Peer-to-Peer Energy Trading and Energy Conversion in Interconnected Multi-Energy Microgrids Using Multi-Agent Deep Reinforcement Learning
Keyword
CogenerationEnergy conversion
Heat pumps
Hydrogen
Multi-agent deep reinforcement learning
Multi-energy microgrids
Natural gas
P2P energy trading
Peer-to-peer computing
Reinforcement learning
Resistance heating
Metadata
Show full item recordAbstract
A key aspect of multi-energy microgrids (MEMGs) is the capability to efficiently convert and store energy in order to reduce the costs and environmental impact. Peer-to-peer (P2P) energy trading is a novel paradigm for decentralized energy market designs. In this paper, we investigate the external P2P energy trading problem and internal energy conversion problem within interconnected residential, commercial and industrial MEMGs. These two problems are complex decision-making problems with enormous high-dimensional data and uncertainty, so a multi-agent deep reinforcement learning approach combining the multi-agent actor-critic algorithm with the twin delayed deep deterministic policy gradient algorithm is proposed. The proposed approach can handle the high-dimensional continuous action space and aligns with the nature of P2P energy trading with multiple MEMGs. Simulation results based on three real-world MG datasets show that the proposed approach significantly reduces each MG's average hourly operation cost. The impact of carbon tax pricing is also considered.ae974a485f413a2113503eed53cd6c53
10.1109/TSG.2021.3124465
Scopus Count
Collections
Related items
Showing items related by title, author, creator and subject.
-
National energy policies of the Federal Republic of Germany and Canada in the 1970s and 1980s: are economic and/or environmental concerns responsible for change?Pfleger, Anita Angelika.; Department of Political Science (Brock University, 1991-07-09)The thesis presents a comparison of the national energy policies of the Federal Republic of Germany and Canada from 1973 until the late 1980s. The purpose of this paper is to analyze whether economic and/or environmental concerns were responsible for changes in the· West-German and Canadian national energy policies. Furthermore, the feasibility of implementing a soft energy path in West-Germany and Canada is examined. For better comprehension of the policy-making process and implemented changes in the national energy policies of the two states, the West-German and Canadian parliamentary systems and the political cultures were compared. For the analysis, several events with international impact were taken as guidelines. Furthermore, based on statistical data, the West-German and Canadian energy production and consumption were analyzed. With reference to these results the degree of the de facto changes in the national energy policies were analyzed. In addition, the thesis discusses the possibilities which a soft energy path offers to both national governments to renounce themselves from the dependencies on a few energy resources. The thesis reveals that changes in the West-German and Canadian national energy policies, in their energy production and consumption are correlated to various world events. In particular, governmental reponses security of energy supply by the two international oil crises of 1973 and 1979/1980 demonstrate that changes in the West-German and Canadian national energy policies were implemented in reaction to economic concerns than environmental ones. With the policies "away from oil" and "off oil", the West-German and Canadian government implemented the i i substitution of oil through various diverse energy supply resources. However, energy savings concepts and policies were initiated through the first oil crisis in 1973. The world recessions in 1975 and 1982 had no 'profound impacts on the agenda of West-German and Canadian energy policies. As a consequence of the stagnation or the negative growth of the world economic market, changes in their energy production and consumption can be perceived. However, the West-German and Canadian energy production and consumption intensified with the augmentation of the world economy. During the period of study, environmental concerns were taken into account in the energy policy agendas of the Federal Republic of Germany and Canada but they were not of primary concern. wi thin the decade of. the 1980s notably more environmental considerations were taken into account in the energy policies of the two states. The two nuclear reactor accidents in 1979 and 1986 sharpened to various degrees West-German and Canadian public discourse of present energy supply mix and attitude towards energy production and consumption. The statistical data reflects yet no changes in the energy policies in regard to the position of nuclear power. However, in the next several years possible changes can be observed through statistical data, because the planning, the construction and possible phase out of nuclear power requires several years. Finally, the thesis reveals that the implementation of a soft energy path requires profound changes in the consumer behaviour. As several studies indicate, a soft energy path is technological and economically feasible for the Federal Republic of Germany and Canada, its implementation remains to be a political decision.
-
Co-Optimizing Battery Storage for Energy Arbitrage and Frequency Regulation in Real-Time Markets Using Deep Reinforcement LearningMiao, Yushen; Chen, Tianyi; Bu, Shengrong; Liang, Hao; Han, Zhu (MDPI, 2021)Battery energy storage systems (BESSs) play a critical role in eliminating uncertainties associated with renewable energy generation, to maintain stability and improve flexibility of power networks. In this paper, a BESS is used to provide energy arbitrage (EA) and frequency regulation (FR) services simultaneously to maximize its total revenue within the physical constraints. The EA and FR actions are taken at different timescales. The multitimescale problem is formulated as two nested Markov decision process (MDP) submodels. The problem is a complex decision-making problem with enormous high-dimensional data and uncertainty (e.g., the price of the electricity). Therefore, a novel co-optimization scheme is proposed to handle the multitimescale problem, and also coordinate EA and FR services. A triplet deep deterministic policy gradient with exploration noise decay (TDD-ND) approach is used to obtain the optimal policy at each timescale. Simulations are conducted with real-time electricity prices and regulation signals data from the American PJM regulation market. The simulation results show that the proposed approach performs better than other studied policies in literature.
-
The band structure of Cd0Leaver, Alan.; Department of Physics (Brock University, 1978-07-09)The Augmented Pl ane Wave Method has been used to calculate the one-electron energy band structure of CdO. Energy eigenva l ues were calculated along three symmetry lines and for some other general wave-vectors of interest.