No abstract

No abstract

This paper presents the development of an intelligent dynamic energy management system (I-DEMS) for a smart microgrid. An evolutionary adaptive dynamic programming and reinforcement learning framework is introduced for evolving the I-DEMS online. The I-DEMS is an optimal or near-optimal DEMS capable of performing grid-connected and islanded microgrid operations. The primary sources of energy are sustainable, green, and environmentally friendly renewable energy systems (RESs), e.g., wind and solar; however, these forms of energy are uncertain and nondispatchable. Backup battery energy storage and thermal generation were used to overcome these challenges. Using the I-DEMS to schedule dispatches allowed the RESs and energy storage devices to be utilized to their maximum in order to supply the critical load at all times. Based on the microgrid's system states, the I-DEMS generates energy dispatch control signals, while a forward-looking network evaluates the dispatched control signals over time. Typical results are presented for varying generation and load profiles, and the performance of I-DEMS is compared with that of a decision tree approach-based DEMS (D-DEMS). The robust performance of the I-DEMS was illustrated by examining microgrid operations under different battery energy storage conditions.

No abstract

MOTIVATION

No abstract

Large-scale data centers (~20,000m2 ) will be the major energy consumers of the next generation. The trend towards deployment of computer systems in large numbers, in very dense configurations in racks in a data center, has resulted in very high power densities at room level. Due to high heat loads (~3MWs) in an interconnected environment, data center design based on simple energy balance with zones, is inadequate. Energy consumption of data centers can be severely increased by inadequate air handling systems and rack layouts that allow the hot and cold air streams to mix. In this paper, for the first time, we formulate nondimensional parameters to evaluate the thermal design and performance of large-scale data centers. The parameters, based on temperature and flow data, reflect the convective heat transfer and fluid flow inside the data center. These parameters have been formulated as indices that are scalable from rack level to data center level. To provide a proof of concept, computational fluid dynamic models of data centers are used to validate and demonstrate these indices. A first level design of experiment study is carried out to understand the effect of geometry and data center workload on the parameters. Different data center configurations are also investigated to understand the effectiveness of these parameters in specific cases. These parameters will not only provide an invaluable tool to understand convective heat transfer in large data centers but also suggest means to improve energy efficiency in data centers. Motivation

No abstract