Algorithmic challenges in green data centers

With data centers being the supporting infrastructure for a wide range of IT services, their efficiency has become a big concern to operators, as well as to society, for both economic and environmental reasons. The goal of this thesis is to design energy-efficient algorithms that reduce energy cost while minimizing compromise to service. We focus on the algorithmic challenges at different levels of energy optimization across the data center stack. The algorithmic challenge at the device level is to improve the energy efficiency of a single computational device via techniques such as job scheduling and speed scaling. We analyze the common speed scaling algorithms in both the worst-case model and stochastic model to answer some fundamental issues in the design of speed scaling algorithms. The algorithmic challenge at the local data center level is to dynamically allocate resources (e.g., servers) and to dispatch the workload in a data center. We develop an online algorithm to make a data center more power-proportional by dynamically adapting the number of active servers. The algorithmic challenge at the global data center level is to dispatch the workload across multiple data centers, considering the geographical diversity of electricity price, availability of renewable energy, and network propagation delay. We propose algorithms to jointly optimize routing and provisioning in an online manner. Motivated by the above online decision problems, we move on to study a general class of online problem named "smoothed online convex optimization", which seeks to minimize the sum of a sequence of convex functions when "smooth" solutions are preferred. This model allows us to bridge different research communities and help us get a more fundamental understanding of general online decision problems.

Towards conditional RNAi : shape and sequence transduction with small conditional RNAs

RNA interference (RNAi) is a powerful biological pathway allowing for sequence-specific knockdown of any gene of interest. While RNAi is a proven tool for probing gene function in biological circuits, it is limited by being constitutively ON and executes the logical operation: silence gene Y. To provide greater control over post-transcriptional gene silencing, we propose engineering a biological logic gate to implement “conditional RNAi.” Such a logic gate would silence gene Y only upon the expression of gene X, a completely unrelated gene, executing the logic: if gene X is transcribed, silence independent gene Y. Silencing of gene Y could be confined to a specific time and/or tissue by appropriately selecting gene X.

To implement the logic of conditional RNAi, we present the design and experimental validation of three nucleic acid self-assembly mechanisms which detect a sub-sequence of mRNA X and produce a Dicer substrate specific to gene Y. We introduce small conditional RNAs (scRNAs) to execute the signal transduction under isothermal conditions. scRNAs are small RNAs which change conformation, leading to both shape and sequence signal transduction, in response to hybridization to an input nucleic acid target. While all three conditional RNAi mechanisms execute the same logical operation, they explore various design alternatives for nucleic acid self-assembly pathways, including the use of duplex and monomer scRNAs, stable versus metastable reactants, multiple methods of nucleation, and 3-way and 4-way branch migration.

We demonstrate the isothermal execution of the conditional RNAi mechanisms in a test tube with recombinant Dicer. These mechanisms execute the logic: if mRNA X is detected, produce a Dicer substrate targeting independent mRNA Y. Only the final Dicer substrate, not the scRNA reactants or intermediates, is efficiently processed by Dicer. Additional work in human whole-cell extracts and a model tissue-culture system delves into both the promise and challenge of implementing conditional RNAi in vivo.

Sequence specific complexation of b DNA at sites containing g,c base pairs

A series of eight related analogs of distamycin A has been synthesized. Footprinting and affinity cleaving reveal that only two of the analogs, pyridine-2- car box amide-netropsin (2-Py N) and 1-methylimidazole-2-carboxamide-netrops in (2-ImN), bind to DNA with a specificity different from that of the parent compound. A new class of sites, represented by a TGACT sequence, is a strong site for 2-PyN binding, and the major recognition site for 2-ImN on DNA. Both compounds recognize the G•C bp specifically, although A's and T's in the site may be interchanged without penalty. Additional A•T bp outside the binding site increase the binding affinity. The compounds bind in the minor groove of the DNA sequence, but protect both grooves from dimethylsulfate. The binding evidence suggests that 2-PyN or 2-ImN binding induces a DNA conformational change.

