Dynamic Heterogeneity-Aware Coded Cooperative Computation at the Edge

Abstract

Cooperative computation is a promising approach for localized data processing at the edge, e.g., for Internet of Things (IoT). Cooperative computation advocates that computationally intensive tasks in a device could be divided into subtasks, and offloaded to other devices or servers in close proximity. However, exploiting the potential of cooperative computation is challenging mainly due to the heterogeneous and time-varying nature of edge devices. Coded computation, which advocates mixing data in sub-tasks by employing erasure codes and offloading these sub-tasks to other devices for computation, is recently gaining interest, thanks to its higher reliability, smaller delay, and lower communication costs. In this paper, we develop a coded cooperative computation framework, which we name Coded Cooperative Computation Protocol (C3P), by taking into account the heterogeneous resources of edge devices. C3P dynamically offloads coded sub-tasks to helpers and is adaptive to timevarying resources. We show that (i) task completion delay of C3P is very close to optimal coded cooperative computation solutions, (ii) the efficiency of C3P in terms of resource utilization is higher than 99%, and (iii) C3P improves task completion delay significantly as compared to baselines via both simulations and in a testbed consisting of real Android-based smartphones.

Secure Coded Cooperative Computation at the Heterogeneous Edge against Byzantine Attacks

“…using the hash function defined in (1), where c i 's are coefficients (We will discuss how c i is selected later in this section.). Next, it calculates…”

“…where x j is the j th element of vector x, and q and r are the parameters of the hash function defined in (1). β n in (3) is calculated by the master device using its local data p n,i and x. β n is used to check α n as described in the next theorem.…”

“…We compare SC 3 with the baselines (i) HW-only, which uses HW function to detect corrupted packets, while SC 3 uses both LW and HW functions gracefully. In HW-only, if a worker is detected as malicious, all the packets coming from that worker are discarded, (ii) Lower Bound, which is obtained by using C3P proposed in [1], the best known dynamic but unsecured coded cooperative computation. Note that C3P is not practical in the presence of an attacker, however it can provide a lower bound on SC 3 and the gap between Lower Bound and SC 3 shows the cost that we should pay to make our system secure against Byzantine attack, and (iii) Upper Bound provided in (7).…”

“…Our key tool is the graceful use of coded cooperative computation and homomorphic hash functions. Coded computation advocates mixing data in computationally-intensive tasks by employing erasure codes and offloading these coded tasks to other devices for computation [1]- [13]. The following canonical example demonstrates the effectiveness of coded computation.…”

“…According to Algorithm 1, the first time period T is defined as the time interval during which R + ǫ packets are received collectively from all workers. Using the dynamic packet offloading module of SC 3 , this time period is equal to R+K n∈N 1/E[βn,i] , according to (17) in [1], where E[β n,i ] is the average of per packet computing time at worker w n , n ∈ N .…”