Edge computing is a recent paradigm where the processing takes place close to the data sources. It therefore reduces latency and saves bandwidth compared to traditional cloud computing. The latter can continue to play a supportive role. Edge-cloud computing provides benefits in many use cases including distributed computation algorithms, where the processing is divided into a number of tasks that are executed in parallel on different equipment. An important relevant challenge is to allocate the appropriate resources to process the data that are continuously generated from user devices. The issue becomes more complicated when we take into account the variations in the volume of the generated data as a function of time. In this paper we present a resource allocation algorithm for distributed computation with emphasis on machine learning algorithms. We consider that the resource requirements vary with time in a semi-static way that exhibits some daily pattern. We distinguish between periodic (expected) variations that occur during the day, and sporadic variations due to unexpected events. We propose an Integer Linear Programming algorithm to allocate the periodic resource requirements. To handle the non-periodic requirements, we consider a suitable prediction algorithm coupled with a reconfiguration algorithm that allocates the predicted required resources. Our results indicate that our proposal outperforms traditional allocation algorithms in terms of resource utilization, monetary cost and achieved accuracy.

Edge computing has emerged as a computing paradigm where the application and data processing takes place close to the end devices. It decreases the distances over which data transfers are made, offering reduced delay and fast speed of action for general data processing and store/retrieve jobs. The benefits of edge computing can also be reaped for distributed computation algorithms, where the cloud also plays an assistive role. In this context, an important challenge is to allocate the required resources at both edge and cloud to carry out the processing of data that are generated over a continuous (“infinite”) time horizon. This is a complex problem due to the variety of requirements (resource needs, accuracy, delay, etc.) that may be posed by each computation algorithm, as well as the heterogeneous resources’ features (e.g., processing, bandwidth). In this work, we develop a solution for serving weakly coupled general distributed algorithms, with emphasis on machine learning algorithms, at the edge and/or the cloud. We present a dual-objective Integer Linear Programming formulation that optimizes monetary cost and computation accuracy. We also introduce efficient heuristics to perform the resource allocation. We examine various distributed ML allocation scenarios using realistic parameters from actual vendors. We quantify trade-offs related to accuracy, performance and cost of edge/cloud bandwidth and processing resources. Our results indicate that among the many parameters of interest, the processing costs seem to play the most important role for the allocation decisions. Finally, we explore interesting interactions between target accuracy, monetary cost and delay.

Networks are always progressing to support the evolving and diverse applications and the needs for improved capacity, latency and security. To this end, monitoring is key to ensuring the uninterrupted network operation and the QoS of the applications. Network Tomography uses a subset of monitoring information (corresponding to partial view of the network state) to estimate wide-sense network performance, including unmonitored parameters. In this paper, we present a novel Machine Learning (ML) formulation for Network Tomography. The proposed formulation accounts for realistic scenarios where: i) the existence of certain links of the network is not known (e.g., due to security reasons), ii) the routing is dynamic (non-deterministic), i.e., for the same origin-destination node pair, a different route may be selected depending on the state of certain links. Our simulations indicate that our proposal has better estimation accuracy compared to traditional algebraic or other ML approaches that cannot or do not take into account these two assumptions.

Edge computing has emerged as a paradigm for local computing/processing tasks, reducing the distances over which data transfers are made. Thus, an opportunity is presented for data transfer-intensive, distributed machine learning. In this paper we develop a solution for serving distributed Machine Learning (ML) training jobs at the edge– cloud continuum. We model the specific requirements of each ML job, and the features of the edge and cloud resources. Next, we develop an Integer Linear Programming algorithm to perform the resource allocation. We examine different scenarios (different processing and bandwidth costs) and quantify tradeoffs related to performance and cost of edge/cloud bandwidth and processing resources. Our simulations indicate that even though there are many parameters that determine the allocation, the processing costs seem to play on average the most important role. The cloud b/w costs can be significant in certain scenarios. Finally, in certain examined cases, significant monetary benefits can be achieved through the collaboration of both edge and cloud resources when compared to using exclusively edge or cloud resources.

In modern power systems with high penetration of renewable energy sources, the flexibility provided by distributed energy resources is becoming invaluable. Demand aggregators offer balancing energy in the real-time balancing market on behalf of flexible resources. A challenging task is the design of the offering strategy of an aggregator. In particular, it is difficult to capture the flexibility cost of a portfolio of flexibility assets within a price-quantity offer, since the costs and constraints of flexibility resources exhibit inter-temporal dependencies. In this article, we propose a generic method for constructing aggregated balancing energy offers that best represent the portfolio’s actual flexibility costs, while accounting for uncertainty in future timeslots. For the case study presented, we use offline simulations to train and compare different machine learning (ML) algorithms that receive the information about the state of the flexible resources and calculate the aggregator’s offer. Once trained, the ML algorithms can make fast decisions about the portfolio’s balancing energy offer in the real-time balancing market. Our simulations show that the proposed method performs reliably towards capturing the flexibility of the Aggregator’s portfolio and minimizing the aggregator’s imbalances.

We propose a scheme to reduce monitoring uncertainties in optical networks. The proposed scheme uses monitoring data of optical connections (lightpaths) which can be obtained from coherent optical receivers that can also function as optical performance monitors (OPM). We exploit both space and time correlation of the monitoring data in order to reduce the monitoring uncertainties. The improved accuracy can result in various benefits, the most common one is that the Quality of Transmission (QoT) can be estimated with higher accuracy which can in turn lead to more optimized decisions and lower provisioning costs. In this paper we present another application, we show how to use the obtained accurate monitoring data to localize soft failures (also referred to as QoT problems) on a per link level.