In order to understand this sequence specific complexation better, the Ackers quantitative footprinting method for measuring individual site affinity constants has been extended to small molecules. MPE•Fe(II) cleavage reactions over a 10^5 range of free ligand concentrations are analyzed by gel electrophoresis. The decrease in cleavage is calculated by densitometry of a gel autoradiogram. The apparent fraction of DNA bound is then calculated from the amount of cleavage protection. The data is fitted to a theoretical curve using non-linear least squares techniques. Affinity constants at four individual sites are determined simultaneously. The distamycin A analog binds solely at A•T rich sites. Affinities range from 10^(6)- 10^(7)M^(-1) The data for parent compound D fit closely to a monomeric binding curve. 2-PyN binds both A•T sites and the TGTCA site with an apparent affinity constant of 10^(5) M^(-1). 2-ImN binds A•T sites with affinities less than 5 x 10^(4) M^(-1). The affinity of 2-ImN for the TGTCA site does not change significantly from the 2-PyN value. At the TGTCA site, the experimental data fit a dimeric binding curve better than a monomeric curve. Both 2-PyN and 2-ImN have substantially lower DNA affinities than closely related compounds.

In order to probe the requirements of this new binding site, fourteen other derivatives have been synthesized and tested. All compounds that recognize the TGTCA site have a heterocyclic aromatic nitrogen ortho to the N or C-terminal amide of the netropsin subunit. Specificity is strongly affected by the overall length of the small molecule. Only compounds that consist of at least three aromatic rings linked by amides exhibit TGTCA site binding. Specificity is only weakly altered by substitution on the pyridine ring, which correlates best with steric factors. A model is proposed for TGTCA site binding that has as its key feature hydrogen bonding to both G's by the small molecule. The specificity is determined by the sequence dependence of the distance between G's.

One derivative of 2-PyN exhibits pH dependent sequence specificity. At low pH, 4-dimethylaminopyridine-2-carboxamide-netropsin binds tightly to A•T sites. At high pH, 4-Me_(2)NPyN binds most tightly to the TGTCA site. In aqueous solution, this compound protonates at the pyridine nitrogen at pH 6. Thus presence of the protonated form correlates with A•T specificity.

The binding site of a class of eukaryotic transcriptional activators typified by yeast protein GCN4 and the mammalian oncogene Jun contains a strong 2-ImN binding site. Specificity requirements for the protein and small molecule are similar. GCN4 and 2-lmN bind simultaneously to the same binding site. GCN4 alters the cleavage pattern of 2-ImN-EDTA derivative at only one of its binding sites. The details of the interaction suggest that GCN4 alters the conformation of an AAAAAAA sequence adjacent to its binding site. The presence of a yeast counterpart to Jun partially blocks 2-lmN binding. The differences do not appear to be caused by direct interactions between 2-lmN and the proteins, but by induced conformational changes in the DNA protein complex. It is likely that the observed differences in complexation are involved in the varying sequence specificity of these proteins.

Sequence-function relationships in E. coli transcriptional regulation

Understanding how transcriptional regulatory sequence maps to regulatory function remains a difficult problem in regulatory biology. Given a particular DNA sequence for a bacterial promoter region, we would like to be able to say which transcription factors bind there, how strongly they bind, and whether they interact with each other and/or RNA polymerase, with the ultimate objective of integrating knowledge of these parameters into a prediction of gene expression levels. The theoretical framework of statistical thermodynamics provides a useful framework for doing so, enabling us to predict how gene expression levels depend on transcription factor binding energies and concentrations. We used thermodynamic models, coupled with models of the sequence-dependent binding energies of transcription factors and RNAP, to construct a genotype to phenotype map for the level of repression exhibited by the lac promoter, and tested it experimentally using a set of promoter variants from E. coli strains isolated from different natural environments. For this work, we sought to ``reverse engineer'' naturally occurring promoter sequences to understand how variations in promoter sequence affects gene expression. The natural inverse of this approach is to ``forward engineer'' promoter sequences to obtain targeted levels of gene expression. We used a high precision model of RNAP-DNA sequence dependent binding energy, coupled with a thermodynamic model relating binding energy to gene expression, to predictively design and verify a suite of synthetic E. coli promoters whose expression varied over nearly three orders of magnitude.

