A novel multi-agent decentralized win or learn fast policy hill-climbing with eligibility trace algorithm for smart generation control of interconnected complex power grids

Xi, Lei; Yu, Tao; Yang, Bo; Zhang, Xiaoshun

doi:10.1016/j.enconman.2015.06.030

Cited by 39 publications

(26 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DWoLF-PHC(k) method based MAS-SG has been developed by the authors. Some basic results are recalled in this section while more details can be found in [31].…”

Section: Mas-sg Frameworkmentioning

confidence: 99%

“…Note that WPH-VTC has to undergo a sufficient pre-learning through offline trial-and-error before the online implementation, which includes extensive explorations in CPS state space for the optimization of Q-functions and state-value functions. Previous work [28][29][30][31] and this paper choose a sinusoidal load profile in the pre-learning due to the fact that most of the signals can be transformed into the sum of series of sinusoidal signals via Fourier Transform. Thus a sinusoidal load contains sufficient information for the algorithm to learn various signals in the prelearning procedure, such that an effective online operation of the algorithm can be achieved.…”

Section: Two-area Lfc Power Systemmentioning

confidence: 99%

“…Based on the game theory, many advanced algorithms have been employed to obtain system equilibriums, such as correlated-Q (CE-Q) [25], asymmetric-Q [26], and their modifications [24]. Author's previous work on the single-agent reinforcement learning (SARL) and MAS-SG has demonstrated that an optimal AGC can be achieved when the agent number is relatively small [27][28][29][30][31][32][33][34][35]. However, multi-equilibrium may emerge as the agent number increases, which inevitably consumes longer time resulted from the extensive online calculation of all system equilibriums, and may even lead to a severe system stability collapse.…”

Section: Introductionmentioning

confidence: 99%

“…However, multi-equilibrium may emerge as the agent number increases, which inevitably consumes longer time resulted from the extensive online calculation of all system equilibriums, and may even lead to a severe system stability collapse. However, the aforementioned literatures [23][24][25][26][27][28][29][30][31][32][33][34][35] only calculated an optimal total power reference, which is then dispatched through a fixed proportion to the adjustable capacity. In general, they may not obtain an optimal dispatch due to the static optimization.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A wolf pack hunting strategy based virtual tribes control for automatic generation control of smart grid

Yang

et al. 2016

Applied Energy

Self Cite

View full text Add to dashboard Cite

“…The DWoLF-PHC(k) method based MAS-SG has been developed by the authors. Some basic results are recalled in this section while more details can be found in [31].…”

Section: Mas-sg Frameworkmentioning

confidence: 99%

Section: Two-area Lfc Power Systemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A wolf pack hunting strategy based virtual tribes control for automatic generation control of smart grid

Yang

et al. 2016

Applied Energy

Self Cite

View full text Add to dashboard Cite

“…It is assumed that ancillary services are the products that generation companies bid in electricity market in steady state and uctuations are not in the scope of this work. For more information, Lei et al [17][18][19] address the problem of devising an optimal AGC for interconnected networks based on a stochastic multi-agent strategy. It should be noted that although the amount of power sold in ancillary services market is not comparable with the amount of power traded in energy market, ancillary services are usually generated at low cost [20].…”

Section: Ancillary Services Marketmentioning

confidence: 99%

Portfolio Optimization in Electricity Market Using a Novel Risk Based Decision Making Approach

2017

View full text Add to dashboard Cite

Abstract. This paper provides generation companies (GENCOs) with a novel decisionmaking tool that accounts for both long-term and short-term risk aversion preferences and devises optimal strategies to participate in energy and ancillary services markets and forward contracts, in which the possibility of involvement in arbitrage opportunities is also considered. Because of the imprecise nature of the decision maker's judgment, appropriate modelling of risk aversion attitude of the GENCO is another challenge. This paper uses fuzzy satisfaction theory to express decision maker's attitude toward risk. Conditional Value at Risk methodology (CVaR) is utilized as the measure of risk and uncertainty sources include prices for the day-ahead energy market, Automatic Generation Control (AGC), and reserve markets. By applying the proposed method, not only trading loss over the whole scheduling horizon can be controlled, but also the amount of imposed loss during every time period can be reduced. An illustrative case study is provided for further analysis.

show abstract

Smart dispatching for energy internet with complex cyber‐physical‐social systems: A parallel dispatch perspective

Cheng

2019

Int J Energy Res

Self Cite

View full text Add to dashboard Cite

Summary Energy internet (EI) is a complex coupled multienergy system; it is essential to investigate its multienergy dispatching optimization issues. To this end, this paper first proposes a novel conception of smart dispatching for EI with a complex cyber‐physical‐social system (CPSS) network from the perspective of parallel dispatch, called parallel dispatching robot (PDR), and investigates the implementations of PDR based on smart artificial society (SAS) modeling. First, we introduce EI and describe the dispatching issues of EI. Second, we discuss several important concepts supporting the parallel dispatch conception of EI, including knowledge automation (KA), CPSS, and parallel machine learning (PML). On the basis of these, we elaborate the concept of parallel dispatch. Moreover, we construct a large closed‐loop feedback control framework of parallel dispatch for EI integrating a CPSS network based on KA and PML. Third, we establish an experimental platform for PDR research based on the proposed parallel dispatch framework. Fourth, we develop the PML‐based SAS models of a single PDR in centralized dispatching modes and group PDRs in decentralized dispatching modes to achieve crowd wisdom emergence and performance improvement in current cyber‐physical system frameworks of EI. Moreover, we design an external global closed loop for PDR to evaluate its operation stability. Lastly, we conduct a detailed discussion on PDR and offer some prospects for its engineering implementations. The biggest innovation of this paper lies in systematically proposing the smart dispatching concept and framework for complex CPSS‐based EI from the perspective of parallel dispatch and thoroughly investigating how to use SAS modeling to implement parallel dispatching and control for EI considering human and social factors, which is a major extension and theoretical improvement to existing single smart wide area robot concept and a preliminary attempt in investigating a shift from Energy 4.0 to Energy 5.0 in China.

show abstract

A novel multi-agent decentralized win or learn fast policy hill-climbing with eligibility trace algorithm for smart generation control of interconnected complex power grids

Cited by 39 publications

References 28 publications

A wolf pack hunting strategy based virtual tribes control for automatic generation control of smart grid

A wolf pack hunting strategy based virtual tribes control for automatic generation control of smart grid

Portfolio Optimization in Electricity Market Using a Novel Risk Based Decision Making Approach

Smart dispatching for energy internet with complex cyber‐physical‐social systems: A parallel dispatch perspective

Contact Info

Product

Resources

About