Real-time data reassurance in electrical power systems based on artificial neural networks

Minimizing energy consumption by joint radio and computing resource allocation in Cloud-RAN

The Unmanned Aerial Vehicles (UAVs), commonly known as drones, are significant in the agriculture sphere to automate the work such as: data acquisition, crop spraying among others. This paper proposes a path planning solution for a team of UAVs that is required to whiten a greenhouse’s roof, this problem having both social-economic impact, as well as scientific-technical impact. First, the space around the roof is partitioned into cells based on a 3D cell decomposition technique, labeling the cells including the surface of the roof as regions of interest (ROIs). Based on this representation, a Petri net (PN) model captures the motion of drones, while their trajectories are returned by a Mixed Integer Linear Programming (MILP) problem which optimizes the energy consumption. An adaptable strategy is used such that the MILP problem considers only the available UAVs with enough energy to reach the ROIs. The algorithm is implemented in MATLAB and the simulation results are captured in a video link, evaluating the impact of the size of the team and the precision used for mapping the environment over the running time.

The surveillance problem is to find optimal trajectories of agents that patrol a given area as evenly as possible. In this paper, we consider multiple agents with fuel constraints. The surveillance area is given by a weighted directed graph, where the weight assigned to each arc corresponds to the fuel consumption/supply. For each node, the penalty to evaluate the unattended time is introduced. Penalties, agents, and fuels are modeled by a mixed logical dynamical system model. Then, the surveillance problem is reduced to a mixed integer linear programming (MILP) problem. Based on the policy of model predictive control, the MILP problem is solved at each discrete time. In this paper, the feasibility condition for the MILP problem is derived. Finally, the proposed method is demonstrated by a numerical example.

This paper presents a metaheuristic approach to solve the transmission network expansion planning (TNEP) problem considering non-conventional solution candidates. The TNEP consists on finding the set of new elements required in a power system to meet a given future demand at a minimum cost. The TNEP traditionally considers as candidate solutions the addition of new lines and transformers. The main contribution of this work is the inclusion of non-conventional solution candidates. Such non-conventional solution candidates are namely: repowering of existing circuits and reactive shunt compensation. Also, an AC modeling of the network that allows obtaining more realistic results than the traditional DC model has been considered. The TNEP is represented by means of a non linear mixed integer programming problem which is solved through a hybrid genetic algorithm (HGA). Several tests were performed on two benchmark power systems to show the applicability and effectiveness of the proposed approach.

Knowledge representation of mathematical optimization problems and constructs for modeling

Process systems engineering is one of the many areas in which mixed integer optimisation formulations have been successfully applied. The nature of the problems requires specialised solution strategies and computer packages or callable libraries able to be extended and modified in order to accommodate new solution techniques. Object-oriented programming languages have been identified to offer these features. Process system applications are usually of large scale, and require modelling and solution techniques with high level of customisation. ooMILP is a library of C++ callable procedures for the definition, manipulation and solution of large, sparse mixed integer linear programming (MILP) problems without the disadvantages of many existing modelling languages. We first present a general approach to the packaging of numerical solvers as software components, derived from material developed for the CAPE-OPEN project. The presentation is in the context of construction and solution of Mixed Integer Linear Programming (MILP) problems. We then demonstrate how this package, based on the use of CORBA interfaces for synchronous execution within a single process, can be adapted with a minimum of problem-specific changes to provide a distributed solution.

This paper is concerned about recovering the observability of cyber-physical power grids after massive cyber attacks, which helps to achieve the cyber-physical resilience of the grids. For recovering the observability of the grid, the measurability of the Phasor Measurement Units (PMUs) and the connectivity of the communication network are needed to be restored. The PMU and communication infrastructure restorations are jointly formulated as a Mixed Integer Linear Programming (MILP) problem to minimize the observability loss of the grid over time after a cyber attack while considering the constraint of limited resources. The efficacy of the proposed optimal restoration strategy is verified by comparing with heuristic methods on the IEEE 57-bus system.

Reliability of network operation is becoming an important issue due to increase in renewable energy sources (RESs). The system controllability is degenerating, while uncertainty due to RESs is increasing and threatening the system security. We refer to the robustness of power system in this context as “Robust Power System Security.” This paper proposes a new approach to monitor the region of robust power system security taking into account the conventional N-1 security criterion against uncertainties. Forecasted RESs and demands with their confidence intervals (CIs) are specified to formulate a problem for the evaluation of the size of the worst case feasible region, where positive size implies feasibility, while negative, infeasibility. A load dispatch problem using CIs of RESs forecast is studied to evaluate the region of robust power system security. The problem is formulated as bi-level optimization, which is linearized and transformed into the mixed integer linear programming (MILP) problem. This is a new approach in the treatment of uncertainties. Simulation results show that the proposed method is a promising approach to assess the degree of feasibility of system operation and planning.

