A Structured Methodology for Pattern based Adaptive Scheduling in Embedded Control

Ghosh, Sumana; Dutta, Souradeep; Dey, Soumyajit; Dasgupta, Pallab

doi:10.1145/3126514

Cited by 11 publications

(13 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This choice ensures that the norm of the control output reduces by a factor of

ϵ

in l consecutive control loop iterations. In order to satisfy this minimum decay rate requirement and the related exponential stability requirement, we compute a bound on the minimum rate of control execution [13] as follows.…”

Section: Deriving Target Specification From Stability and Performancementioning

confidence: 99%

“…For each j ,

1 \leq j \leq l_{i}

, if

ρ_{i} false[j false]

1

(i.e. there is a loop execution instance), we add a periodic control task into

T_{i}

, having a set of task instantiations:

falsefalse{falsefalse⟨ i, a_{s}, e_{i}, a_{s} + h_{i} falsefalse⟩ | a_{s} = false(j + s \times l_{i} false) \times h_{i}, s = 0, 1, \dots falsefalse}

, where

a_{s}

represents the arrival time of the

false(s + 1 false)

th instance of

ρ_{i} false[j false]

h_{i}

is the sampling period of the i th loop, and

a_{s} + h_{i}

is the deadline for that

false(s + 1 false)

th instance [13]. Therefore, we have a set of periodic tasks in

double-struckT = ⋃_{1 \leq i \leq n} T_{i}

corresponding to n loop execution patterns

falsefalse{ρ_{1}, ρ_{2}, \dots, ρ_{n} falsefalse}

.…”

Section: Synthesising Performance‐ and Energy‐aware Robust Loop Execumentioning

confidence: 99%

“…The necessary and sufficient conditions for EDF scheduling of n control loops executed according to a combination of patterns,

falsefalse{ρ_{1}, ρ_{2}, \dots, ρ_{n} falsefalse}

, on a shared pre‐emptive ECU have been introduced in [13]. Let

B R false(ρ_{i}, false[t_{1}, t_{2} false) false)

be the cumulative execution requirement of the control tasks initiated according to some loop execution pattern

ρ_{i}

within any finite time interval

false[t_{1}, t_{2} false)

.…”

Section: Synthesising Performance‐ and Energy‐aware Robust Loop Execumentioning

confidence: 99%

“…Let

B R false(ρ_{i}, false[t_{1}, t_{2} false) false)

be the cumulative execution requirement of the control tasks initiated according to some loop execution pattern

ρ_{i}

within any finite time interval

false[t_{1}, t_{2} false)

. Therefore, the total bandwidth requirement of all the control tasks initiated according to

falsefalse{ρ_{1}, \dots, ρ_{n} falsefalse}

B R false(ρ_{1}, \dots, ρ_{n}, false[t_{1}, t_{2} false) false) = \sum_{i = 1}^{n} B R false(ρ_{i}, false[t_{1}, t_{2} false) false)

Following [13, 19], the necessary and sufficient condition for n control loops executed according to the loop execution patterns,

falsefalse{ρ_{1}, \dots, ρ_{n} falsefalse}

, to be feasible on a shared pre‐emptive ECU using EDF policy, is

B R false(ρ_{1}, \dots, ρ_{n}, false[t_{1}, t_{2} false) false) \leq false(t_{2} - t_{1} false), normal∀ t_{1}, t_{2}, t_{1} < t_{2} \leq t_{B}

where

t_{B} = l c m false(l_{1} \times h_{1}, l_{2} \times h_{2}, \dots, l_{n} \times h_{n} false)

is the hyper‐period. The schedulability constraint is checked up to the time horizon

t_{B}

since within this hyper‐period,

t_{B}

, each pattern repeats a finite number of times.…”

Section: Synthesising Performance‐ and Energy‐aware Robust Loop Execumentioning

confidence: 99%

See 3 more Smart Citations

Performance and energy aware robust specification of control execution patterns under dropped samples

Ghosh

Dey

Dasgupta

2019

IET Computers & Digital Techniques

Self Cite

View full text Add to dashboard Cite

“…This choice ensures that the norm of the control output reduces by a factor of

ϵ

Section: Deriving Target Specification From Stability and Performancementioning

confidence: 99%

“…For each j ,

1 \leq j \leq l_{i}

, if

ρ_{i} false[j false]

1

(i.e. there is a loop execution instance), we add a periodic control task into

T_{i}

, having a set of task instantiations:

falsefalse{falsefalse⟨ i, a_{s}, e_{i}, a_{s} + h_{i} falsefalse⟩ | a_{s} = false(j + s \times l_{i} false) \times h_{i}, s = 0, 1, \dots falsefalse}

