prolong its lifetime. Finally, a detailed economic analysis of the proposed system has been presented, highlighting the levellised cost of energy and net present value. Extensive case studies and simulation results depict the effectiveness and suitability of the proposed MEMS for the rural off-grid microgrid.

show abstract

Time-Coordinated Multienergy Management of Smart Buildings Under Uncertainties

Cited by 62 publications

References 26 publications

A Multi-Agent Reinforcement Learning-Based Data-Driven Method for Home Energy Management

A Multi-Agent Reinforcement Learning-Based Data-Driven Method for Home Energy Management

Deep Reinforcement Learning for Smart Home Energy Management

Optimal sizing and multi‐energy management strategy for PV‐biofuel‐based off‐grid systems

Contact Info

Product

Resources

About