Xiao Liu PhD Thesis.pdf - Faculty of Information and Communication ...

More documents

Recommendations

Info

local fine-grained control. As analysed above, this criterion actually means that temporal constraint setting should support both coarse-grained temporal constraints and fine-grained temporal constraints. Specifically, the task of setting build time temporal constraints includes setting both coarse-grained temporal constraints (a global deadline for the entire workflow instance and several milestones for local workflow segments) and fine-grained temporal constraints (temporal constraints for individual workflow activities). However, although the overall workflow process is composed of individual workflow activities, coarse-grained temporal constraints and fine-grained temporal constraints are not in a simple relationship of linear culmination and decomposition. Meanwhile, it is impractical to set or update finegrained temporal constraints manually for a large amount of activities in scientific workflows. Since coarse-grained temporal constraints can be obtained through the negotiation process, the problem for setting fine-grained temporal constraints is how to automatically derive them based on the coarse-grained temporal constraints. To conclude, the basic requirements for temporal constraint setting in scientific cloud workflow systems can be put as: effective negotiation for setting coarsegrained temporal constraints and automatically derive fine-grained temporal constraints. 5.2 Probability Based Temporal Consistency Model In this section, we propose a novel probability based temporal consistency model which utilises the weighted joint distribution of workflow activity durations to facilitate temporal constraint setting in scientific workflow systems. 5.2.1 Weighted Joint Normal Distribution for Workflow Activity Durations To define the weighted joint distribution of workflow activity durations, we first present two assumptions on the probability distribution of activity durations. Assumption 1: The distribution of activity durations can be obtained from workflow system logs through statistical analysis [57]. Without losing generality, we assume that all the activity durations follow the normal distribution model, which 72
2 2 can be denoted as N ( µ , σ ) where µ is the expected value, σ is the variance and σ is the standard deviation [87]. Assumption 2: The activity durations are independent from each other. For the convenience of analysis, Assumption 1 chooses normal distribution to model the activity durations without losing generality. If most of the activity durations follow non-normal distribution, e.g. uniform distribution, exponential distribution, lognormal distribution or Beta distribution [49], the idea of our strategy can still be applied in a similar way given different joint distribution models. However, we will leave the detailed investigation of different distribution models as our future work. Furthermore, as it is commonly applied in the area of system simulation and performance analysis, Assumption 2 requires that the activity durations be independent from each other to facilitate the analysis of joint normal distribution. For those which do not follow the above assumptions, they can be treated by normal transformation and correlation analysis [87], or moreover, they can be ignored first when calculating joint distribution and then added up afterwards. Furthermore, we present an important formula, Formula 5.1, of joint normal distribution. If there are n independent variables of Xi ~ N( µ i, σi ) and n real numbers θ i , where n is a natural number, then the joint distribution of these variables can be obtained with the following formula [87]: Z = θ 1 X 1 + θ 2 X 2 + ... + θ n X n n i i= 1 = ∑θ X i ⎛ n n ⎜ 2 ~ N ∑θiµ i, ∑θi σi ⎝i= 1 i= 1 2 ⎞ ⎟ ⎠ 2 Formula 5.1 Based on this formula, we define the weighted joint distribution of workflow activity durations as follows. Definition 5.1: (Weighted joint distribution). For a scientific workflow process SW which consists of n activities, we denote 2 the activity duration distribution of activity a i as N( µ i, σi ) with 1 ≤ i ≤ n . Then the weighted joint distribution is defined as where ⎛ n n 2 ⎟ ⎞ ⎜ 2 2 N( µ sw, σ sw) = N ∑ wi µ i , ∑ wi σ i , ⎝i= 1 i= 1 ⎠ w i stands for the weight of activity a i that denotes the choice probability or 73
Page 1 and 2:
A Novel Probabilistic Temporal Fram
Page 3 and 4:
Declaration This thesis contains no
Page 5 and 6:
Abstract Cloud computing is a lates
Page 7 and 8:
Component 2, the state of scientifi
Page 9 and 10:
http://dx.doi.org/10.1016/j.jpdc.20
Page 11 and 12:
17. X. Liu, J. Chen, and Y. Yang, A
Page 13 and 14:
4.2 RELATED WORK AND PROBLEM ANALYS
Page 15 and 16:
STRATEGY ..........................
Page 17 and 18:
FIGURE 7.4 EXPERIMENTAL RESULTS (NO
Page 19 and 20:
Chapter 1 Introduction This thesis
Page 21 and 22:
Clearly, if the execution time of t
Page 23 and 24:
to seek all the candidates. Further
Page 25 and 26:
e unnecessary. Hence, an effective
Page 27 and 28:
temporal violations, viz. recoverab
Page 29 and 30:
In Chapter 2, we introduce the rela
Page 31 and 32:
a two-stage searching process with
Page 33 and 34:
QoS requirements. Generally speakin
Page 35 and 36:
handling strategies employed in a s
Page 37 and 38:
activity points to conduct temporal
Page 39 and 40: compensation, is believed as a suit
Page 41 and 42: successful completion. Specifically
Page 43 and 44: Chapter 4 and Chapter 5 respectivel
Page 45 and 46: etween time deficit compensation an
Page 47 and 48: service user’s requirements and t
Page 49 and 50: conducted for three times, i.e. sta
Page 51 and 52: PTDA+ACOWR as an example to introdu
Page 53 and 54: currently running. It is built on t
Page 55 and 56: workflow instance to determine whet
Page 57 and 58: framework for cost-effective delive
Page 59 and 60: pattern based forecasting strategy.
Page 61 and 62: 4.2 Related Work and Problem Analys
Page 63 and 64: 4.2.2 Problem Analysis In cloud wor
Page 65 and 66: significantly deteriorate the overa
Page 67 and 68: activity durations: characteristics
Page 69 and 70: specified with different means and
Page 71 and 72: Table 4.1 Notations Used in K-MaxSD
Page 73 and 74: 1) Duration series building As ment
Page 75 and 76: Table 4.5 Algorithm 4: Pattern Matc
Page 77 and 78: to search for those activities whic
Page 79 and 80: cycle. Here, we also trace back the
Page 81 and 82: ecognition. Sliding Window ranks in
Page 83 and 84: predicted value will be the one pre
Page 85 and 86: segmentation algorithm is capable o
Page 87 and 88: distributed soft real-time system,
Page 89: Table 5.1 Overview on the Support o
Page 93 and 94: mean iteration times or with some p
Page 95 and 96: Figure 5.4 Choice Building Block No
Page 97 and 98: activities may be omitted for the e
Page 99 and 100: 5.3.1 Calculating Weighted Joint Di
Page 101 and 102: constraints until the constraint is
Page 103 and 104: Therefore, it can be expressed as n
Page 105 and 106: Table 5.3 Specification of the Work
Page 107 and 108: and the constraint for activity X 1
Page 109 and 110: ease of discussion and to avoid the
Page 111 and 112: Unfortunately, conventional discret
Page 113 and 114: The probability consistency range w
Page 115 and 116: 6.2.3 Temporal Checkpoint Selection
Page 117 and 118: 100 times each. All the activity du
Page 119 and 120: normal distribution and correlated
Page 121 and 122: Figure 6.3 Checkpoint Selection wit
Page 123 and 124: work and problem analysis. Section
Page 125 and 126: expected time redundancy of subsequ
Page 127 and 128: the probability for self-recovery i
Page 129 and 130: skipped if self-recovery applies. A
Page 131 and 132: To evaluate the average performance
Page 133 and 134: activities and around 300 violation
Page 135 and 136: Figure 7.3 Experimental Results (No
Page 137 and 138: Figure 7.5 Cost Reduction Rate vs.
Page 139 and 140: 8.1 Related Work and Problem Analys
Page 141 and 142:
scientific processes, human interve
Page 143 and 144:
alone does not involve any time def
Page 145 and 146:
swap slower machines in the active
Page 147 and 148:
TD( a p ) L{ ( ai , R j ) | i = p +
Page 149 and 150:
For example, in Figure 8.2, local w
Page 151 and 152:
value to sample all of the solution
Page 153 and 154:
mapping task a i to resource R j fr
Page 155 and 156:
have done some simulation experimen
Page 157 and 158:
violations can still be recovered b
Page 159 and 160:
PTDA+ACOWR for Level III Violations
Page 161 and 162:
an integer from 1 to 5 where the ex
Page 163 and 164:
D: Definition for Fitness Value Fit
Page 165 and 166:
strategy; and End(Rescheduling) is
Page 167 and 168:
(a) Optimisation Ratio on Total Cos
Page 169 and 170:
makespan. In our two stage workflow
Page 171 and 172:
espectively. It is clearly that ACO
Page 173 and 174:
comparison results on the violation
Page 175 and 176:
percentiles. The average global vio
Page 177 and 178:
equivalent times of ACOWR are calcu
Page 179 and 180:
Chapter 9 Conclusions and Future Wo
Page 181 and 182:
the real world, simulation experime
Page 183 and 184:
ased temporal consistency model. Ac
Page 185 and 186:
the whole lifecycle support for hig
Page 187 and 188:
which can be further investigated i
Page 189 and 190:
Bibliography [1] W. M. P. van der A
Page 191 and 192:
Systems", ACM Trans. on Software En
Page 193 and 194:
conjunction with 23 rd Parallel and
Page 195 and 196:
Elsevier, vol. 84, no. 3, pp. 354-3
Page 197 and 198:
Distributed Computing Systems", Jou
Page 199 and 200:
Appendix: Notation Index Symbols α
Page 201 and 202:
PTR ( U ( SW ), ( a p + , a p + 1 m
show all

Xiao Liu PhD Thesis.pdf - Faculty of Information and Communication ...

You also want an ePaper? Increase the reach of your titles

Delete template?

Save as template?