, where

a_{s}

represents the arrival time of the

false(s + 1 false)

th instance of

ρ_{i} false[j false]

h_{i}

is the sampling period of the i th loop, and

a_{s} + h_{i}

is the deadline for that

false(s + 1 false)

th instance [13]. Therefore, we have a set of periodic tasks in

double-struckT = ⋃_{1 \leq i \leq n} T_{i}

corresponding to n loop execution patterns

falsefalse{ρ_{1}, ρ_{2}, \dots, ρ_{n} falsefalse}

.…”

Section: Synthesising Performance‐ and Energy‐aware Robust Loop Execumentioning

confidence: 99%

“…The necessary and sufficient conditions for EDF scheduling of n control loops executed according to a combination of patterns,

falsefalse{ρ_{1}, ρ_{2}, \dots, ρ_{n} falsefalse}

, on a shared pre‐emptive ECU have been introduced in [13]. Let

B R false(ρ_{i}, false[t_{1}, t_{2} false) false)

be the cumulative execution requirement of the control tasks initiated according to some loop execution pattern

ρ_{i}

within any finite time interval

false[t_{1}, t_{2} false)

.…”

Section: Synthesising Performance‐ and Energy‐aware Robust Loop Execumentioning

confidence: 99%

“…Let

B R false(ρ_{i}, false[t_{1}, t_{2} false) false)

be the cumulative execution requirement of the control tasks initiated according to some loop execution pattern

ρ_{i}

within any finite time interval

false[t_{1}, t_{2} false)

. Therefore, the total bandwidth requirement of all the control tasks initiated according to

falsefalse{ρ_{1}, \dots, ρ_{n} falsefalse}

B R false(ρ_{1}, \dots, ρ_{n}, false[t_{1}, t_{2} false) false) = \sum_{i = 1}^{n} B R false(ρ_{i}, false[t_{1}, t_{2} false) false)

Following [13, 19], the necessary and sufficient condition for n control loops executed according to the loop execution patterns,

falsefalse{ρ_{1}, \dots, ρ_{n} falsefalse}

, to be feasible on a shared pre‐emptive ECU using EDF policy, is

B R false(ρ_{1}, \dots, ρ_{n}, false[t_{1}, t_{2} false) false) \leq false(t_{2} - t_{1} false), normal∀ t_{1}, t_{2}, t_{1} < t_{2} \leq t_{B}

where

t_{B} = l c m false(l_{1} \times h_{1}, l_{2} \times h_{2}, \dots, l_{n} \times h_{n} false)

is the hyper‐period. The schedulability constraint is checked up to the time horizon

t_{B}

since within this hyper‐period,

t_{B}

, each pattern repeats a finite number of times.…”

Section: Synthesising Performance‐ and Energy‐aware Robust Loop Execumentioning

confidence: 99%

See 2 more Smart Citations

Performance and energy aware robust specification of control execution patterns under dropped samples

Ghosh

Dey

Dasgupta

2019

IET Computers & Digital Techniques

Self Cite

View full text Add to dashboard Cite

“…The pattern exhibiting best control performance may lack in attack resilience. Also, the dependence of control performance on the skipping pattern of a control schedule is nonlinear [7]. Hence, formulating a single step optimization framework for maximizing both control performance and attack resilience of a CPS is not a scalable approach.…”

Section: Introductionmentioning

confidence: 99%

Skip to Secure: Securing Cyber-physical Control Loops with Intentionally Skipped Executions

Adhikary¹,

Koley²,

Ghosh³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

We consider the problem of provably securing a given control loop implementation in the presence of adversarial interventions on data exchange between plant and controller. Such interventions can be thwarted using continuously operating monitoring systems and also cryptographic techniques, both of which consume network and computational resources. We provide a principled approach for intentional skipping of control loop executions which may qualify as a useful control theoretic countermeasure against stealthy attacks which violate message integrity and authenticity. As is evident from our experiments, such a control theoretic counter-measure helps in lowering the cryptographic security measure overhead and resulting resource consumption in Control Area Network (CAN) based automotive CPS without compromising performance and safety.

show abstract

GoodSpread: Criticality-Aware Static Scheduling of CPS with Multi-QoS Resources

Roy

Ghosh

Zhu

et al. 2020

2020 IEEE Real-Time Systems Symposium (RTSS)

View full text Add to dashboard Cite

A Structured Methodology for Pattern based Adaptive Scheduling in Embedded Control

Cited by 11 publications

References 16 publications

Performance and energy aware robust specification of control execution patterns under dropped samples

Performance and energy aware robust specification of control execution patterns under dropped samples

Skip to Secure: Securing Cyber-physical Control Loops with Intentionally Skipped Executions

GoodSpread: Criticality-Aware Static Scheduling of CPS with Multi-QoS Resources

Contact Info

Product

Resources

About