However, although thermodynamic models enable predictions of mean levels of gene expression, it has become evident that cell-to-cell variability or ``noise'' in gene expression can also play a biologically important role. In order to address this aspect of gene regulation, we developed models based on the chemical master equation framework and used them to explore the noise properties of a number of common E. coli regulatory motifs; these properties included the dependence of the noise on parameters such as transcription factor binding strength and copy number. We then performed experiments in which these parameters were systematically varied and measured the level of variability using mRNA FISH. The results showed a clear dependence of the noise on these parameters, in accord with model predictions.

Finally, one shortcoming of the preceding modeling frameworks is that their applicability is largely limited to systems that are already well-characterized, such as the lac promoter. Motivated by this fact, we used a high throughput promoter mutagenesis assay called Sort-Seq to explore the completely uncharacterized transcriptional regulatory DNA of the E. coli mechanosensitive channel of large conductance (MscL). We identified several candidate transcription factor binding sites, and work is continuing to identify the associated proteins.

Model predictive control for deferrable loads scheduling

Real-time demand response is essential for handling the uncertainties of renewable generation. Traditionally, demand response has been focused on large industrial and commercial loads, however it is expected that a large number of small residential loads such as air conditioners, dish washers, and electric vehicles will also participate in the coming years. The electricity consumption of these smaller loads, which we call deferrable loads, can be shifted over time, and thus be used (in aggregate) to compensate for the random fluctuations in renewable generation.

In this thesis, we propose a real-time distributed deferrable load control algorithm to reduce the variance of aggregate load (load minus renewable generation) by shifting the power consumption of deferrable loads to periods with high renewable generation. The algorithm is model predictive in nature, i.e., at every time step, the algorithm minimizes the expected variance to go with updated predictions. We prove that suboptimality of this model predictive algorithm vanishes as time horizon expands in the average case analysis. Further, we prove strong concentration results on the distribution of the load variance obtained by model predictive deferrable load control. These concentration results highlight that the typical performance of model predictive deferrable load control is tightly concentrated around the average-case performance. Finally, we evaluate the algorithm via trace-based simulations.

Radio-aware service-level scheduling to minimize downlink traffic delay through Mobile Edge Computing

One of the most challenging problems in mobile broadband networks is how to assign the available radio resources among the different mobile users. Traditionally, research proposals are either speci c to some type of traffic or deal with computationally intensive algorithms aimed at optimizing the delivery of general purpose traffic. Consequently, commercial networks do not incorporate these mechanisms due to the limited hardware resources at the mobile edge. Emerging 5G architectures introduce cloud computing principles to add flexible computational resources to Radio Access Networks. This paper makes use of the Mobile Edge Computing concepts to introduce a new element, denoted as Mobile Edge Scheduler, aimed at minimizing the mean delay of general traffic flows in the LTE downlink. This element runs close to the eNodeB element and implements a novel flow-aware and channel-aware scheduling policy in order to accommodate the transmissions to the available channel quality of end users.

Adaptive image sequence coding based on global and local compensability analysis

Our study of a novel technique for adaptive image sequence coding is reported. The number of reference frames and the intervals between them are adjusted to improve the temporal compensability of the input video. The bits are distributed more efficiently on different frame types according to temporal and spatial complexity of the image scene. Experimental results show that this dynamic group-of-picture (GOP) structure coding scheme is not only feasible but also better than the conventional fixed GOP method in terms of perceptual quality and SNR. (C) 1996 Society of Photo-Optical Instrumentation Engineers.

Insight on how fishing bats discern prey and adjust their mechanic and sensorial features during the attack sequence

Several insectivorous bats have included fish in their diet, yet little is known about the processes underlying this trophic shift. We performed three field experiments with wild fishing bats to address how they manage to discern fish from insects and adapt their hunting technique to capture fish. We show that bats react only to targets protruding above the water and discern fish from insects based on prey disappearance patterns. Stationary fish trigger short and shallow dips and a terminal echolocation pattern with an important component of the narrowband and low frequency calls. When the fish disappears during the attack process, bats regulate their attack increasing the number of broadband and high frequency calls in the last phase of the echolocation as well as by lengthening and deepening their dips. These adjustments may allow bats to obtain more valuable sensorial information and to perform dips adjusted to the level of uncertainty on the location of the submerged prey. The observed ultrafast regulation may be essential for enabling fishing to become cost-effective in bats, and demonstrates the ability of bats to rapidly modify and synchronise their sensorial and motor features as a response to last minute stimulus variations.