Multi-Objective Optimization of Energy Saving Control for Air Conditioning System in Data Center

Abstract

A multi-objective optimization scheme is proposed to save energy for a data center air conditioning system (ACS). Since the air handling units (AHU) and chillers are the most energy consuming facilities, the proposed energy saving control scheme aims to maximize the saved energy for these two facilities. However, the rack intake air temperature tends to increase if the energy saving control scheme applied to AHU and chillers is conducted inappropriately. Both ACS energy consumption and rack intake air temperature stabilization are set as two objectives for multi-objective optimization. The non-dominated sorting genetic algorithm II (NSGA-II) is utilized to solve the multi-objective optimization problem. In order for the NSGA-II to evaluate fitness functions that are both the ACS total power consumption and AHU outlet cold air temperature deviations from a specified range, neural network models are utilized. Feedforward neural networks are utilized to learn the power consumption models for both chillers and AHUs as well as the AHU outlet cold air temperature based on the recorded data collected in the field. The effectiveness and efficiency of the proposed energy saving control scheme is verified through practical experiments conducted on a campus data center ACS.

An Efficient HVAC Network Control for Safety Enhancement of a Typical Uninterrupted Power Supply Battery Storage Room

“…It is because the necessity of energy efficiency, occupant health, and thermal comfort is on the rise. Some studies, such as in [57][58][59], focus on energy savings and lack control of temperature evaluation in battery rooms. Despite the state-of-the-art analysis of the available literature, the study focus is mainly on the residential building which includes offices.…”

“…Existing literature report intelligent control methods, which include model predictive control (MPC), gain scheduling, optimal control, robust control, nonlinear adaptive control, fuzzy logic, genetic algorithm, etc., [32,34,35,38,[40][41][42][43][44][45][46][47][48][51][52][53][56][57][58][59][67][68][69][70][71][72][73][74][75][76][77][78][79][80][81][82][83][84]. As compared with PIDs as proposed in this study via mixing loops, they are robust and energy efficient.…”

A detailed Study on Data Centre Energy Efficiency and Efficient Cooling Techniques

“…The company provides a passive system named JouleForce conductor for using the filtered, non-refrigerated and ambient air for whisking the heat and temperature away from computer. Leehter Yao et.al [44] emphasised on a multi-objective optimization scheme that can save the energy for the ACS (air conditioning system) of a data centre. The main objective of the proposed scheme is to increase the saved energy for AHU [air handling units] and Chillers, two most energy consuming services.…”

Wind Farm Area Shape Optimization Using Newly Developed Multi-Objective Evolutionary Algorithms

“…MO optimization has been used in many different fields, especially in problems involving some economic variable with a problem-specific feature, e.g., residential comfort [23], safety of infrastructures [24], energetic performance (e.g., [25]) or environmental objective functions (e.g., [26][27][28]), including those addressing wind power (e.g., [29][30][31]). Other fields in which MO optimization has provided successful insight include finance, (e.g., [32,33]), optimal control design (e.g., [34,35]) or industrial processes (e.g., [36,37]).…”

“…In addition, we conceive that the developed routine must keep the total available area (in terms of km 2 ) constrained, to keep the same amount of sea surface usage, and to ensure that any potential improvement is due to the shape optimization instead of a mere area increase. Here we design a novel MO, WFLO-oriented algorithm inspired by our previous algorithm in [39], and compare it to the Non-dominated Sorting Genetic Algorithm version II (NSGA-II [69]), a MO algorithm widely used in the context of industrial processes [36,37,70], including those considering wind energy (e.g., [40,71]). Furthermore, a set of 11 additional algorithms, with different variations from the two are also developed and tested.…”