This paper studies the problem of computing an input vector for a given pair of Artificial Neural Network (ANN) and output vector, which is a kind of inverse problem. This problem has potential applications in design of new objects, especially in design of new chemical compounds. This paper focuses on ANNs in which activation functions are represented as continuous piece-wise linear functions, which can exactly represent ReLU functions and well approximate sigmoid functions. It is shown that this inverse problem can be formulated as a Mixed Integer Linear Programming Problem (MILP) with O(|V | + nb) variables and constraints, where V is a set of neurons in a given ANN and nb denotes the total number of break points over all activation functions fv, v ϵ V.

Heating Ventilation and Air Conditioning (HVAC) systems consume a significant portion of energy within corporate buildings, mainly due to the lack of stringent monitoring which results in compromising either energy efficiency or user comfort. We propose a simple optimized HVAC control system that automates the HVAC operation in real-time for an optimal cost-comfort trade-off using optimization techniques and demand response. Our system is built on top of an IoT (Internet of Things) framework, where thermal parameters from sensors and user feedback information are collected for real-time processing in our distributed cloud environment. We utilize a predictive model using time-series forecasting based on Artificial Neural Network, Multilayer Perceptron (MLP) and optimize the HVAC control problem using Mixed Integer Linear Programming (MILP) problem. User feedback is periodically obtained to set the desired temperature dynamically and is also utilized for subjective evaluation of HVAC effectiveness. Our experiments indicate that we achieve 20%-40% reduction in energy consumption (summer) approximately and maintain user thermal comfort consistently.

Predictive route choice control of destination coded vehicles with mixed integer linear programming optimization

We present a general approach to the FPGA technology mapping problem that applies to any logic block composed of lookup tables (LUTs) and can yield optimal solutions. The connections between LUTs of a logic block are modeled by virtual switches, which define a set of multiple-LUT blocks (MLBs) called an MLB-basis. We identify the MLB-bases for various commercial logic blocks. Given a n MLB-basis, we formulate FPGA mapping as a mixed integer linear programming (MILP) problem to achieve both the generality and the optimality objectives. We solve the MILP models using a general-purpose MILP solver, and present the results of mapping some ISCAS.85 benchmark circuits with a variety of commercial FPGAs. Circuits of a few hundred gates can be mapped in reasonable time using the MILP approach directly. Larger circuits can be handled by partitioning them prior to technology mapping. We show that optimal or provably near-optimal solutions can be obtained for the large ISCAS.85 benchmark circuits using partitions defined by their high-level functions.

Security constrained unit commitment (SCUC) is one of the most important daily tasks that independent system operators (ISOs) or regional transmission organizations (RTOs) must accomplish in daily electric power market. Security constraints have long been regarded as difficult constraints for unit commitment problems. If the inactive security constraints can be identified and eliminated, the SCUC problem can be greatly simplified. In this paper, a necessary and sufficient condition for a security constraint to be inactive is established. It is proved that all inactive constraints can be identified by solving a series of small-scale mixed integer linear programming (MILP) problems. More importantly, an analytical sufficient condition is established and most of the inactive constraints can be quickly identified without solving MILP or linear programming (LP) problems. A very important feature of the conditions obtained is that they are only related to the load demands and parameters of the transmission network. Numerical testing is performed for three power grids and the results are impressive. Over 85% of the security constraints are identified as inactive and the crucial transmission lines affecting the total operating cost are among those associated with the remaining security constraints, providing useful information for transmission planning.

A time-dependent shared autonomous vehicle system design problem

More realistic than deterministic vehicle routing, stochastic vehicle routing considers uncertainties in traffic. Its two representative optimization models are the probability tail (PT) and the stochastic shortest path problem with delay excess penalty (SSPD), which can be approximately solved by expressing them as mixed-integer linear programming (MILP) problems. The traditional method to solve these two MILP problems, i.e., branch and bound (B&B), suffers from exponential computation complexity because of integer constraints. To overcome this computation inefficiency, we propose a partial Lagrange multiplier method. It benefits from the total unimodularity of the incidence matrix in the models, which guarantees an optimal integer solution by only solving a linear programming (LP) problem. Thus, this partial Lagrange multiplier problem can be further solved using the subgradient method, and the proposed method can guarantee polynomial computation complexity. Moreover, we theoretically prove the convergence and the efficiency, which are also assessed by the experiments on three different scales of graphs (road networks): small scale, medium scale, and large scale. More importantly, the experimental results on the Beijing road network with real traffic data show that our method can efficiently solve the time-dependent routing problem. Additionally, the implementation on the navigation system based on the Singapore road network further confirms that our method can be applied to efficiently solve the real-world stochastic vehicle routing problem.