Dataset Information

Implementation of real-time energy management strategy based on reinforcement learning for hybrid electric vehicles and simulation validation.

ABSTRACT: To further improve the fuel economy of series hybrid electric tracked vehicles, a reinforcement learning (RL)-based real-time energy management strategy is developed in this paper. In order to utilize the statistical characteristics of online driving schedule effectively, a recursive algorithm for the transition probability matrix (TPM) of power-request is derived. The reinforcement learning (RL) is applied to calculate and update the control policy at regular time, adapting to the varying driving conditions. A facing-forward powertrain model is built in detail, including the engine-generator model, battery model and vehicle dynamical model. The robustness and adaptability of real-time energy management strategy are validated through the comparison with the stationary control strategy based on initial transition probability matrix (TPM) generated from a long naturalistic driving cycle in the simulation. Results indicate that proposed method has better fuel economy than stationary one and is more effective in real-time control.

SUBMITTER: Kong Z

PROVIDER: S-EPMC5495435 | biostudies-literature | 2017

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Implementation of real-time energy management strategy based on reinforcement learning for hybrid electric vehicles and simulation validation.

Kong Zehui Z Zou Yuan Y Liu Teng T

PloS one 20170703 7

To further improve the fuel economy of series hybrid electric tracked vehicles, a reinforcement learning (RL)-based real-time energy management strategy is developed in this paper. In order to utilize the statistical characteristics of online driving schedule effectively, a recursive algorithm for the transition probability matrix (TPM) of power-request is derived. The reinforcement learning (RL) is applied to calculate and update the control policy at regular time, adapting to the varying drivi ...[more]

PMID: 28671967

Similar Datasets

Project description:Traction batteries are a key factor in the environmental sustainability of electric mobility and, therefore, it is necessary to evaluate their environmental performance to allow a comprehensive sustainability assessment of electric mobility. This article presents an environmental assessment of a lithium-ion traction battery for plug-in hybrid electric vehicles, characterized by a composite cathode material of lithium manganese oxide (LiMn2O4) and lithium nickel manganese cobalt oxide Li(NixCoyMn1-x-y)O2. Composite cathode material is an emerging technology that promises to combine the merits of several active materials into a hybrid electrode to optimize performance and reduce costs. In this study, the environmental assessment of one battery pack (with a nominal capacity of 11.4 kWh able to be used for about 140,000 km of driving) is carried out by using the Life Cycle Assessment methodology consistent with ISO 14040. The system boundaries are the battery production, the operation phase and recycling at the end of life, including the recovery of various material fractions. The composite cathode technology examined besides a good compromise between the higher and the lower performance of NMC and LMO cathodes, can present good environmental performances. The results of the analysis show that the manufacturing phase is relevant to all assessed impact categories (contribution higher than 60%). With regard to electricity losses due to battery efficiency and battery transport, the contribution to the use phase impact of battery efficiency is larger than that of battery transport. Recycling the battery pack contributes less than 11% to all of the assessed impact categories, with the exception of freshwater ecotoxicity (60% of the life cycle impact). The environmental credits related to the recovery of valuable materials (e.g. cobalt and nickel sulphates) and other metal fractions (e.g. aluminium and steel) are particularly relevant to impact categories such as marine eutrophication, human toxicity and abiotic resource depletion. The main innovations of this article are that (1) it presents the first bill of materials of a lithium-ion battery cell for plug-in hybrid electric vehicles with a composite cathode active material; (2) it describes one of the first applications of the life cycle assessment to a lithium-ion battery pack for plug-in hybrid electric vehicles with a composite cathode active material with the aim of identifying the "hot spots" of this technology and providing useful information to battery manufacturers on potentially improving its environmental sustainability; (3) it evaluates the impacts associated with the use phase based on primary data about the battery pack's lifetime, in terms of kilometres driven; and (4) it models the end-of-life phase of the battery components through processes specifically created for or adapted to the case study.

Project description:The idea that households produce and consume their own energy, that is, energy self-sufficiency at a very local level, captures the popular imagination and commands political support across parts of Europe. This paper investigates the technical and economic feasibility of household energy self-sufficiency in Switzerland, which can be seen as representative for other regions with a temperate climate, by 2050. We compare sixteen cases that vary across four dimensions: household type, building type, electricity demand reduction, and passenger vehicle use patterns. We assume that photovoltaic (PV) electricity supplies all energy, which implies a complete shift away from fossil fuel based heating and internal combustion engine vehicles. Two energy storage technologies are considered: short-term storage in lithium-ion batteries and long-term storage with hydrogen, requiring an electrolyzer, storage tank, and a fuel cell for electricity conversion. We examine technological feasibility and total system costs for self-sufficient households compared to base cases that rely on fossil fuels and the existing power grid. PV efficiency and available rooftop/facade area are most critical with respect to the overall energy balance. Single-family dwellings with profound electricity demand reduction and urban mobility patterns achieve self-sufficiency most easily. Multi-family buildings with conventional electricity demand and rural mobility patterns can only be self-sufficient if PV efficiency increases, and all of the roof plus most of the facade can be covered with PV. All self-sufficient cases are technically feasible but more expensive than fully electrified grid-connected cases. Self-sufficiency may even become cost-competitive in some cases depending on storage and fossil fuel prices. Thus, if political measures improve their financial attractiveness or individuals decide to shoulder the necessary investments, self-sufficient buildings may start to become increasingly prevalent.

Dataset Information

Implementation of real-time energy management strategy based on reinforcement learning for hybrid electric vehicles and simulation validation.

Publications

Implementation of real-time energy management strategy based on reinforcement learning for hybrid electric vehicles and simulation validation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets